30,302 results on '"image compression"'
Search Results
2. Asymmetric Learned Image Compression Using Fast Residual Channel Attention
- Author
-
Hu, Yusong, Jung, Cheolkon, Liu, Yang, Li, Ming, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Antonacopoulos, Apostolos, editor, Chaudhuri, Subhasis, editor, Chellappa, Rama, editor, Liu, Cheng-Lin, editor, Bhattacharya, Saumik, editor, and Pal, Umapada, editor
- Published
- 2025
- Full Text
- View/download PDF
3. Lossy Image Compression with Foundation Diffusion Models
- Author
-
Relic, Lucas, Azevedo, Roberto, Gross, Markus, Schroers, Christopher, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Leonardis, Aleš, editor, Ricci, Elisa, editor, Roth, Stefan, editor, Russakovsky, Olga, editor, Sattler, Torsten, editor, and Varol, Gül, editor
- Published
- 2025
- Full Text
- View/download PDF
4. Rethinking Image Super-Resolution from Training Data Perspectives
- Author
-
Ohtani, Go, Tadokoro, Ryu, Yamada, Ryosuke, Asano, Yuki M., Laina, Iro, Rupprecht, Christian, Inoue, Nakamasa, Yokota, Rio, Kataoka, Hirokatsu, Aoki, Yoshimitsu, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Leonardis, Aleš, editor, Ricci, Elisa, editor, Roth, Stefan, editor, Russakovsky, Olga, editor, Sattler, Torsten, editor, and Varol, Gül, editor
- Published
- 2025
- Full Text
- View/download PDF
5. Implementing, Specifying, and Verifying the QOI Format in Dafny: A Case Study
- Author
-
Ciobâcă, Ştefan, Gratie, Diana-Elena, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Kosmatov, Nikolai, editor, and Kovács, Laura, editor
- Published
- 2025
- Full Text
- View/download PDF
6. Enhanced Discrete Cosine Transform Image Compression for Ultra-High-Resolution Imagery
- Author
-
Narlagiri, Shilpa, Malathy, V., Vanamala, Kedhareshwar Rao, Ganja, Sri Sai Sathyanarayana, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Tan, Kay Chen, Series Editor, Shrivastava, Vivek, editor, Bansal, Jagdish Chand, editor, and Panigrahi, B. K., editor
- Published
- 2025
- Full Text
- View/download PDF
7. BaSIC: BayesNet Structure Learning for Computational Scalable Neural Image Compression
- Author
-
Zhang, Yufeng, Yu, Hang, Liu, Shizhan, Dai, Wenrui, Lin, Weiyao, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Leonardis, Aleš, editor, Ricci, Elisa, editor, Roth, Stefan, editor, Russakovsky, Olga, editor, Sattler, Torsten, editor, and Varol, Gül, editor
- Published
- 2025
- Full Text
- View/download PDF
8. GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting
- Author
-
Zhang, Xinjie, Ge, Xingtong, Xu, Tongda, He, Dailan, Wang, Yan, Qin, Hongwei, Lu, Guo, Geng, Jing, Zhang, Jun, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Leonardis, Aleš, editor, Ricci, Elisa, editor, Roth, Stefan, editor, Russakovsky, Olga, editor, Sattler, Torsten, editor, and Varol, Gül, editor
- Published
- 2025
- Full Text
- View/download PDF
9. Perceptual Image Compression with Text-Guided Multi-level Fusion
- Author
-
Hu, Jiaqi, Zhuang, Jiedong, Liang, Xiaoyu, Wang, Dayong, Yu, Lu, Hu, Haoji, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Lin, Zhouchen, editor, Cheng, Ming-Ming, editor, He, Ran, editor, Ubul, Kurban, editor, Silamu, Wushouer, editor, Zha, Hongbin, editor, Zhou, Jie, editor, and Liu, Cheng-Lin, editor
- Published
- 2025
- Full Text
- View/download PDF
10. Beyond Learned Metadata-Based Raw Image Reconstruction.
- Author
-
Wang, Yufei, Yu, Yi, Yang, Wenhan, Guo, Lanqing, Chau, Lap-Pui, Kot, Alex C., and Wen, Bihan
- Subjects
- *
IMAGE reconstruction , *BIT rate , *IMAGE representation , *SPATIAL resolution , *MASK laws , *IMAGE compression , *METADATA - Abstract
While raw images possess distinct advantages over sRGB images, e.g., linearity and fine-grained quantization levels, they are not widely adopted by general users due to their substantial storage requirements. Very recent studies propose to compress raw images by designing sampling masks within the pixel space of the raw image. However, these approaches often leave space for pursuing more effective image representations and compact metadata. In this work, we propose a novel framework that learns a compact representation in the latent space, serving as metadata, in an end-to-end manner. Compared with lossy image compression, we analyze the intrinsic difference of the raw image reconstruction task caused by rich information from the sRGB image. Based on the analysis, a novel design of the backbone with asymmetric and hybrid spatial feature resolutions is proposed, which significantly improves the rate-distortion performance. Besides, we propose a novel design of the sRGB-guided context model, which can better predict the order masks of encoding/decoding based on both the sRGB image and the the masks of already processed features. Benefited from the better modeling of the correlation between order masks, the already processed information can be better utilized. Moreover, a novel sRGB-guided adaptive quantization precision strategy, which dynamically assigns varying levels of quantization precision to different regions, further enhances the representation ability of the model. Finally, based on the iterative properties of the proposed context model, we propose a novel strategy to achieve variable bit rates using a single model. This strategy allows for the continuous convergence of a wide range of bit rates. We demonstrate how our raw image compression scheme effectively allocates more bits to image regions that hold greater global importance. Extensive experimental results validate the superior performance of the proposed method, achieving high-quality raw image reconstruction with a smaller metadata size, compared with existing SOTA methods. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
11. Implementation of a novel adaptive coding using VLSI architecture for data compression in image processing.
- Author
-
Kiranmaye, G. and Sridhar, B.
- Subjects
VERY large scale circuit integration ,IMAGE compression ,SIGNAL-to-noise ratio ,PATTERNS (Mathematics) ,IMAGE processing ,FIELD programmable gate arrays ,DATA compression - Abstract
Image Compression is one of the emerging techniques of a Digital System for storing and retrieving of digital information. The main challenge in implementing Image Compression is to maintain the accuracy of the retrieved data. As the encoding techniques used for data compression are computationally intensive, new hardware architectures are required so that the processing of image consumes less space with increase in computation speed, reduction in area and power consumption. In this paper we address this problem and developed a Dynamic Adaptive coding technique based on probability of occurrence,where the variable and fixed length code are fused to generate a code word for eliminating the extra bit encountered at the entropy coder. Here the Entropy code has a maximum search overhead of 6 match per 4-bit pattern. Wherein a maximum of 5-bit search is observed in proposed approach. This reduces a search overhead of (N⨉m)-1 iterations. Here N is the number of unique patterns and m is the block size. The proposed architecture is developed using Very high speed integrated circuit Hardware Descriptive Language (VHDL) and implemented using Xilinx Aldec's Field Programmable Gate Array (FPGA). The adaptive coding approach attains a compression of 35% more as compared to the entropy coding. The implementation on to a targeted Xilinx FPGA results in power minimization and area coverage reduction. The speed of operation is observed to be improved by 135 MHz. The validation of proposed approach is made on image data to observe the coding accuracy. The mean square error of the output image is reduced by 35% with an increase in the signal to noise ratio of the output image. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
12. VLSI implementation of an energy-efficient color image compressor using improved block truncation coding and enhanced Golomb-rice coding for wireless sensor networks.
- Author
-
Nirmala, R., Begum, S. Ariffa, Selvanayagi, A., and Ramya, P.
- Subjects
- *
BLOCK codes , *IMAGE compression , *ENVIRONMENTAL reporting , *ENERGY consumption , *VERY large scale circuit integration , *WIRELESS sensor networks - Abstract
The very large-scale integration implementation of a unique hardware-oriented image compression technique for wireless sensor networks (WSNs) is presented in this work. Networks of individually owned sensors spread out throughout an area that can detect, measure, and report changes in environmental variables are known as wireless sensor networks (WSNs). Color sampling, block truncation coding (BTC), threshold optimization, sub-sampling, estimation, quantization, and enhanced Golomb-rice coding (EGRC) are all included in the proposed design. A unique improved BTC with an enhanced Golomb-rice coding (IBTC-EGRC) framework has been proposed in this paper. IBTC training framework has been developed using the fuzzy decision-based approach to achieve representative levels and satisfy WSN requirements to accomplish the cost-effective and power-efficient features. Two ideal reconstruction values and bitmap files have been obtained for every block. IBTC divides images into variable block sizes for mathematical translation and inter-pixel redundancy removal. The subsampling, estimation, and quantization stages have minimized redundant data. Finally, EGRC has been used to code the value with the highest likelihood. An EGRC module decreases memory use and computation complexity. The EGRC technique reduces hardware resource utilization by removing the need for the context module, a crucial part of lossless image compressor designs and its memory. Proposed method, Golomb-rice parameter forecasting and managment module is used to preserve pixel connection and improved compression ratio. A UMC 180 nm CMOS technology has been used to implement the suggested framework. This design has 5.8k synthesized gate counts and a core area of 56,000 µm2. 100 MHz and 3.01 mW were the operational frequency and energy consumption, respectively. The proposed method has a 9.37% reduction in gate count compared to the previous fuzzy BTC-based approach. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
13. Using Compressed JPEG and JPEG2000 Medical Images in Deep Learning: A Review.
- Author
-
Urbaniak, Ilona Anna
- Subjects
COMPUTER-assisted image analysis (Medicine) ,MACHINE learning ,DIAGNOSTIC imaging ,IMAGE analysis ,DEEP learning ,IMAGE compression - Abstract
Machine Learning (ML), particularly Deep Learning (DL), has become increasingly integral to medical imaging, significantly enhancing diagnostic processes and treatment planning. By leveraging extensive datasets and advanced algorithms, ML models can analyze medical images with exceptional precision. However, their effectiveness depends on large datasets, which require extended training times for accurate predictions. With the rapid increase in data volume due to advancements in medical imaging technology, managing the data has become increasingly challenging. Consequently, irreversible compression of medical images has become essential for efficiently handling the substantial volume of data. Extensive research has established recommended compression ratios tailored to specific anatomies and imaging modalities, and these guidelines have been widely endorsed by government bodies and professional organizations globally. This work investigates the effects of irreversible compression on DL models by reviewing the relevant literature. It is crucial to understand how DL models respond to image compression degradations, particularly those introduced by JPEG and JPEG2000—both of which are the only permissible irreversible compression techniques in the most commonly used medical image format—the Digital Imaging and Communications in Medicine (DICOM) standard. This study provides insights into how DL models react to such degradations, focusing on the loss of high-frequency content and its implications for diagnostic interpretation. The findings suggest that while existing studies offer valuable insights, future research should systematically explore varying compression levels based on modality and anatomy, and consider developing strategies for integrating compressed images into DL model training for medical image analysis. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
14. Coefficient-Shuffled Variable Block Compressed Sensing for Medical Image Compression in Telemedicine Systems.
- Author
-
Monika, R, Dhanalakshmi, Samiappan, Rajamanickam, Narayanamoorthi, Yousef, Amr, and Alroobaea, Roobaea
- Subjects
- *
DIAGNOSTIC imaging , *IMAGE compression , *IMAGE reconstruction , *COMPRESSED sensing , *FEATURE extraction - Abstract
Medical professionals primarily utilize medical images to detect anomalies within the interior structures and essential organs concealed by the skeletal and dermal layers. The primary purpose of medical imaging is to extract image features for the diagnosis of medical conditions. The processing of these images is indispensable for evaluating a patient's health. However, when monitoring patients over extended periods using specific medical imaging technologies, a substantial volume of data accumulates daily. Consequently, there arises a necessity to compress these data in order to remove duplicates and speed up the process of acquiring data, making it appropriate for effective analysis and transmission. Compressed Sensing (CS) has recently gained widespread acceptance for rapidly compressing images with a reduced number of samples. Ensuring high-quality image reconstruction using conventional CS and block-based CS (BCS) poses a significant challenge since they rely on randomly selected samples. This challenge can be surmounted by adopting a variable BCS approach that selectively samples from diverse regions within an image. In this context, this paper introduces a novel CS method that uses an energy matrix, namely coefficient shuffling variable BCS (CSEM-VBCS), tailored for compressing a variety of medical images with balanced sparsity, thereby achieving a substantial compression ratio and good reconstruction quality. The results of experimental evaluations underscore a remarkable enhancement in the performance metrics of the proposed method when compared to contemporary state-of-the-art techniques. Unlike other approaches, CSEM-VBCS uses coefficient shuffling to prioritize regions of interest, allowing for more effective compression without compromising image quality. This strategy is especially useful in telemedicine, where bandwidth constraints often limit the transmission of high-resolution medical images. By ensuring faster data acquisition and reduced redundancy, CSEM-VBCS significantly enhances the efficiency of remote patient monitoring and diagnosis. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
15. A Knowledge Base Driven Task-Oriented Image Semantic Communication Scheme.
- Author
-
Guo, Chang, Xi, Junhua, He, Zhanhao, Liu, Jiaqi, and Yang, Jungang
- Subjects
- *
COMPUTERS , *ARTIFICIAL intelligence , *DRONE aircraft , *IMAGE reconstruction , *KNOWLEDGE base , *IMAGE compression , *IMAGE reconstruction algorithms - Abstract
With the development of artificial intelligence and computer hardware, semantic communication has been attracting great interest. As an emerging communication paradigm, semantic communication can reduce the requirement for channel bandwidth by extracting semantic information. This is an effective method that can be applied to image acquisition of unmanned aerial vehicles, which can transmit high-data-volume images within the constraints of limited available bandwidth. However, the existing semantic communication schemes fail to adequately incorporate the guidance of task requirements into the semantic communication process and are difficult to adapt to the dynamic changes of tasks. A task-oriented image semantic communication scheme driven by knowledge base is proposed, aiming at achieving high compression ratio and high quality image reconstruction, and effectively solving the bandwidth limitation. This scheme segments the input image into several semantic information unit under the guidance of task requirements by Yolo-World and Segment Anything Model. The assigned bandwidth for each unit is according to the task relevance scores, which enables high-quality transmission of task-related information with lower communication overheads. An improved metric weighted learned perceptual image patch similarity (LPIPS) is proposed to evaluate the transmission accuracy of the novel scheme. Experimental results show that our scheme achieves a notable performance improvement on weighted LPIPS while the same compression ratio compared with traditional image compression schemes. Our scheme has a higher target capture ratio than traditional image compression schemes under the task of target detection. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
16. Parallel implementation of discrete cosine transform and its inverse for image compression applications.
- Author
-
Mukherjee, Debasish
- Subjects
- *
DISCRETE cosine transforms , *GRAPHICS processing units - Abstract
This paper presents the graphics processing unit (GPU) implementation of two-dimensional discrete cosine transform (2D DCT) and inverse discrete cosine transform (2D IDCT) for image compression applications. Based on the trigonometric properties, the transform matrices are simplified, resulting in reduced computation over the naive implementation. To assess its performance, the output image quality is measured in terms of several metrics and found to be better than all other existing transforms. To further improve the timings, a GPU implementation of the proposed transforms is obtained by exploiting the inter-level parallelism among threads and blocks in addition to efficiently accessing data from the shared memory resources. This has resulted in significant improvement in speedup (more than 5k) for both the transforms. The proposed GPU implementation of 2D DCT is compared in terms of processing time and is shown to outperform the existing work across all image dimensions. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
17. 2D Gaussian Splatting for Image Compression.
- Author
-
Zhang, Pingping, Liu, Xiangrui, Wang, Meng, Wang, Shiqi, Kwong, Sam, Gao, Wei, and Zhang, Xinfeng
- Subjects
VECTOR quantization ,ADAPTIVE control systems ,SOURCE code ,TRAINING needs ,ENTROPY ,IMAGE compression - Abstract
The implicit neural representation (INR) employed in image compression shows high decoding efficiency, yet it requires long encoding times due to the need for the model training tailored to the specific image being coded. Thus, we propose a new image compression scheme leveraging the 2D Gaussian splatting technique to accelerate encoding speed and maintain decoding efficiency. Specifically, we parameterize these Gaussians with key attributes including position, anisotropic covariance, color, and opacity coefficients, totaling 9 parameters per Gaussian. We initialize these Gaussians by sampling points from the image, followed by employing an α- blending mechanism to determine the color values of each pixel. For compact attribute representation, we adopt a K-means based vector quantization approach for anisotropic covariance, color and opacity coefficients. Additionally, we introduce an adaptive dense control methodology to dynamically adjust Gaussian numbers, facilitating automatic point reduction or augmentation. Finally, the position, codebooks and indexes of other attributes are quantized and compressed by the lossless entropy coding. Our experimental evaluation demonstrates that our method achieves faster encoding speeds compared to other INR techniques while exhibiting comparable decoding speeds. The source code is available via the following link: https://github.com/ppingzhang/2DGS_ImageCompression. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
18. Human-Machine Collaborative Image and Video Compression: A Survey.
- Author
-
Li, Huanyang, Zhang, Xinfeng, Wang, Shiqi, Wang, Shanshe, Pan, Jingshan, Gao, Wei, and Kwong, Sam
- Subjects
COMPUTER vision ,IMAGE compression ,VIDEO compression ,BINARY sequences ,VIDEO coding - Abstract
Traditional image and video compression methods are designed to maintain the quality of human visual perception, which makes it necessary to reconstruct the image or video before machine analysis. Compression methods oriented towards machine vision tasks make it possible to use the bit stream directly for machine vision tasks, but it is difficult for them to decode high quality images. To bridge the gap between machine vision tasks and signal-level representation, researchers present plenty of the human-machine collaborative compression methods. In order to provide researchers with a comprehensive understanding of this field and promote the development of image and video compression, we present this survey. In this work, we give a problem definition and explore the relationship and application scenarios of different methods. In addition, we provide a comparative analysis of existing methods on compression and machine vision tasks performance. Finally, we provide a discussion of several directions that are most promising for future research. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
19. Forgery Detection by Weighted Complementarity between Significant Invariance and Detail Enhancement.
- Author
-
Xiao, Shuai, Zhang, Zhuo, Yang, Jiachen, Wen, Jiabao, and Li, Yang
- Subjects
GENERATIVE adversarial networks ,IMAGE compression ,DEEPFAKES ,FOURIER transforms ,FORGERY - Abstract
Generative adversarial networks have shown impressive results in the modeling of movies and games, but what if such powerful image generation capability is used to harm the Multimedia? The face replacement methods represented by Deepfakes are becoming a threat to everyone, so the development of image authenticity detection methods has become a top priority. For achieving accurate detection resistant to compression effects, we propose a weighted complementary dual-stream detection method. First, to alleviate the influence of image compression on manipulation detection, we propose the concept of pixel-wise saliency invariance. We map fake images onto saliency maps via Quaternary Fourier Transform, which discovers the invariant properties of image phase spectra on different compressions. Meanwhile, to capture boundary traces more easily, we propose the concept of pixel-wise detail enhancement. We apply Bilateral Filtering to preserve the texture edges of fake images and amplify the fake boundaries. Finally, to take full advantage of the two proposed concepts, a weighted complementary dual-stream network is designed as a classifier to fuse features and identify real and fake. On different benchmarks like FaceForensics++ (FF++), Celeb-DF, and DFDC, the experimental results show that the proposed method has the average best detection accuracy compared to existing methods. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
20. Balancing the encoder and decoder complexity in image compression for classification.
- Author
-
Duan, Zhihao, Hossain, Md Adnan Faisal, He, Jiangpeng, and Zhu, Fengqing
- Subjects
- *
IMAGE recognition (Computer vision) , *IMAGE compression , *COMPUTATIONAL complexity , *MACHINE learning , *CLASSIFICATION - Abstract
This paper presents a study on the computational complexity of coding for machines, with a focus on image coding for classification. We first conduct a comprehensive set of experiments to analyze the size of the encoder (which encodes images to bitstreams), the size of the decoder (which decodes bitstreams and predicts class labels), and their impact on the rate–accuracy trade-off in compression for classification. Through empirical investigation, we demonstrate a complementary relationship between the encoder size and the decoder size, i.e., it is better to employ a large encoder with a small decoder and vice versa. Motivated by this relationship, we introduce a feature compression-based method for efficient image compression for classification. By compressing features at various layers of a neural network-based image classification model, our method achieves adjustable rate, accuracy, and encoder (or decoder) size using a single model. Experimental results on ImageNet classification show that our method achieves competitive results with existing methods while being much more flexible. The code will be made publicly available. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
21. Laser Scan Compression for Rail Inspection.
- Author
-
Hauck, Jeremiasz and Gniado, Piotr
- Subjects
- *
IMAGE compression , *DATA compression , *MAINTENANCE costs , *ACQUISITION of data , *GEOMETRY , *OPTICAL scanners - Abstract
The automation of rail track inspection addresses key issues in railway transportation, notably reducing maintenance costs and improving safety. However, it presents numerous technical challenges, including sensor selection, calibration, data acquisition, defect detection, and storage. This paper introduces a compression method tailored for laser triangulation scanners, which are crucial for scanning the entire rail track, including the rails, rail fasteners, sleepers, and ballast, and capturing rail profiles for geometry measurement. The compression technique capitalizes on the regularity of rail track data and the sensors' limited measurement range and resolution. By transforming scans, they can be stored using widely available image compression formats, such as PNG. This method achieved a compression ratio of 7.5 for rail scans used in the rail geometry computation and maintained rail gauge reproducibility. For the scans employed in defect detection, a compression ratio of 5.6 was attained without visibly compromising the scan quality. Lossless compression resulted in compression ratios of 5.1 for the rail geometry computation scans and 3.8 for the rail track inspection scans. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
22. Parallel Lossless Compression of Raw Bayer Images on FPGA-Based High-Speed Camera.
- Author
-
Regoršek, Žan, Gorkič, Aleš, and Trost, Andrej
- Subjects
- *
PARALLEL processing , *ELECTRONIC data processing , *ALGORITHMS , *PIXELS , *BINARY sequences , *IMAGE compression - Abstract
Digital image compression is applied to reduce camera bandwidth and storage requirements, but real-time lossless compression on a high-speed high-resolution camera is a challenging task. The article presents hardware implementation of a Bayer colour filter array lossless image compression algorithm on an FPGA-based camera. The compression algorithm reduces colour and spatial redundancy and employs Golomb–Rice entropy coding. A rule limiting the maximum code length is introduced for the edge cases. The proposed algorithm is based on integer operators for efficient hardware implementation. The algorithm is first verified as a C++ model and later implemented on AMD-Xilinx Zynq UltraScale+ device using VHDL. An effective tree-like pipeline structure is proposed to concatenate codes of compressed pixel data to generate a bitstream representing data of 16 parallel pixels. The proposed parallel compression achieves up to 56% reduction in image size for high-resolution images. Pipelined implementation without any state machine ensures operating frequencies up to 320 MHz. Parallelised operation on 16 pixels effectively increases data throughput to 40 Gbit/s while keeping the total memory requirements low due to real-time processing. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
23. High-Quality Image Compression Algorithm Design Based on Unsupervised Learning.
- Author
-
Han, Shuo, Mo, Bo, Zhao, Jie, Xu, Junwei, Sun, Shizun, and Jin, Bo
- Subjects
- *
GENERATIVE adversarial networks , *DATA integrity , *BIT rate , *WEIGHT training , *IMAGE compression , *PROBLEM solving - Abstract
Increasingly massive image data is restricted by conditions such as information transmission and reconstruction, and it is increasingly difficult to meet the requirements of speed and integrity in the information age. To solve the urgent problems faced by massive image data in information transmission, this paper proposes a high-quality image compression algorithm based on unsupervised learning. Among them, a content-weighted autoencoder network is proposed to achieve image compression coding on the basis of a smaller bit rate to solve the entropy rate optimization problem. Binary quantizers are used for coding quantization, and importance maps are used to achieve better bit allocation. The compression rate is further controlled and optimized. A multi-scale discriminator suitable for the generative adversarial network image compression framework is designed to solve the problem that the generated compressed image is prone to blurring and distortion. Finally, through training with different weights, the distortion of each scale is minimized, so that the image compression can achieve a higher quality compression and reconstruction effect. The experimental results show that the algorithm model can save the details of the image and greatly compress the memory of the image. Its advantage is that it can expand and compress a large number of images quickly and efficiently and realize the efficient processing of image compression. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
24. DNACoder: a CNN-LSTM attention-based network for genomic sequence data compression.
- Author
-
Sheena, K. S. and Nair, Madhu S.
- Subjects
- *
IMAGE compression , *DATA integrity , *DATA warehousing , *MARKOV processes , *PREDICTION models , *DEEP learning , *DATA compression - Abstract
Genomic sequencing has become increasingly prevalent, generating massive amounts of data and facing a significant challenge in long-term storage and transmission. A solution that reduces the storage and transfer requirements without compromising data integrity is needed. The effectiveness of neural networks has already been endorsed in tasks like image and speech compression. Adapting them to recognize the intricate patterns in genomic sequences could help to find more redundancies and reduce storage requirements. The proposed method, called DNACoder, leverages deep learning techniques to achieve significant compression ratios while preserving the essential information in genomic data and offers a high-performance compression for genomic sequences in any data format. The results of the experiments clearly demonstrate the effectiveness of the method and its potential applications in genomic data storage. Our proposed method improves compression by 21.1% on bits per base compared to existing compressors on the benchmarked dataset. By using a deep learning prediction model that is structured as a convolutional layer followed by an attention-based long short-term memory network, we propose a novel lossless and reference-free compression approach (DNACoder), which can also be utilized as a reference-based compressor. The experimental outcome on the tested data illustrates that the advocated compression algorithm's CNN-LSTM model makes generalizations effectively for genomic sequence data and outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
25. On the bitmap compression for joint coding and data hiding of AMBTC compressed images.
- Author
-
Hong, Wien, Su, Guan-Zhong, Chen, Tung-Shou, and Chen, Jeanne
- Subjects
BLOCK codes ,ENCODING ,STORAGE ,IMAGE compression ,HUFFMAN codes - Abstract
The compressed code of Absolute Moment Block Truncation Coding (AMBTC) consists of quantized values (QVs) and bitmaps. The QVs exhibit greater predictability, and the bitmaps themselves carry more randomness. While existing joint coding and data hiding based methods have focused on compressing the QVs, none of them have addressed the coding of bitmaps. Furthermore, evidence also reveals that the sub-divided bitmaps exhibit a highly uneven pattern distribution. Therefore, we propose an efficient method to compress the bitmaps by representing sub-divided bitmaps as decimal digits. This exploits the varying frequency of certain digits, allowing Huffman encoding for shorter codewords to represent frequently occurring digits. Moreover, we have observed that less frequent digits, which require longer codewords, tend to appear among blocks with smaller difference of QVs. As a solution, we employ an adaptive approach to directly record the original bitmap when the difference is below a specific threshold. Otherwise, we employ Huffman encoding to reduce the code length. The experimental results demonstrate the effectiveness of our approach in reducing the storage space required for Lena's bitmaps by 7.36%. Moreover, the reduction in bitrate is more pronounced when the test image exhibits a smooth texture. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
26. Adjoint method in PDE-based image compression.
- Author
-
Belhachmi, Zakaria and Jacumin, Thomas
- Subjects
- *
IMAGE compression , *IMAGE denoising , *STRUCTURAL optimization , *TOPOLOGICAL derivatives , *ASYMPTOTIC expansions - Abstract
We consider a shape optimization based method for finding the best interpolation data in the compression of images with noise. The aim is to reconstruct missing regions by means of minimizing a data fitting term in an L p -norm, for 1 ⩽ p < + ∞, between original images and their reconstructed counterparts using linear diffusion PDE-based inpainting. Reformulating the problem as a constrained optimization over sets (shapes), we derive the topological asymptotic expansion of the considered shape functionals with respect to the insertion of small ball (a single pixel) using the adjoint method. Based on the achieved distributed topological shape derivatives, we propose a numerical approach to determine the optimal set and present numerical experiments showing the efficiency of our method. Numerical computations are presented that confirm the usefulness of our theoretical findings for PDE-based image compression. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
27. The value of quantitative analysis of radionuclide bone SPECT/CT imaging in vertebral compression fracture: a retrospective study.
- Author
-
Wang, Yuhua, Qiao, Feifei, Li, Na, Liu, Ye, Long, Yahong, Xu, Kang, Wang, Jiantao, and Zhang, Wanchun
- Subjects
VERTEBRAL fractures ,RADIONUCLIDE imaging ,COMPUTED tomography ,BONE metastasis ,IMAGE compression ,VERTEBRAE injuries - Abstract
Background: Most patients with osteoporosis experience vertebral compression fracture (VCF), which significantly reduces their quality of life. These patients are at a high risk of secondary VCF regardless of treatment. Thus, accurate diagnosis of VCF is important for treating and preventing new fractures. We aimed to investigate the diagnostic and predictive value of quantitative bone imaging techniques for fresh VCF. Methods: From November 2021 to March 2023, 34 patients with VCF were enrolled in this study, all of whom underwent routine
99m Tc-MDP whole-body bone planar scan and local SPECT/CT imaging. The maximum standard uptake value (SUVmax) of 57 fresh VCF, 57 normal adjacent vertebrae, and 19 old VCF were measured. Based on the site of the fracture, fresh VCFs were regrouped into the intervertebral-type group and the margin-type group. Meanwhile, 52 patients who had no bone metastasis or VCFs in their bone scan were assigned to the control group. The SUVmax of 110 normal vertebral bodies and 10 old VCFs in the control group were measured. Results: The median SUVmax of fresh VCF was 19.80, which was significantly higher than the SUVmax of other groups. The receiver operator characteristic (ROC) curve showed that the cut-off value of SUVmax was 9.925 for diagnosing fresh VCF. The SUVmax in the intervertebral-type group was significantly higher than that in the margin-type group (P = 0.04). The SUVmax of normal vertebrae was higher among patients than among the control group (P<0.01), but the CT HU value showed no significant difference. Conclusion: The quantitative technique of bone SPECT/CT has a significant value in diagnosing fresh VCF. It can also determine the severity of fractures. In addition, whether the SUVs of the vertebrae adjacent to the fractured vertebra can predict re-fracture deserves further studies. [ABSTRACT FROM AUTHOR]- Published
- 2024
- Full Text
- View/download PDF
28. A Gray Scale Image Compression Using Hierarchical DWT Decomposition and Mixing Quantization Techniques.
- Author
-
Mahdi, Noor Sabah and Al-Khafaji, Ghadah
- Subjects
- *
DISCRETE wavelet transforms , *GRAYSCALE model , *LINEAR codes , *IMAGE compression , *JPEG (Image coding standard) , *DISCRETE systems - Abstract
This paper describes a hybrid grayscale compression system based on the discrete wavelet transform (DWT) and a polynomial coding technique for mixing quantization schemes to increase the compression ratio while maintaining quality. The proposed compression system consists of three main steps: first, decomposing an image using a three-level DWT; second, applying the 2-D linear polynomial coding technique to the approximation sub-band; and third, dividing the detailed sub-bands of each level into the Most Significant Value (MSV) and Least Significant Value (LSV), where the former is compressed using iterative scalar uniform quantization and the latter by soft quantization thresholding. For testing the performance of the suggested compression system, five standard images of size 256×256 pixels were adopted. The suggested technique showed superior performance in terms of reconstructed (decoded) image quality and compression ratio (gain), where the compression ratio is between 21–27 with a PSNR value between 36–38 dB and the compression ratio of JPEG is between 7–20 with a PSNR value between 33–37 dB. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
29. MRACNN: Multi-Path Residual Asymmetric Convolution and Enhanced Local Attention Mechanism for Industrial Image Compression.
- Author
-
Yan, Zikang, Liu, Peishun, Wang, Xuefang, Gao, Haojie, Ma, Xiaolong, and Hu, Xintong
- Subjects
- *
CONVOLUTIONAL neural networks , *FEATURE extraction , *KNOWLEDGE transfer , *ENTROPY - Abstract
The rich information and complex background of industrial images make it a challenging task to improve the high compression rate of images. Current learning-based image compression methods mostly use customized convolutional neural networks (CNNs), which find it difficult to cope with the complex production background of industrial images. This causes useful information to be lost in the abundance of irrelevant data, making it difficult to accurately extract important features during the feature extraction stage. To address this, a Multi-path Residual Asymmetric Convolutional Compression Network (MRACNN) is proposed. Firstly, a Multi-path Residual Asymmetric Convolution Block (MRACB) is introduced, which includes the Multi-path Residual Asymmetric Convolution Down-sampling Module for down-sampling in the encoder to extract key features, and the Mult-path Residual Asymmetric Convolution Up-sampling Module for up-sampling in the decoder to recover details and reconstruct the image. This feature transfer and information flow enables the better capture of image details and important information, thereby improving the quality and efficiency of image compression and decompression. Furthermore, a two-branch enhanced local attention mechanisms, and a channel-squeezing entropy model based on the compression-based enhanced local attention module is proposed to enhance the performance of the modeled compression. Extensive experimental evaluations demonstrate that the proposed method outperforms state-of-the-art techniques, achieves superior Rate–Distortion Performance, and excels in preserving local details. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
30. Some Properties of Reduced Biquaternion Tensors.
- Author
-
Liu, Ting-Ting and Yu, Shao-Wen
- Subjects
- *
DIGITAL signal processing , *IMAGE compression , *IMAGE processing , *EIGENVALUES , *QUATERNIONS - Abstract
Compared to quaternions, reduced biquaternions satisfy the multiplication commutative rule and are widely employed in applications such as image processing, fuzzy recognition, image compression, and digital signal processing. However, there is little information available regarding reduced biquaternion tensors; thus, in this study, we investigate some properties of reduced biquaternion tensors. Firstly, we introduce the concept of reduced biquaternion tensors, propose the real and complex representations of reduced biquaternion tensors, and prove several fundamental theorems. Subsequently, we provide the definitions for the eigenvalues and eigentensors of reduced biquaternion tensors and present the Ger s ˇ gorin theorem as it applies to their eigenvalues. Additionally, we establish the relationship between the reduced biquaternion tensor and its complex representation. Notably, the complex representation is a symmetry tensor, which significantly simplifies the process and complexity of solving for eigenvalues. Corresponding numerical examples are also provided in the paper. Furthermore, some special properties of eigenvalues of reduced biquaternion tensors are presented. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
31. MapGen-Diff: An End-to-End Remote Sensing Image to Map Generator via Denoising Diffusion Bridge Model.
- Author
-
Tian, Jilong, Wu, Jiangjiang, Chen, Hao, and Ma, Mengyu
- Subjects
- *
IMAGE compression , *REMOTE sensing , *URBAN planning , *SAMPLING (Process) ,TRAVEL planning - Abstract
Online maps are of great importance in modern life, especially in commuting, traveling and urban planning. The accessibility of remote sensing (RS) images has contributed to the widespread practice of generating online maps based on RS images. The previous works leverage an idea of domain mapping to achieve end-to-end remote sensing image-to-map translation (RSMT). Although existing methods are effective and efficient for online map generation, generated online maps still suffer from ground features distortion and boundary inaccuracy to a certain extent. Recently, the emergence of diffusion models has signaled a significant advance in high-fidelity image synthesis. Based on rigorous mathematical theories, denoising diffusion models can offer controllable generation in sampling process, which are very suitable for end-to-end RSMT. Therefore, we design a novel end-to-end diffusion model to generate online maps directly from remote sensing images, called MapGen-Diff. We leverage a strategy inspired by Brownian motion to make a trade-off between the diversity and the accuracy of generation process. Meanwhile, an image compression module is proposed to map the raw images into the latent space for capturing more perception features. In order to enhance the geometric accuracy of ground features, a consistency regularization is designed, which allows the model to generate maps with clearer boundaries and colorization. Compared to several state-of-the-art methods, the proposed MapGen-Diff achieves outstanding performance, especially a 5 % RMSE and 7 % SSIM improvement on Los Angeles and Toronto datasets. The visualization results also demonstrate more accurate local details and higher quality. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
32. Subjective assessment of visual fidelity: Comparison of forced‐choice methods.
- Author
-
Au, Domenic, Mohona, Sanjida Sharmin, Wilcox, Laurie M., and Allison, Robert S.
- Subjects
- *
IMAGE compression , *PYRAMIDS , *BANDWIDTHS , *FORECASTING , *VIDEOS - Abstract
Increases in display resolution, frame rate, and bit depth, particularly with advances in stereoscopic 3D (S3D) displays, have increased demand for efficient compression throughout the imaging pipeline. To meet such requirements, typically the aim is to reduce bandwidth while presenting content that is visually indistinguishable from the original uncompressed versions. Subjective image quality assessment is essential and multiple methods have been proposed. Of these, the ISO/IEC 29170‐2 flicker paradigm is a rigorous method used to define visually lossless performance. However, it is possible that the enhanced sensitivity to artifacts in the presence of flicker does not predict visibility under natural viewing conditions. Here, we test this prediction using high‐dynamic range S3D images and video under flicker and non‐flicker protocols. As hypothesized, sensitivity to artifacts was greater when using the flicker paradigm, but no differences were observed between the non‐flicker paradigms. Results were modeled using the Pyramid of Visibility, which predicted artifact detection driven by moderately low spatial frequencies. Overall, our results confirm the flicker paradigm is a conservative estimate of visually lossless behavior; it is highly unlikely to miss artifacts that would be visible under normal viewing. Conversely, artifacts identified by the flicker protocol may not be problematic in practice. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
33. Estimating the Complexity of Objects in Images.
- Author
-
Bokshanskiy, V. B., Kulin, V. A., Finiakin, G. S., Kharlamov, A. S., and Shatskiy, A. A.
- Subjects
- *
IMAGE recognition (Computer vision) , *IMAGE compression , *IMAGE segmentation , *COMPUTATIONAL complexity , *DIGITAL images - Abstract
A new method for estimating the complexity of geometric shapes (spots) is proposed that takes into account the internal structure of the spots in addition to their external contour. The task of calculating the degree of complexity of objects is divided into the subtasks of segmenting the spots and estimating the complexity of isolated spots. The new method has a relatively low computational complexity compared to the alternative methods considered in the work. Using the new method, an algorithm based on parallel computing in the CUDA architecture for GPUs is implemented, which further increases the performance of the method. A qualitative and quantitative analysis of existing (alternative) methods is carried out, and their advantages and disadvantages in comparison with the proposed method and with each other are revealed. The algorithm implemented on the basis of the new method was tested on both artificial and real digital images. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
34. Image compression–based DS-InSAR method for landslide identification and monitoring of alpine canyon region: a case study of Ahai Reservoir area in Jinsha River Basin.
- Author
-
Gu, Xiaona, Li, Yongfa, Zuo, Xiaoqing, Bu, Jinwei, Yang, Fang, Yang, Xu, Li, Yongning, Zhang, Jianming, Huang, Cheng, Shi, Chao, and Xing, Mingze
- Subjects
- *
DEFORMATION of surfaces , *ALPINE regions , *IMAGE compression , *SYNTHETIC aperture radar , *PRINCIPAL components analysis , *LANDSLIDES - Abstract
Interferometric Synthetic Aperture Radar (InSAR) technology is capable of detecting large areas of potentially unstable slopes. However, traditional time-series InSAR methods yield fewer valid measurement points (MPs) in alpine canyon regions. Distributed Scatterer (DS) Interferometry (DSI) technology serves as a potent tool for monitoring surface deformation in complex land cover areas; nonetheless, it grapples with high computational demands and low efficiency when interpreting deformation across extended time series. This study proposes an image compression–based DSI (ICDSI) method, which, building upon the DSI method, utilizes principal component analysis (PCA) to compress multi-temporal SAR images in the time dimension. It develops a module for compressing long-time sequence SAR images, acquires the compressed image (referred to as a virtual image), and integrates the developed image compression module into the DSI data processing flow to facilitate the inversion of long-time sequence InSAR land surface deformation information. To validate and assess the credibility of the ICDSI method, we processed a total of 78 ascending and 81 descending scenes of Sentinel-1A images spanning the period 2019–2021 using Small Baseline Subset (SBAS), DSI, and the ICDSI method proposed in this paper. Subsequently, these methods were applied to detect landscape displacements on both coasts of the Jinsha River Basin. The investigation reveals that the ICDSI method outperforms SBAS and DSI significantly in monitoring landslide displacements, enabling the detection of more measurement points (MPs) while utilizing less raw data. The accomplishments of this research program carry crucial theoretical implications and practical application value for the detection of surface deformation using long-time series InSAR. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
35. 基于整数 U 变换的图像压缩方法.
- Author
-
袁茜茜, 蔡占川, 石武祯, and 尹文楠
- Abstract
Copyright of Journal of South China University of Technology (Natural Science Edition) is the property of South China University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2024
- Full Text
- View/download PDF
36. Digital colposcopy image analysis techniques requirements and their role in clinical diagnosis: a systematic review.
- Author
-
Tamang, Parimala, Gupta, Mousumi, and Thatal, Annet
- Subjects
IMAGE compression ,ARTIFICIAL intelligence ,DIGITAL image processing ,IMAGE analysis ,EVIDENCE gaps - Abstract
Introduction: Colposcopy is a medical procedure for detecting cervical lesions. Access to devices required for colposcopy procedures is limited in low- and middle-income countries. However, various existing digital imaging techniques based on artificial intelligence offer solutions to analyze colposcopy images and address accessibility challenges. Methods: We systematically searched PubMed, National Library of Medicine, and Crossref, which met our inclusion criteria for our study. Various methods and research gaps are addressed, including how variability in images and sample size affect the accuracy of the methods. The quality and risk of each study were assessed following the QUADAS-2 guidelines. Results: Development of image analysis and compression algorithms, and their efficiency are analyzed. Most of the studied algorithms have attained specificity, sensitivity, and accuracy which range from 86% to 95%, 75%–100%, and 100%, respectively, and these results were validated by the clinician to analyze the images quickly and thus minimize biases among the clinicians. Conclusion: This systematic review provides a comprehensive study on colposcopy image analysis stages and the advantages of utilizing digital imaging techniques to enhance image analysis and diagnostic procedures and ensure prompt consultations. Furthermore, compression techniques can be applied to send medical images over media for further analysis among periphery hospitals. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
37. Financial Digital Images Compression Method Based on Discrete Cosine Transform.
- Author
-
Wenjin Wang, Lu, Miaomiao, Dai, Xuanling, and Jiang, Ping
- Abstract
In response to the characteristics of financial image data, this paper proposes an efficient digital image compression scheme. Firstly, discrete cosine transform (DCT) is applied to divide the financial image into DC and AC coefficients. Secondly, based on the characteristics of DCT coefficients, a fuzzy method is employed to categorize DCT subblocks into smooth, texture, and edge classes, enabling distinct quantization strategies. Subsequently, to eliminate spatial and statistical redundancies in financial images, common features and structures are utilized, and a specific scanning approach is employed to optimize the arrangement of important coefficients. Finally, differential prediction and entropy coding are employed for DCT coefficient scanning encoding, enhancing compression efficiency. The objective evaluation metrics of this algorithm are approximately 2 dB higher than existing algorithms at bit rates of 0.25 and 0.5. Even at bit rates of 0.75, 1.5, 2.5, and 3.5, the performance of this method still outperforms the comparative algorithms, demonstrating its capability to efficiently store and transmit massive financial image data, thereby providing robust support for data processing in the financial sector. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
38. Deblurring image compression algorithm using deep convolutional neural network.
- Author
-
Menassel, Rafik, Gattal, Abdeljalil, and Kerdoud, Fateh
- Subjects
CONVOLUTIONAL neural networks ,IMAGE compression ,DEEP learning ,MACHINE learning ,METAHEURISTIC algorithms - Abstract
There are instances where image compression becomes necessary; however, the use of lossy compression techniques often results in visual artifacts. These artifacts typically remove high-frequency detail and may introduce noise or small image structures. To mitigate the impact of compression on image perception, various technologies, including machine learning and optimization metaheuristics that optimize the parameters of image compression algorithms, have been developed. This paper investigates the application of convolutional neural networks (CNNs) to reduce artifacts associated with image compression, and it presents a proposed method termed deblurring compression image using a CNN (DCI-CNN). Trained on a UTKFace dataset and tested on six benchmark images, the DCI-CNN aims to address artifacts such as block artifacts, ringing artifacts, blurring artifacts, color bleeding, and mosquito noise. The DCI-CNN application is designed to enhance the visual quality and fidelity of compressed images, offering a more detailed output compared to generic and other deep learningbased deblurring methods found in related work. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
39. MAKING USE OF MANUFACTURING PROCESS VARIATIONS: MACHINE LEARNING APPROACHES FOR EFFICIENT MEDICAL AND BIOLOGICAL STUDY-BASED IMAGE COMPRESSION AND LOSSLESS TRANSMISSION.
- Author
-
Sachi, Savya, Noorjahan, Ranjan, Ravi, Kumari, Shweta, and Alam, Md Mohtab
- Subjects
IMAGE compression ,DEEP learning ,MACHINE learning ,TRANSFORMER models ,GENERATIVE adversarial networks ,MANUFACTURING processes ,COMPUTER-assisted image analysis (Medicine) - Abstract
This research paper explores advanced machine learning techniques for compressing and transmitting medical and biological study-based images without loss of critical diagnostic information. We investigate deep learning architectures including autoencoders, generative adversarial networks (GANs) and transformer models optimized for various medical and biological imaging modalities. Our proposed hybrid compression pipeline combines semantic segmentation, region-adaptive encoding, and learned post-processing to achieve state-of-the-art compression ratios while preserving clinically relevant features. Extensive experiments on large-scale datasets of X-rays, CT scans, MRI scans and microscopy images demonstrate the efficacy of our approach in terms of compression performance, reconstruction quality, and computational efficiency. We also present a novel blockchain-based system for secure and lossless transmission of the compressed medical and biological data. Our findings indicate that machine learning-driven compression can enable more efficient storage and sharing of medical and biological images in resource-constrained healthcare and research environments. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
40. Unified and Scalable Deep Image Compression Framework for Human and Machine.
- Author
-
Zhang, Gai, Zhang, Xinfeng, and Tang, Lv
- Subjects
COMPUTER vision ,TASK analysis ,IMAGE analysis ,DEEP learning ,IMAGE representation ,IMAGE compression - Abstract
Image compression aims to minimize the amount of data in image representation while maintaining a certain visual quality for humans, which is an essential technique for storage and transmission. Recently, along with the development of computer vision, machines have become another primary receiver for images and require compressed images at a certain quality level, which may be different from that of human vision. In many scenarios, compressed images should serve both human and machine vision tasks, but few compression methods are designed for both goals simultaneously. In this article, we propose a unified and scalable deep image compression (USDIC) framework that jointly optimizes the image quality according to human and machine vision in an end-to-end style. For the encoder, we propose an information splitting mechanism (ISM) to separate images into semantic and visual features, which mainly aims at machine analysis and human viewing tasks. For the decoder, we design a scalable decoding architecture. The encoded semantic feature is first decoded for machine analysis tasks, and the image is decoded and reconstructed further by leveraging the decoded semantic features. Herein, to further remove the redundancy between the semantic and visual features of images, we propose a scalable entropy model (SEM) with a joint optimization strategy to reconstruct the image using the two kinds of decoded features. Extensive experimental results show that the proposed USDIC achieves much better performance on the image analysis task while maintaining competitive performance on the traditional image reconstruction task compared with popular image compression methods. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
41. Reconstruction-Free Image Compression for Machine Vision via Knowledge Transfer.
- Author
-
Tu, Hanyue, Li, Li, Zhou, Wengang, and Li, Houqiang
- Subjects
COMPUTER vision ,IMAGE reconstruction ,CONVOLUTIONAL neural networks ,KNOWLEDGE transfer ,PIXELS ,LOW vision - Abstract
Reconstruction-free image compression for machine vision aims to perform machine vision tasks directly on compressed-domain representations instead of reconstructed images. Existing reports have validated the feasibility of compressed-domain machine vision. However, we observe that when using recently learned compression models, the performance gap between compressed-domain and pixel-domain vision tasks is still large due to the lack of some natural inductive biases in pixel-domain convolutional neural networks. In this article, we attempt to address this problem by transferring knowledge from the pixel domain to the compressed domain. A knowledge transfer loss defined at both output level and feature level is proposed to narrow the gap between the compressed domain and the pixel domain. In addition, we modify neural networks for pixel-domain vision tasks to better suit compressed-domain inputs. Experimental results on several machine vision tasks show that the proposed method improves the accuracy of compressed-domain vision tasks significantly, which even outperforms learning on reconstructed images while avoiding the computational cost of image reconstruction. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
42. A lossless image compression using deep learning.
- Author
-
Thulasi, Thushara and Antony, Bejoy
- Subjects
- *
ELLIPTIC curve cryptography , *IMAGE encryption , *DISTRIBUTION (Probability theory) , *IMAGE representation , *IMAGE transmission , *IMAGE compression - Abstract
Variational Autoencoders (VAEs) is a type of generative model that can be used for image compression. The steps involved in using VAEs for lossless image compression are pre-processing, encoding, sampling, decoding, loss function, training and compression. The input image is first pre-processed to convert it into a format that can be used as input to the VAE. Typically, this process entails normalizing the pixel values to fall within the range of 0 to 1, followed by transforming the image into a flattened vector. The encoder network receives the pre-processed image and condenses it into a reduced-dimensional representation. The encoder network consists of multiple layers of neural networks that reduce the dimensionality of the input image while capturing the important features of the image. The output of the encoder network is a mean vector and a variance vector, which are used to sample a compressed representation of the image. The compressed representation of the image is sampled from a probability distribution that is defined by the mean vector and variance vector output by the encoder network. This sampling process makes VAEs a generative model. The decoder network takes in the compressed representation of the image as input and reconstructs the original image. The loss function used in VAEs is a combination of a reconstruction loss and a regularization loss. The VAE undergoes training through back-propagation to minimize its loss function. Once the VAE is trained, it can be used to compress new images. The encoder network condenses the input image into a reduced-dimensional representation, which can then be stored or transmitted. In order to achieve secure image transmission we can perform an image encryption using Elliptic Curve Cryptography (ECC). Variational Autoencoders for lossless image compression is a promising research area that will provide good results in achieving high-quality compression while preserving the entirety of the data within the original image. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
43. Performance analysis of image compression techniques for MRI image using machine learning techniques.
- Author
-
Kawadkar, Pankaj, Rathore, Deepak Kumar, Kushwaha, Devendra Singh, Rebecca, B., Karunya, G. Priyanka Jeeva, and Yohan, P. M.
- Subjects
- *
COMPUTER-assisted image analysis (Medicine) , *TELECOMMUNICATION , *DATA compression , *IMAGE compression , *TECHNOLOGICAL innovations , *DIGITAL communications - Abstract
As we saw that the development of new technology and communication in digital media is increasing day by day, as the internet is showing tremendous growth for communication and in another sector also, here the information represented in the form of multimedia, image data is one of them. Communication for the image data is very vital nowadays because data in the form of an image is very important for the various section, and medical imaging or the healthcare sector is one of them. In medical imaging for communication, we used the data compression and decompression techniques for transmission of data. In this work, we present the comparative literature study with medical image compression and find the performance parameters value for different techniques i.e. wavelet transformation techniques and machine learning techniques. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
44. Deep learning for satellite image compression and quality image restoration using context-sensitive quantization and interpolation.
- Author
-
Mukil, A., Ravichandran, C., Nataraj, C., and Selvaperumal, S. K.
- Subjects
- *
NATURAL language processing , *GPS receivers , *IMAGE compression , *STANDARD deviations , *REMOTE sensing , *DEEP learning - Abstract
CubeSats, nanosatellites, including microsatellites with a moisture content of up to 60 kg have all contributed to the fast expansion of the Earth Observation sector. This development has also been aided by the reduction in cost associated with reaching space. Image data that has been acquired serves as a vital source of information in a variety of fields. As more remote sensing data is collected, the available bandwidth capabilities for the data transfer, known as the downlink, will eventually be used up. Under this article, we explain six different methodologies, including Pruning, Quantization, Information Distillation, Present Sample, Tensor Decomposing, and Sub-quadratic Converter based approaches, for compaction of such modeling techniques to enable their implementations in real industry NLP projects. These methods include information extraction, present sample, tensor decomposition, and parametric sharing. We believe that this survey organises the vast amount of work that has been done in the field of "deep learning for natural language processing" over the past couple of years and introduces it as a coherent story. This is especially important in light of the important need to build implementations with effectual and small designs, as well as the huge portion of newly published work in this area. Examples are shown using three-channel remote sensing and pictures obtained using RS that are included in multispectral data. It has been proved that the quality of pictures compressed using Discrete Atomic Transform may be adjusted and controlled by adjusting the greatest absolute deviation. This parameter also has a direct and tight relationship with more conventional metrics such as root mean square error (RMSE) and peak transmission ratio (PSNR), all of which are within the control of the user. Nevertheless, the majority of attention is being paid to several antenna applications, including millimetre wave, body-centric, radiofrequency, satellite, unmanned aircraft systems, gps devices, and textiles. The objective of this study is to investigate the recent trends in research within this sphere. We look at a variety of optimization strategies that are presently used to cram resource-constrained embedded and mobile systems with computation- and memory-intensive algorithms and examine how these strategies may be improved. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
45. Universal almost Optimal Compression and Slepian-wolf Coding in Probabilistic Polynomial Time.
- Author
-
BAUWENS, BRUNO and ZIMAND, MARIUS
- Subjects
POLYNOMIAL time algorithms ,KOLMOGOROV complexity ,COMPRESSORS ,IMAGE compression - Abstract
In a lossless compression system with target lengths, a compressor C maps an integerm and a binary string x to anm-bit code p, and ifm is sufficiently large, a decompressor D reconstructs x from p. We call a pair (m, x) achievable for (C,D) if this reconstruction is successful. We introduce the notion of an optimal compressor Copt by the following universality property: For any compressor-decompressor pair (C,D), there exists a decompressor D' such that if (m, x) is achievable for (C,D), then (m + Δ, x) is achievable for (Copt,D'), where Δ is some small value called the overhead. We show that there exists an optimal compressor that has only polylogarithmic overhead and works in probabilistic polynomial time. Differently said, for any pair (C,D), nomatter howslowC is, or even if C is non-computable, Copt is a fixed compressor that in polynomial time produces codes almost as short as those of C. The cost is that the corresponding decompressor is slower. We also show that each such optimal compressor can be used for distributed compression, in which case it can achieve optimal compression rates as given in the Slepian–Wolf theorem and even for the Kolmogorov complexity variant of this theorem. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
46. Efficient representation of bit-planes for quantum image processing.
- Author
-
Mir, Mohmad Saleem, Bhat, Hilal Ahmad, and Khanday, Farooq Ahmad
- Subjects
QUANTUM computing ,TIME complexity ,QUANTUM states ,IMAGE compression ,IMAGE processing - Abstract
Quantum computers can be used for efficient storage, processing and transmission of digital images. It involves exploitation of quantum properties to represent and process the images in a quantum computer. The first important step to process images in a quantum computer is the representation of images in quantum states. In this paper, we introduce two efficient implementation of algorithms to store the bit-planes of an image in quantum states, one for grayscale images and other for color images. The proposed implementations can be used to improve the effectiveness of image processing algorithms such as color complement operation, edge detection, image compression and so on. The proposed implementation has 10% less quantum cost and four times less time complexity compared to BRQI model for greyscale images, and 30% less quantum cost and four times less time complexity compared to QRCI model for color images. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
47. Efficient Compression Techniques for Medical Image Storage and Transmission: A Comprehensive Review.
- Author
-
Kaushik, Bhavana
- Subjects
- *
BIT rate , *DIAGNOSTIC imaging , *IMAGE transmission , *GRAYSCALE model , *COMPARATIVE studies , *IMAGE compression - Abstract
In the field of medical imaging, there is a strong requirement for the storage of an immense volume of digitized medical image data. The digital image must be compressed heavily before storing and transferring it because of having restricted bandwidth and scope of storage. When compression of images is done at a lower bit rate it reduces the image fidelity that results in a drop in quality but poses many challenges to overcome and prevents diagnostic miscalculations with great compression rates for reduced storage and quick transmission. To overcome this challenging issue several hybrid efficient compression procedures solely for medical digital images have been introduced in recent years. The transformation of image, quantization, and encoding is part of image compression. This paper presents a qualitative and comprehensive review of image compression techniques for two-dimensional (2D) still and three-dimensional (3D) medical images. The features and constraints associated with various compression methods for compressing grayscale images are reviewed and discussed in this paper. In-depth reviews of the practical concerns and difficulties in the medical scan compression arena are provided. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
48. Efficient On-Board Compression for Arbitrary-Shaped Cloud-Covered Remote Sensing Images via Adaptive Filling and Controllable Quantization.
- Author
-
Wang, Keyan, Jia, Jia, Zhou, Peicheng, Ma, Haoyi, Yang, Liyun, Liu, Kai, and Li, Yunsong
- Subjects
- *
IMAGE compression , *BIT rate , *REMOTE sensing , *BINARY codes - Abstract
Due to the fact that invalid cloud-covered regions in remote sensing images consume a considerable quantity of coding bit rates under the limited satellite-to-ground transmission rate, existing image compression methods suffer from low compression efficiency and poor reconstruction quality, especially in cloud-free regions which are generally regarded as regions of interest (ROIs). Therefore, we propose an efficient on-board compression method for remote sensing images with arbitrary-shaped clouds by leveraging the characteristics of cloudy images. Firstly, we introduce two novel spatial preprocessing strategies, namely, the optimized adaptive filling (OAF) strategy and the controllable quantization (CQ) strategy. Specifically, the OAF strategy fills each cloudy region using the contextual information at its inner and outer edge to completely remove the information of cloudy regions and minimize their coding consumption, which is suitable for images with only thick clouds. The CQ strategy implicitly identifies thin and thick clouds and rationally quantifies the data in cloudy regions to alleviate information loss in thin cloud-covered regions, which can achieve the balance between coding efficiency and reconstructed image quality and is more suitable for images containing thin clouds. Secondly, we develop an efficient coding method for a binary cloud mask to effectively save the bit rate of the side information. Our method provides the flexibility for users to choose the desired preprocessing strategy as needed and can be embedded into existing compression framework such as JPEG2000. Experimental results on the GF-1 dataset show that our method effectively reduces the coding consumption of invalid cloud-covered regions and significantly improve the compression efficiency as well as the quality of decoded images. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
49. Lossless hyperspectral image compression by combining the spectral decorrelation techniques with transform coding methods.
- Author
-
Nagendran, R., Ramadass, Sudhir, Thilagavathi, K., and Ravuri, Ananda
- Subjects
- *
SPECTRAL imaging , *DATA warehousing , *DATA transmission systems , *CUBES , *IMAGE compression , *ALGORITHMS - Abstract
This study explores the utilization of Binary Embedded Zero Tree Wavelet Algorithms (BEZW) to compress hyperspectral images. The primary goal is to enhance the representation of spectral data while minimizing storage and transmission requirements. The BEZW algorithm employs wavelet transformations to leverage both spectral and spatial redundancies found in hyperspectral data cubes. Its embedded zero tree structure ensures efficient encoding of small coefficients with minimal overhead. The study evaluates the performance of the BEZW method utilizing various hyper-spectral datasets and compression settings, comparing it to other compression techniques. The results illustrate that the BEZW algorithm offers a promising approach to hyperspectral image compression, achieving competitive compression ratios while preserving spectral accuracy. This makes it a valuable option for applications where efficient hyperspectral data storage and transmission are crucial. The research contributes to the field of hyperspectral imaging by introducing an effective compression method that enhances data accessibility, simplifying the utilization of hyperspectral data in resource-constrained environments. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
50. Efficient Lossy Compression of Video Sequences of Automotive High-Dynamic Range Image Sensors for Advanced Driver-Assistance Systems and Autonomous Vehicles.
- Author
-
Pawłowski, Paweł and Piniarski, Karol
- Subjects
IMAGE compression ,IMAGE color analysis ,VIDEO compression ,IMAGE processing software ,GRAYSCALE model - Abstract
In this paper, we introduce an efficient lossy coding procedure specifically tailored for handling video sequences of automotive high-dynamic range (HDR) image sensors in advanced driver-assistance systems (ADASs) for autonomous vehicles. Nowadays, mainly for security reasons, lossless compression is used in the automotive industry. However, it offers very low compression rates. To obtain higher compression rates, we suggest using lossy codecs, especially when testing image processing algorithms in software in-the-loop (SiL) or hardware-in-the-loop (HiL) conditions. Our approach leverages the high-quality VP9 codec, operating in two distinct modes: grayscale image compression for automatic image analysis and color (in RGB format) image compression for manual analysis. In both modes, images are acquired from the automotive-specific RCCC (red, clear, clear, clear) image sensor. The codec is designed to achieve a controlled image quality and state-of-the-art compression ratios while maintaining real-time feasibility. In automotive applications, the inherent data loss poses challenges associated with lossy codecs, particularly in rapidly changing scenes with intricate details. To address this, we propose configuring the lossy codecs in variable bitrate (VBR) mode with a constrained quality (CQ) parameter. By adjusting the quantization parameter, users can tailor the codec behavior to their specific application requirements. In this context, a detailed analysis of the quality of lossy compressed images in terms of the structural similarity index metric (SSIM) and the peak signal-to-noise ratio (PSNR) metrics is presented. With this analysis, we extracted some codec parameters, which have an important impact on preservation of video quality and compression ratio. The proposed compression settings are very efficient: the compression ratios vary from 51 to 7765 for grayscale image mode and from 4.51 to 602.6 for RGB image mode, depending on the specified output image quality settings. We reached 129 frames per second (fps) for compression and 315 fps for decompression in grayscale mode and 102 fps for compression and 121 fps for decompression in the RGB mode. These make it possible to achieve a much higher compression ratio compared to lossless compression while maintaining control over image quality. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.