Search

Image quality assessment (IQA) is an important task of image processing and has diverse applications, such as image super-resolution reconstruction, image transmission and monitoring systems. This paper proposes a perceptual hashing algorithm with complementary color wavelet transform (CCWT) and compressed sensing (CS) for reduced-reference (RR) IQA. The CCWT is exploited to decompose input color image into different sub-bands. Since the calculation of CCWT uses all color channels without discarding any information, the distortions introduced by digital operations on color channels are preserved in the CCWT sub-bands. The block-based CS is used to extract features from the CCWT sub-bands. As the Euclidean distance between the block-based CS features is slightly influenced by content-preserving operations, perceptual features constructed by Euclidean distances are robust, discriminative and compact. Hash sequence is finally determined by quantifying the perceptual features. Effectiveness of the proposed hashing is verified by various experiments on four open image databases. Experimental results demonstrate that the proposed hashing is superior to some state-of-the-art algorithms in terms of classification and RR IQA application. [ABSTRACT FROM AUTHOR]

The generative adversarial network (GAN) is successfully applied to study the perceptual single image super-resolution (SISR). However, since the GAN is data-driven, it has a fundamental limitation on restoring real high frequency information for an unknown instance (or image) during test. On the other hand, the conventional model-based methods have a superiority to achieve instance adaptation as they operate by considering the statistics of each instance (or image) only. Motivated by this, we propose a novel model-based algorithm, which can extract the detail layer of an image efficiently. The detail layer represents the high frequency information of image and it is constituted of image edges and fine textures. It is seamlessly incorporated into the GAN and serves as a prior knowledge to assist the GAN in generating more realistic details. The proposed method, named DSRGAN, takes advantages from both the model-based conventional algorithm and the data-driven deep learning network. Experimental results demonstrate that the DSRGAN outperforms the state-of-the-art SISR methods on perceptual metrics, meanwhile achieving comparable results in terms of fidelity metrics. Following the DSRGAN, it is feasible to incorporate other conventional image processing algorithms into a deep learning network to form a model-based deep SISR. [ABSTRACT FROM AUTHOR]

Images captured under low-light environments typically have poor visibility, affecting many advanced computer vision tasks. In recent years, there have been some low-light image enhancement models based on deep learning, but they have not been able to effectively mine the deep multiscale features in the image, resulting in poor generalization performance and instability of the model. The disadvantages are mainly reflected in the color distortion, color unsaturation and artifacts. Current methods unable to adjust the exposure effectively, resulting in uneven exposure or partial overexposure. To address these issues, we propose an end-to-end low-light image enhancement model, which is called multiscale low-light image enhancement network with illumination constraint (MLLEN-IC), to achieve preferable generalization ability and stable performance. On the one hand, we use the squeeze-and-excitation-Res2Net block (SE-Res2block) as a base unit to enhance the model’s ability by extracting deep multiscale features. On the other hand, to make the model more adaptable in low-light image enhancement tasks, we calculate the illumination constraint by the low-light itself to prevent overexposure, uneven exposure, and unsaturated colors. Extensive experiments are conducted to demonstrate MLLEN-IC not only adjusts light levels, but also has a more natural visual effect, and avoids problems such as color distortion, artifacts, and uneven exposure. In particular, MLLEN-IC has pretty generalization and stability performance. The source code and supplementary are available at https://github.com/CCECfgd/MLLEN-IC. [ABSTRACT FROM AUTHOR]

In this paper, we conduct an extensive study on the use of pre-trained convolutional neural networks (CNNs) for omnidirectional image quality assessment (IQA). To cope with the lack of available IQA databases, transfer learning from seven pre-trained CNN models is investigated over retraining on standard 2D databases. In addition, we explore the influence of various image representations and training strategies on the model’s performance. A comparison of the use of projected versus radial content, and multichannel CNN versus patch-wise training is also covered. The experimental results on two publicly available databases are used to draw conclusions about which strategy best fits the visual quality prediction and at which computational cost. The analysis shows that retraining CNN models on 2D IQA databases improves the prediction accuracy. The latter and the required computational time are found to be significantly affected by the training strategy. Cross-database evaluations demonstrate that the nature and variety of the content impact the generalization ability of the models. Finally, we show that conclusions coming from other image processing communities may not hold for IQA. The provided discussion shall provide insights and recommendations when using pre-trained CNNs for omnidirectional IQA. [ABSTRACT FROM AUTHOR]

Even if Application-Specific Integrated Circuits (ASIC) have proven to be a relevant choice for integrating inference at the edge, they are often limited in terms of applicability. In this paper, we demonstrate that an ASIC neural network accelerator dedicated to image processing can be applied to multiple tasks of different levels: image classification and compression, while requiring a very limited hardware. The key component is a reconfigurable, mixed-precision (3b/2b/1b) encoder that takes advantage of proper weight and activation quantizations combined with convolutional layer structural pruning to lower hardware-related constraints (memory and computing). We introduce an automatic adaptation of linear symmetric quantizer scaling factors to perform quantized levels equalization, aiming at stabilizing quinary and ternary weights training. In addition, a proposed layer-shared Bit-Shift Normalization significantly simplifies the implementation of the hardware-expensive Batch Normalization. For a specific configuration in which the encoder design only requires 1Mb, the classification accuracy reaches 87.5% on CIFAR-10. Besides, we also show that this quantized encoder can be used to compress image patch-by-patch while the reconstruction can performed remotely, by a dedicated full-frame decoder. This solution typically enables an end-to-end compression almost without any block artifacts, outperforming patch-based state-of-the-art techniques employing a patch-constant bitrate. [ABSTRACT FROM AUTHOR]

Optical flow estimation is a fundamental task in computer vision and image processing. Due to the difficulty in obtaining the ground truth of flow field, unsupervised learning approaches attract more and more research interests in recent years. However, despite of their good generalization capability, unsupervised optical flow methods suffer in the scenarios with large displacement, small objects, and occlusions. In this work, we propose a novel optical flow network based on decoder with multi-scale kernels. Different from previous U-Net like or pyramidal methods, we design our network based on RAFT architecture that with a 4D correlation layer and recurrent decoder. More importantly, we incorporate three novel ideas with regard to the input, information processing and output of the update units improve the performance. Firstly, we utilize various motion-related information as input to the update units. Secondly, we propose a module of multi-scale update unit. Thirdly, for the final flow up-sampling procedure, we propose an image-guided up-sampling loss to guide the learning of up-sampling masks. Our model is trained by the occlusion-aware photometric loss, edge-aware smoothness loss, self-supervised loss, and image-guided up-sampling loss. Experimental results demonstrate that our model achieves the state-of-the-art performance on both Sintel and KITTI and outperforms other unsupervised optical flow methods remarkably. [ABSTRACT FROM AUTHOR]

As two practical and important image processing tasks, color demosaicking (CDM) and super-resolution (SR) have been studied for decades. However, most literature studies these two tasks independently, ignoring the potential benefits of a joint solution. In this paper, aiming at efficient and effective joint demosaicking and super-resolution (JDSR), a well-designed two-stage convolutional neural network (CNN) architecture is proposed. For the first stage, by making use of the sampling-pattern information, a pattern-aware feature extraction (PFE) module extracts features directly from the Bayer-sampled low-resolution (LR) image, while keeping the resolution of the extracted features the same as the input. For the second stage, a dual-branch feature refinement (DFR) module effectively decomposes the features into two components with different spatial frequencies, on which different learning strategies are applied. On each branch of the DFR module, the feature refinement unit, namely, densely-connected dual-path enhancement blocks (DDEB), establishes a sophisticated nonlinear mapping from the LR space to the high-resolution (HR) space. To achieve strong representational power, two paths of transformations and the channel attention mechanism are adopted in DDEB. Extensive experiments demonstrate that the proposed method is superior to the sequential combination of state-of-the-art (SOTA) CDM and SR methods. Moreover, with much smaller model size, our approach also surpasses other SOTA JDSR methods. [ABSTRACT FROM AUTHOR]

Joint photographic experts group (JPEG) compression is widely used in image processing and computer vision. Detecting double compressed JPEG images is a common problem in forensics and detecting compressed images with the same quantization matrix remains a challenging task. However, most existing methods were designed for detection in grayscale images and cannot fully use the unique characteristics of color images (such as the relationship between channels and color information). In addition, the performance of existing methods is unsatisfactory for low JPEG quality factors and in cross detection experiments. To solve these problems, we analyze the stability of a color image to obtain the convergence error and transposition error. According to the convergence characteristics of color JPEG images, the continuous compression by the same quantization matrix can make the JPEG image tend to be stable. The final stable state and the convergence process are determined by the number of compressions of the original image. Thus, continuously compressed JPEG images can be regarded as a continuous frame to obtain the convergence error. As the color image converges, its ability to resist interference decreases. To reflect the changes in anti-interference ability, the transposition operation is used to disturb the color JPEG image to obtain the transposition error. In addition, quaternion mapping is used to retain the relationship between continuously compressed JPEG images and enlarge the influence caused by transposition operation. In our experiments on several image databases, the proposed method outperforms existing methods in different settings. [ABSTRACT FROM AUTHOR]

Image classification is a fundamental artificial intelligence task that labels images into one of some predefined classes. However, training complex image classification models requires a large amount of computation resources and data in order to reach state-of-the-art performance. This demand drives the growth of distributed deep learning, where multiple agents cooperatively train global models with their individual datasets. Among such learning systems, decentralized learning is particularly attractive, as it can improve the efficiency and fault tolerance by eliminating the centralized parameter server, which could be the single point of failure or performance bottleneck. Although the agents do not need to disclose their training image samples, they exchange parameters with each other at each iteration, which can put them at the risk of data privacy leakage. Past works demonstrated the possibility of recovering training images from the exchanged parameters. One common defense direction is to adopt Differential Privacy (DP) to secure the optimization algorithms such as Stochastic Gradient Descent (SGD). Those DP-based methods mainly focus on standalone systems, or centralized distributed learning. How to enforce and optimize DP protection in decentralized learning systems is unknown and challenging, due to their complex communication topologies and distinct learning characteristics. In this paper, we design TOP- DP, a novel solution to optimize the differential privacy protection of decentralized image classification systems. The key insight of our solution is to leverage the unique features of decentralized communication topologies to reduce the noise scale and improve the model usability. (1) We enhance the DP-SGD algorithm with this topology-aware noise reduction strategy, and integrate the time-aware noise decay technique. (2) We design two novel learning protocols (synchronous and asynchronous) to protect systems with different network connectivities and topologies. We formally analyze and prove the DP requirement of our proposed solutions. Experimental evaluations demonstrate that our solution achieves a better trade-off between usability and privacy than prior works. To the best of our knowledge, this is the first DP optimization work from the perspective of network topologies. [ABSTRACT FROM AUTHOR]

Image quality assessment (IQA) plays a central role in many image processing algorithms and systems. Although many popular IQA models achieves high performance on existing released databases, they are still not well accepted in practical applications due to the not-always satisfactory accuracy on real-world data and situations. In this paper, we revisit the IQA research, and point out an ignored but interesting problem in IQA: the coarse-grained (i.e., when quality variation is sufficiently big, as the setting of most IQA databases up to date) statistical results evaluated on existing databases mask the fine-grained differentiation. Accordingly, we present a survey on image quality assessment from a new perspective: fine-grained image quality assessment (FG-IQA). Recent FG-IQA research on five major kinds of images is introduced, and some popular IQA methods are analyzed from FG-IQA perspective. The potential problems for current IQA research based on existing coarse-grained databases are analyzed and the necessity of more FG-IQA research is justified. Finally, we discuss some challenges and possible directions for future works in FG-IQA. [ABSTRACT FROM AUTHOR]

Retrieving 3D shapes based on 2D images is a challenging research topic, due to the significant gap between different domains. Recently, various approaches have been proposed to handle this problem. However, the majority of methods target the cross-domain retrieval task as a pure domain adaptation problem, which focuses on the alignment but ignores the visual relevance between the 2D images and their corresponding 3D shapes. To fundamentally decrease the divergence between different domains, we propose a novel cross-domain learning network (CLN) for 2D image-based 3D shape retrieval task. First, we estimate the pose information from the 2D image to guide the view rendering of 3D shapes, which increases the visual correlations of the cross-domain data to eliminate the divergence between them. Second, we introduce a novel joint learning network, considering both the domain-specific characteristics and the cross-domain interactions for data alignment, which further compensates for the gap between different domains by controlling the distance of intra- and inter-classes. After the metric learning process, discriminative descriptors of images and shapes are generated for the cross-domain retrieval task. To prove the effectiveness and robustness of the proposed method, we conduct extensive experiments on the MI3DOR, SHREC’13, and SHREC’14 datasets. The experimental results demonstrate the superiority of our proposed method, and significant improvements have been achieved compared with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

As an efficient watermark attack method, geometric distortions destroy the synchronization between the watermark encoder and decoder. Local geometric distortion is a considerable challenge in the watermarking field. Although many geometric distortion resilient watermarking schemes have been proposed, few perform well against local geometric distortions, such as random bending attacks (RBAs). To address this problem, this paper proposes a novel watermark synchronization process and a corresponding watermarking scheme. In our scheme, the watermark bits are represented by random patterns. The message is encoded to obtain a watermark unit, and the watermark unit is flipped to generate a symmetrical watermark. Then, the symmetrical watermark is additively embedded into the spatial domain of the host image. In watermark extraction, we first obtain the theoretical mean-square error minimized estimation of the watermark. Then, an autoconvolution function is applied to this estimation to detect the symmetry and obtain a watermark unit map. According to this map, the watermark can be accurately synchronized, and then extraction can be performed. Experimental results demonstrate the excellent robustness of the proposed watermarking scheme to local geometric distortions, global geometric distortions, common image processing operations, and some kinds of combined attacks. [ABSTRACT FROM AUTHOR]

In this work, we simulate the early visual information processing mechanisms in biological visual system (BVS) to solve the visible-infrared image fusion (VIIF) task. Concretely, both infrared and visible images are first processed with a dynamic receptive field (DRF), which is imitated by a Difference of Gaussian (DoG) function whose parameters are adjusted according to local image statistics (e.g., local edge responses). The DRF processing produces two components for each source image (e.g., the visible image or the infrared image) that respectively represent the results of On-center based DRF and Off-center based DRF. Then, the results of On-center based DRF for visible image are fused with the results of Off-center based DRF for infrared image and the results of On-center based DRF for infrared image are fused with the results of Off-center based DRF for visible image, according to the mechanisms of cortex-based center-surround fusion. Algorithmically, this step fuses the visible and infrared images processed by DRF with On-center and Off-center according to the different levels of local homogeneity. Moreover, a feedward signal acting as the sub-cortical flow is also introduced to adjust the results during the fusion. The final output image is simply obtained by the summation of two components after the cortex and sub-cortex based fusion. Qualitative and quantitative tests on four datasets demonstrate that our approach can fuse the infrared and visible images effectively with the good background details and discernible salient areas. We emphasize the importance of corticothalamic feedback, cortex and sub-cortex-based fusion, and the interactions between On-center pathway and Off-center pathway that are ubiquitous in BVS for producing the high-quality visual signals. [ABSTRACT FROM AUTHOR]

With the development of video and image processing technology, the field of video tampering forensics is facing enormous challenges. Specifically, as the fundamental basis of judicial forensics, passive forensics for object removal video forgery is particularly essential. To extract tampering traces in video more sufficiently, the author proposed a spatiotemporal trident network based on the spatial rich model (SRM) and 3D convolution (C3D), which provides three branches and can theoretically improve the detection and localization accuracy of tampered regions. Based on the spatiotemporal trident network, a temporal detector and a spatial locator were designed to detect and locate the tampered regions in the temporal and spatial domains of videos. For the temporal detector, 3D CNNs were employed in three branches as the encoders and a bidirectional long short-term memory (BiLSTM) as the decoder. For the spatial locator, a backbone network named C3D-ResNet12 was designed as the encoder of the three branches, and the region proposal networks (RPNs) were employed as the decoders in three branches. In addition, we optimized the loss functions of the above two algorithms based on focal loss and GIoU loss. The experimental results revealed the effectiveness of spatiotemporal detection and localization algorithms: for temporal forgery detection, the accuracy of the frame classification increased to 99+%; for spatial forgery localization, the successful localization rate of the tampered regions in forged frames reached 96+%, and the mean intersection over union of the located tampered regions and the real tampered regions reached 62+%. [ABSTRACT FROM AUTHOR]

Color demosaicing is an essential step in the camera image processing pipeline, especially on hardware platforms for real-time video applications. Though many demosaicing algorithms have been proposed in the past two decades, there remains a substantial gap between industrial needs and academic research. On one hand, industry requires a high perceptual quality, artifact-free, and low-cost demosaicing algorithm that is noniterative and small window based ready to be implemented on a hardware platform with a limited line buffer. On the other hand, academia is targeting high PSNR/SSIM, with the computation cost and line buffer receiving second priority, and often a frame buffer and iterative operation are used. The cost, large line buffer and iteration requirement make most existing demosaicing algorithms inapplicable on hardware platforms. In this paper, we introduce a novel low-cost demosaicing algorithm to narrow the gap. We keep the operation window size and computation cost as the first priority and achieve both high PSNR/SSIM and visual perceptual quality compared to previous state-of-the-art methods on standard test datasets. We fully investigate the a priori knowledge of natural scene raw images and find several key cues that are beneficial to demosaicing. Our demosaicing algorithm is a smart fusion of these useful cues. Furthermore, we solve typical demosaicing issues that occur in many traditional methods, including false color artifacts, T-section closing, and zippering artifacts. The proposed method has no learning stage, no iteration operation, a small line buffer and a limited number of parameters, so it can easily be applied to hardware platforms. [ABSTRACT FROM AUTHOR]

Blind image deblurring is a long standing challenging problem in image processing and low-level vision. Recently, sophisticated priors such as dark channel prior, extreme channel prior, and local maximum gradient prior, have shown promising effectiveness. However, these methods are computationally expensive. Meanwhile, since these priors involved subproblems cannot be solved explicitly, approximate solution is commonly used, which limits the best exploitation of their capability. To address these problems, this work firstly proposes a simplified sparsity prior of local minimal pixels, namely patch-wise minimal pixels (PMP). The PMP of clear images is much more sparse than that of blurred ones, and hence is very effective in discriminating between clear and blurred images. Then, a novel algorithm is designed to efficiently exploit the sparsity of PMP in deblurring. The new algorithm flexibly imposes sparsity inducing on the PMP under the maximum a posterior (MAP) framework rather than directly uses the half quadratic splitting algorithm. By this, it avoids non-rigorous approximation solution in existing algorithms, while being much more computationally efficient. Extensive experiments demonstrate that the proposed algorithm can achieve better practical stability compared with state-of-the-arts. In terms of deblurring quality, robustness and computational efficiency, the new algorithm is superior to state-of-the-arts. Code for reproducing the results of the new method is available at https://github.com/FWen/deblur-pmp.git. [ABSTRACT FROM AUTHOR]

Watermarking neural networks is a quite important means to protect the intellectual property (IP) of neural networks. In this paper, we introduce a novel digital watermarking framework suitable for deep neural networks that output images as the results, in which any image outputted from a watermarked neural network must contain a certain watermark. Here, the host neural network to be protected and a watermark-extraction network are trained together, so that, by optimizing a combined loss function, the trained neural network can accomplish the original task while embedding a watermark into the outputted images. This work is totally different from previous schemes carrying a watermark by network weights or classification labels of the trigger set. By detecting watermarks in the outputted images, this technique can be adopted to identify the ownership of the host network and find whether an image is generated from a certain neural network or not. We demonstrate that this technique is effective and robust on a variety of image processing tasks, including image colorization, super-resolution, image editing, semantic segmentation and so on. [ABSTRACT FROM AUTHOR]

It is challenging to extend the support region of state-of-the-art local edge-preserving filtering approaches to the entire input image on account of huge memory cost and heavy computational burden. In this paper, we propose an O(N) time recursive non-local edge-aware filter. A novel graph and a linear time algorithm are presented to effectively propagate information across the entire image. In this graph, information is propagated along all directions to avoid visual artifacts. Both the intensity similarity and the spatial affinity are utilized to estimate the similarity of neighboring pixels, and the distance of any two pixels is the length of the path between these two pixels on a binary tree. Specifically, the input image is filtered at four directions, namely left-to-right, right-to-left, top-to-bottom and bottom-to-top. In each pass, the un-normalized output and the normalization constant of the root node are computed recursively from leaf nodes to the root node on a binary tree in linear time. The filtering output is the average of the outputs for these four directions. A comparison with other non-local edge-aware filters is presented to show the advantages of our approach. Extensive experiments demonstrate that our recursive non-local edge-preserving filter is effective in a variety of computer vision and image processing applications, including edge-aware filtering, detail enhancement, stylization, and stereo matching. [ABSTRACT FROM AUTHOR]

Being able to predict the salient object is of fundamental importance in image processing and computer vision. With numerous approaches proposed for automatic image and video salient object detection, much less work has been dedicated to detecting and segmenting salient objects from light fields. In this article, based on the intrinsic characteristics of light fields, we carefully explore the complementary coherence among multiple cues including spatial, edge and depth information, and elaborately design a multi-task collaborative network for light field salient object detection. More specifically, the correlation mechanisms among edge detection, depth inference and salient object detection are carefully investigated to facilitate the representative saliency features. We first model the coherence among low-level features and heuristic semantic priors, as well as the edge information. Subsequently, the depth-oriented saliency features are derived from the geometry of light fields, in which the 3D convolution operation is leveraged with powerful representation capability to model the disparity correlations among multiple viewpoint images. Finally, a feature-enhanced salient object generator is developed to integrate these complementary saliency features, leading to the final salient object predictions for light fields. Quantitative and qualitative experiments demonstrate the superiority of our proposed model against the state-of-the-art methods over the public light field salient object detection datasets. [ABSTRACT FROM AUTHOR]

A reliable and accurate visual object 6DoF pose tracking system for texture-less objects plays an important role in various fields of modern industry hence it has been a hot research topic for decades. Traditional feature-based pose tracking methods require rich feature points on objects, and it cannot handle texture-less objects. To tackle this problem, the paper proposes a novel edge-based method for continuous 6DOF pose tracking of texture-less objects. The pose of the object is estimated by minimizing the matching error between extracted image edges and re-projected CAD model edges. The matching error is represented using the Directional Chamfer Matching (DCM) Tensor. Compared with previous methods, the proposed system improves the overall performance of pose tracking system in two ways. Firstly, the method proposes an analytical mathematic model in the optimization process; Secondly, the method proposes an adaptive edge point weighting algorithm to tackle the occlusion or edge weakness problem. Both methods help improve the accuracy and robustness of the pose estimation system. With the benefit of GPU acceleration on DCM Tensor calculation the proposed method could run in real time. Extensive experiments are conducted both on public datasets and CG-rendered synthetic datasets to validate the accuracy and robustness of the proposed algorithm against other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

N × N filter operations are frequently used in various image processing algorithms in display driver circuits. The implementation of the N × N filter requires a storage element to temporarily retain N or N-1 lines of display data. The traditional approach for this temporary storage element for N × N image filter is either by using N blocks of memory to store N lines of display data with single-port six-transistor (6T) SRAM bit-cells or by using N-1 blocks of memory to store N-1 lines of display data with dual-port eight-transistor (8T) SRAM bit-cells. In this paper, a pseudo multi-port SRAM circuit is proposed for N × N filter in image processing in a display driver integrated circuit (IC). By using pre-read mechanism and word-line/column selection signal forwarding technique, the proposed approach only stores N-1 lines of display 3 × 3 filter application, the proposed approach reduces the overall layout area by 50.3% and 30.2% compared to the traditional dual-port 8T and single-port 6T memory implementations, respectively, in an industrial 0.18-μm CMOS technology. Furthermore, the power used to perform a 3 × 3 filter operation is reduced by 47% and 30.8% with the proposed approach as compared to the traditional dual-port 8T and signal-port 6T memory circuits, respectively, with slight degradation of the access speed. [ABSTRACT FROM AUTHOR]

Low level image restoration is an integral component of modern artificial intelligence (AI) driven camera pipelines. Most of these frameworks are based on deep neural networks which present a massive computational overhead on resource constrained platform like a mobile phone. In this paper, we propose several lightweight low-level modules which can be used to create a computationally low cost variant of a given baseline model. Recent works for efficient neural networks design have mainly focused on classification. However, low-level image processing falls under the ‘image-to-image’ translation genre which requires some additional computational modules not present in classification. This paper seeks to bridge this gap by designing generic efficient modules which can replace essential components used in contemporary deep learning based image restoration networks. We also present and analyse our results highlighting the drawbacks of applying depthwise separable convolutional kernel (a popular method for efficient classification network) for sub-pixel convolution based upsampling (a popular upsampling strategy for low-level vision applications). This shows that concepts from domain of classification cannot always be seamlessly integrated into ‘image-to-image’ translation tasks. We extensively validate our findings on three popular tasks of image inpainting, denoising and super-resolution. Our results show that proposed networks consistently output visually similar reconstructions compared to full capacity baselines with significant reduction of parameters, memory footprint and execution speeds on contemporary mobile devices. [ABSTRACT FROM AUTHOR]

JPEG is the most widely used lossy image compression standard. When using JPEG with high compression ratios, visual artifacts cannot be avoided. These artifacts not only degrade the user experience but also negatively affect many low-level image processing tasks. Recently, convolutional neural network (CNN)-based compression artifact removal approaches have achieved significant success, however, at the cost of high computational complexity due to an enormous number of parameters. To address this issue, we propose a dual-stream recursive residual network (STRRN) which consists of structure and texture streams for separately reducing the specific artifacts related to high-frequency or low-frequency image components. The outputs of these streams are combined and fed into an aggregation network to further enhance the restored images. By using parameter sharing, the proposed network reduces the total number of training parameters significantly. Moreover, experiments conducted on five commonly used datasets confirm that the proposed STRRN can efficiently reduce the compression artifacts, while using up to 4.6 times less training parameters and 5 times less running time compared to the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Counting passengers in railway compartments is an essential problem for improving service quality, user experience, public security, and disaster relief in the railway system. Considering many limitations in the compartment, the infrared sensor, 3D camera, etc. are not practical in this scene. Due to the flexibility and lower cost, solutions with standard cameras attract much attention in real applications. However, since the problem with scale variation in the narrow space is different from universal detection or counting problems, the specific benchmark of dataset and methods should be provided and proposed for this task. In this paper, we provide a passenger counting dataset. Relying on this dataset, we propose a passenger counting method. The solution contains a motion supervised multi-scale representation method which provides proposals against scale variation, a spatially-temporally enhanced counting which provides precise counting numbers, and a partial proposal method which conducts methods to be utilized in reality. With the proposed solution, the passengers counting task is solved in higher accuracy and practicable in the compartment environment. In experiments, the results show that all the modules in our solution are useful and efficient, and our method outperforms in comparison with others in the compartment scene. [ABSTRACT FROM AUTHOR]

Due to their good rotational invariance and stability, image continuous orthogonal moments are intensively applied in rotationally invariant recognition and image processing. However, most moments produce numerical instability, which impacts the image reconstruction and recognition performance. In this paper, a new set of invariant continuous orthogonal moments, polar harmonic Fourier moments (PHFMs), free of numerical instability is designed. The radial basis functions (RBFs) of the PHFMs are much simpler than those of the Chebyshev-Fourier moments (CHFMs), orthogonal Fourier-Mellin moments (OFMMs), Zernike moments (ZMs), and pseudo-Zernike moments (PZMs). For the same degree, the RBFs of the PHFMs have more zeros and are more evenly distributed than those of the ZMs and PZMs. Therefore, PHFMs do not suffer from information suppression problem; hence, the image description ability of the PHFMs is superior to that of the ZMs and PZMs. Moreover, the RBFs of the PHFMs are always less than or equal to 1.0 near the unit disk center, whereas those of the OFMMs, PZMs, CHFMs, and radial harmonic Fourier moments (RHFMs) are infinite (implying numerical instability). This indicates that PHFMs can outperform these moments in image reconstruction tasks. We theoretically and experimentally demonstrate that PHFMs outperform the above moments in reconstructing images and recognizing rotationally invariant objects considering noise and various attacks. This paper also details the significance of the PHFM phase in image reconstruction, angle estimation using PHFMs, and the accurate moment selection of the PHFMs. [ABSTRACT FROM AUTHOR]

Distortion rectification is a fundamental task in the field of computer vision and image processing. Nevertheless, previous methods have regarded distortion rectification as a static problem that learns a mapping function and corrects the distorted image to a unique state. However, this state is generally not the optimal solution, as it would result in an under-rectified or over-rectified structure. In this study, we revisit the classical distortion rectification task with a new perspective and redesign the algorithm, inspired by video processing techniques. Specifically, we regard distortion rectification as a dynamic problem that can be extended to a sequence of different distortion states: the input distorted image (t), under-rectified image (t+1), ideal-rectified image (t+2), and over-rectified image (t+3). We first estimate the residual distortion map (RDM) between the input distorted image and the coarse-rectified (t+1 or t+3) image. Here, RDM indicates the motion difference between two distorted images. Subsequently, the RDM is used to guide the refinement rectification process, aiming to convert the coarse-rectified state into the ideal-rectified state. In addition, the flexible implementation of the proposed refinement process with RDM to improve the rectification results of any method is appealing. The experimental results demonstrate that our method outperforms the state-of-the-art schemes by a significant margin, revealing approximately 40% improvement through quantitative evaluation. [ABSTRACT FROM AUTHOR]

Semi-global matching (SGM) is favored for high accuracy real-time stereo matching design as it achieves a good trade-off between disparity image quality and computational complexity. Nevertheless, most of previous SGM designs so far are restricted to the real-time processing of small image resolution and disparity range, or achieve high throughput by simplifying the original algorithm at the penalty of significant disparity image quality degradation. We analyze that the major challenge to efficient SGM design is its memory architecture, including both on-chip memory cost and off-chip memory bandwidth. We address the memory architecture challenge by algorithm and architecture co-design. Based on two observed features of SGM algorithm, i.e. incompleteness and inaccuracy, this paper proposes several efficient techniques to reduce on-chip memory cost and compress off-chip memory bandwidth respectively. Moreover, we also design high throughput and pipelined architecture to implement the proposed techniques. The disparity image quality and hardware efficiency of the proposed SGM design are evaluated on both KITTI2015 and Middlebury V3 stereo datasets. Evaluation results demonstrate that, the throughput of the proposed circuit designs can easily achieve 1080P@30fps at the disparity range of 128, and can reduce the on-chip memory cost and off-chip memory bandwidth by up to $4\times $ and $2\times $ respectively while achieving better or the same disparity image quality, compared with the best reference design techniques. [ABSTRACT FROM AUTHOR]

Blur is one of the most common distortions that degrade natural images. This stimulates the blossom of sharpness assessment metrics. Existing sharpness metrics possess good performance for evaluating simulated blur, but are limited for the more common realistic blur that are introduced during image capture and processing in real life. To this end, we propose an effective Realistic Blur Assessment method (RBA) based on discrepancy learning. First, motivated by the fact that the distortion-free reference images are usually unavailable in practice, but the Human Visual System (HVS) can still accurately perceive image sharpness by quantifying the perceptual discrepancy between the distorted image and the hallucinated reference image in mind, we propose to train a discrepancy generation model to automatically generate the discrepancy map from the distorted image analogous to the HVS. This is achieved by using a deep neural network with rich training images. With the discrepancy map, two sharpness-aware features, i.e. sparse representation based entropy of primitive and content-guided variation of power, are then extracted to severally quantify spatial visual information amount and spectral power. Finally, the two features are integrated to produce the overall sharpness score. Extensive experiments demonstrate the superiority of the proposed method over the state-of-the-arts. [ABSTRACT FROM AUTHOR]

Image dehazing is a crucial image processing step for outdoor vision systems. However, images recovered through conventional image dehazing methods that use either haze-relevant priors or heuristic cues to estimate transmission maps may not lead to sufficiently accurate haze removal from single images. The most commonly observed effects are darkened and brightened artifacts on some areas of the recovered images, which cause considerable loss of fidelity, brightness, and sharpness. This paper develops a variational image dehazing method on the basis of a color-transfer image dehazing model that is superior to conventional image dehazing methods. By creating a color-transfer image dehazing model to remove haze obscuration and acquire information regarding the coefficients of the model by using the devised convolutional neural network-based deep framework as a supervised learning strategy, an image fidelity, brightness, and sharpness can be effectively restored. The experimental results verify through quantitative and qualitative evaluations of either synthesized or real haze images, and the proposed method outperforms existing single image dehazing methods. [ABSTRACT FROM AUTHOR]

Considering that traditional image steganography technologies suffer from the potential risk of failure under lossy channels, an enhanced adaptive steganography with multiple robustness against image processing attacks is proposed, while maintaining good detection resistance. First, a robust domain constructing method is proposed utilizing robust element extraction and optimal element modification, which can be applied to both spatial and JPEG images. Then, a robust steganography is proposed based on “Robust Domain Constructing + RS-STC Codes,” combined with cover selection, robust cover extraction, message coding, and embedding with minimized costs. In addition, to provide a theoretical basis for message extraction integrity, the fault tolerance of the proposed algorithm is deduced using error model based on burst errors and decoding damage. Finally, on the basis of parameter discussion about robust domain construction, performance experiments are conducted, and the recommended coding parameters are given for lossy channels with different attacks using the analytic results for fault tolerance. A series of experimental results demonstrate that the proposed algorithm can extract embedded messages with significantly higher accuracy after different attacks, such as compression, noising, scaling and other attacks, compared with the state-of-the-art adaptive steganography, and robust watermarking algorithms, while maintaining good detection resistant performance. [ABSTRACT FROM AUTHOR]

Dictionary learning has emerged as a powerful tool for a range of image processing applications and a proper dictionary always plays a key issue to the final achievable performance. In this paper, a class-oriented discriminative dictionary learning (CODDL) method is presented for image classification applications. It takes a comprehensive consideration of multiple optimization objectives, emphasizing class discrimination of both dictionary atoms and representation coefficients. The atoms of the learned dictionary should be grouped into class level sub-dictionaries. Meanwhile, the sparse representation coefficients of an input sample should be concentrated on the sub-dictionary of the class it belongs to. Then, based on the learned class-oriented discriminative dictionary, the structured representation coefficients can thus be used for image classification with a simple and efficient classification scheme. The superior performance of the proposed algorithm is demonstrated through extensive experiments. [ABSTRACT FROM AUTHOR]

Color and color differences are critical aspects in many image processing and computer vision applications. A paradigmatic example is object segmentation, where color distances can greatly influence the performance of the algorithms. Metrics for color difference have been proposed in the literature, including the definition of standards such as CIEDE2000, which quantifies the change in visual perception of two given colors. This standard has been recommended for industrial computer vision applications, but the benefits of its application have been impaired by the complexity of the formula. This paper proposes a new strategy that improves the usability of the CIEDE2000 metric when a maximum acceptable distance can be imposed. We argue that, for applications where a maximum value, above which colors are considered to be different, can be established, then it is possible to reduce the amount of calculations of the metric, by preemptively analyzing the color features. This methodology encompasses the benefits of the metric while overcoming its computational limitations, thus broadening the range of applications of CIEDE2000 in both the computer vision algorithms and computational resource requirements. [ABSTRACT FROM AUTHOR]

With the advances in commercial light field cameras, light field image processing has attracted considerable attention from researchers. In this paper, we propose a novel method for generating stereoscopic images from a light field image pair with flexible control over the convergence of the virtual stereo cameras. We have developed a light field image-capturing prototype that consists of two horizontally arranged light field cameras (i.e., with their optical axes being parallel to each other). When using our proposed device for image/video capture, stereo photographers can concentrate on how to capture the desired visual experience without being frequently disturbed by having to manipulate the stereo camera parameters, i.e., the convergence angle of a stereo camera. During postprocessing, our method estimates accurate disparity maps for the light field image pair and then generates the target stereoscopic images that satisfy the desired stereo camera convergence requirements by adopting a novel view synthesis method for light field images. We have conducted extensive experiments to demonstrate the effectiveness of our proposed method. [ABSTRACT FROM AUTHOR]

Deep learning has achieved great success in the past decade, especially in the fields of computer vision and image processing. After witnessing such success, video coding experts are motivated to consider whether deep learning can also benefit video coding, and if so, they seek to discover why and how. Indeed, a number of research studies have been conducted to explore deep learning for image and video coding, which has been an active and fast-growing research area especially since the year 2015. These prior arts can be divided into two categories: new coding schemes that are built solely upon deep networks (deep schemes), and deep network-based coding tools that are embedded into traditional coding schemes (deep tools). Moreover, in the responses to the joint call for proposals on video compression with capability beyond High Efficiency Video Coding (HEVC), a number of deep tools have been proposed, and some of them are further studied for the upcoming Versatile Video Coding (VVC). In this paper, we summarize the ongoing efforts in the Joint Video Experts Team about the proposed deep tools, and we discuss several promising tools in much detail, including neural network-based intra prediction, convolutional neural network (CNN) based in-loop filtering, and CNN-based block-adaptive-resolution coding. A series of experimental results are provided to demonstrate the capability of these tools in achieving higher compression efficiency than the VVC or HEVC anchor. These results shed light on the promising direction of deep learning-based future video coding, towards which a lot of open problems call for further study. [ABSTRACT FROM AUTHOR]

Wavelet transform using Haar filter is a fast process for decomposing an image into low and high frequency sub-bands, which is an important step in multi-focus image fusion. This transformation alone is usually not sufficient to produce satisfying fused images, and therefore additional tools like focused region decision map and feature extraction are needed to enhance the fusion quality. In this paper, we propose a multi-focus image fusion algorithm that is suitable for efficient hardware implementation. The algorithm speed is significantly improved by utilizing Haar wavelet and computationally simple fusion rules. To further improve the circuit power and delay, we limit the logic operations to additions, subtractions, and multiplications only. Experiments on different benchmarks demonstrate that our proposed algorithm can reduce the fusion time by up to 99.97% compared with the state-of-the-art competing methods without compromising the fusion quality. In addition, the hardware implementation of the proposed algorithm reduces the circuit area and delay by 79.5% and 92.5%, respectively, when compared to the most competitive algorithm in this paper while maintaining similar fusion quality. [ABSTRACT FROM AUTHOR]

Human action recognition (HAR) is an important field of research that intercepts with areas such as image processing, computer vision, and the design of fast algorithms, among others. HAR has several important applications including healthcare monitoring, security and surveillance, assisted living, smart homes, and video search and indexing. Despite recent developments in the field, major challenges remain. For instance, HAR is computationally expensive. Tasks such as video preprocessing, feature extraction, feature quantization, and feature classification require the execution of millions of arithmetic operations for a video sequence lasting a few seconds. To address these problems, we propose a heterogeneous approach that is based on an extensive algorithmic and experimental analysis of the histogram of gradients application. We divide the application into four stages and evaluate each on the CPU, GPU, and FPGA platforms. Our heterogeneous design combines the strengths of both the FPGA and GPU platforms, and achieves a $1.3X$ speedup compared with a state-of-the-art GPU while being $1.5X$ more energy efficient than other homogeneous solutions, including FPGA-based designs. Moreover, our heterogeneous HAR design using fixed-point arithmetic has comparable accuracy to those of HAR algorithms using single precision floating point arithmetic. [ABSTRACT FROM AUTHOR]

The rising popularity of social networks and cloud computing has greatly increased a number of JPEG compressed image exchanges. In this context, the security of the transmission channel and/or the cloud storage can be susceptible to privacy leaks. The selective encryption is an efficient tool to mask the image content and to protect confidentiality while remaining format-compliant. However, image processing in the encrypted domain is not a trivial task. In this paper, we present a JPEG crypto-compression method which allows us to recompress a JPEG crypto-compressed image several times, without any information about the secret key or the original image content. Indeed, using the proposed method in this paper, each recompression can be done directly on the JPEG bitstream by removing the last bit of the code representation of each non-zero coefficient, adapting the entropic code part, and slightly modifying the quantization table. This method is efficient to recompress JPEG crypto-compressed images in terms of compression ratio. Moreover, the decryption of the recompressed image produces an image with a very similar visual quality when compared to the original image, according to the obtained results. [ABSTRACT FROM AUTHOR]

Resampling detection is one of the most important topics in image forensics, and the most widely used method in resampling detection is spectral analysis. Since JPEG is the most widely used image format, it is reasonable that the resampling operation is processed on JPEG images. JPEG block artifacts bring severe interference to spectrum-based methods and degrade the detection performance. In addition, the spectral characteristics of the downscaling scenarios are very weak. The detection of downscaling still presents a considerable challenge to forensic applications. In this paper, we propose a method to estimate the downscaling factors of pre-JPEG compressed images in the presence of image downscaling after JPEG compressions. We first analyze the spectrum of scaled images and give an exact formulation of how the scaling factors influence the appearance of periodic artifacts. The expected positions of the characteristic resampling peaks are analytically derived. For the downscaling scenario, the shifted JPEG block artifacts produce periodic peaks, which cause misdetection in the characteristic peak. We find that the interval between the adjacent extrema of difference images obeys the geometric distribution and the distribution has periodic peaks for JPEG images. Hence, we adopt the difference image extremum interval histogram and combine the spectral method to obtain the final estimation. The experimental results demonstrate that the proposed detection method outperforms some state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Object detection in embedded systems is important for many contemporary applications that involve vision and scene analysis. In this paper, we propose a novel architecture for object detection implemented in FPGA, based on the Stripe Memory Engine (SME), and point out shortcomings of existing architectures. SME processes a stream of image data so that it stores a narrow stripe of the input image and its scaled versions and uses a detector unit which is efficiently pipelined across multiple image positions within the SME. We show how to process images with up to 4K resolution at high frame rates using cascades of SMEs. As a detector algorithm, the SMEs use boosted soft cascade with simple image features that require only pixel comparisons and look-up tables; therefore, they are well suitable for hardware implemenation. We describe the components of our architecture and compare it to several published works in several configurations. As an example, we implemented face detection and license plate detection applications that work with HD images ($1280\times 720$ pixels) running at over 60 frames/s on Xilinx Zynq platform. We analyzed their power consumption, evaluated the accuracy of our detectors, and compared them to Haar Cascades from OpenCV that are often used by other authors. We show that our detectors offer better accuracy as well as performance at lower power consumption. [ABSTRACT FROM AUTHOR]

Vehicle detection in aerial images is a crucial image processing step for many applications such as screening of large areas as used for surveillance, reconnaissance, or rescue tasks. In recent years, several deep learning-based frameworks have been proposed for object detection. However, these detectors were developed for data sets that considerably differ from aerial images. In this paper, we systematically investigate the potential of fast R-CNN and faster R-CNN for aerial images, which achieve top performing results on common detection benchmark data sets. Therefore, the applicability of eight state-of-the-art object proposal methods used to generate a set of candidate regions and of both detectors is examined. Relevant adaptations to account for the characteristics of the aerial images are provided. To overcome the shortcomings of the original approach in the case of handling small instances, we further propose our own networks that clearly outperform state-of-the-art methods for vehicle detection in aerial images. Furthermore, we analyze the impact of the different adaptations with respect to various ground sampling distances to provide a guideline for detecting small objects in aerial images. All experiments are performed on two publicly available data sets to account for differing characteristics such as varying object sizes, number of objects per image, and varying backgrounds. [ABSTRACT FROM AUTHOR]

In this paper, a novel forensics scheme for color image is proposed in color quaternion wavelet transform (CQWT) domain. Compared with discrete wavelet transform (DWT), contourlet wavelet transform, and local binary patterns, CQWT processes a color image as a unit, and so, it can provide more forensics information to identify the photograph (PG) and computer generated (CG) images by considering the quaternion magnitude and phase measures. Meanwhile, two novel quaternion central moments for color images, i.e., quaternion skewness and kurtosis, are proposed to extract forensics features. In the condition of the same statistical model as Farid’s model, the CQWT can boost the performance of the existing identification models. Compared with Farid’s model and Li’s model in 7500 PG and 7500 CG, the quaternion statistical features show a better classification performance. Results in the comparative experiments show that the classification accuracy of the CQWT improves by 19% more than Farid’s model, and the quaternion features approximately improve by 2% more than the traditional. [ABSTRACT FROM AUTHOR]

Surveying wide areas with only one camera is a typical scenario in surveillance and automotive applications. Ultra wide-angle fisheye cameras employed to that end produce video data with characteristics that differ significantly from conventional rectilinear imagery as obtained by perspective pinhole cameras. Those characteristics are not considered in typical image and video processing algorithms such as motion estimation, where translation is assumed to be the predominant kind of motion. This contribution introduces an adapted technique for use in block-based motion estimation that takes into the account the projection function of fisheye cameras and thus compensates for the non-perspective properties of fisheye videos. By including suitable projections, the translational motion model that would otherwise only hold for perspective material is exploited, leading to improved motion estimation results without altering the source material. In addition, we discuss extensions that allow for a better prediction of the peripheral image areas, where motion estimation falters due to spatial constraints, and further include calibration information to account for lens properties deviating from the theoretical function. Simulations and experiments are conducted on synthetic as well as real-world fisheye video sequences that are part of a data set created in the context of this paper. Average synthetic and real-world gains of 1.45 and 1.51 dB in luminance PSNR are achieved compared against conventional block matching. Furthermore, the proposed fisheye motion estimation method is successfully applied to motion compensated temporal resolution enhancement, where average gains amount to 0.79 and 0.76 dB. [ABSTRACT FROM AUTHOR]

Ill-posed problems are very common in many image processing and computer vision tasks. To solve such problems, a regularization must be imposed. In this paper, we argue why mean curvature is a good regularization for these tasks. From a geometry point of view, we show that minimizing mean curvature is to assume that the ground truth is a piece-wise minimal surface. From a statistics point of view, we show that the mean curvature from natural images is sparse. From an optimization point of view, we show that the gradient of mean curvature regularization can be numerically approximated by very simple filters. This fact significantly simplifies the optimization procedure. Thus, the link between these filters and the gradient of mean curvature regularization is established in this paper. In summary, mean curvature is a proper regularization for various ill-posed problems in image processing and computer vision. [ABSTRACT FROM AUTHOR]

Recently, there has been a significant progress in the research and development of the high dynamic range (HDR) video technology and the state-of-the-art video pipelines are able to offer a higher bit depth support to capture, store, encode, and display HDR video content. In this paper, we introduce a novel HDR video compression algorithm, which uses a perceptually uniform color opponent space, a novel perceptual transfer function to encode the dynamic range of the scene, and a novel error minimization scheme for accurate chroma reproduction. The proposed algorithm was objectively and subjectively evaluated against four state-of-the-art algorithms. The objective evaluation was conducted across a set of 39 HDR video sequences, using the latest x265 10-bit video codec along with several perceptual and structural quality assessment metrics at 11 different quality levels. Furthermore, a rating-based subjective evaluation ($n=40$) was conducted with six sequences at two different output bitrates. Results suggest that the proposed algorithm exhibits the lowest coding error amongst the five algorithms evaluated. Additionally, the rate–distortion characteristics suggest that the proposed algorithm outperforms the existing state-of-the-art at bitrates ≥ 0.4 bits/pixel. [ABSTRACT FROM AUTHOR]

In order to efficiently utilize the information in the data and eliminate the negative effects of outliers in the principal component analysis (PCA) method, in this paper, we propose a novel robust sparse PCA method based on maximum correntropy criterion (MCC) with high-order manifold constraints called the RHSPCA. Compared with the traditional PCA methods, the proposed RHSPCA has the following benefits: 1) the MCC regression term is more robust to outliers than the MSE-based regression term; 2) thanks to the high-order manifold constraints, the low-dimensional representations can preserve the local relations of the data and greatly improve the clustering and classification performance for image processing tasks; and 3) in order to further counteract the adverse effects of outliers, the MCC-based samples’ mean is proposed to better centralize the data. We also propose a new solver based on the half-quadratic technique and accelerated block coordinate update strategy to solve the RHSPCA model. Extensive experimental results show that the proposed method can outperform the state-of-the-art robust PCA methods on a variety of image processing tasks, including reconstruction, clustering, and classification, on outliers contaminated datasets. [ABSTRACT FROM AUTHOR]

Image representation based on sparse coding generalizes the bag of words model. Although it reduces the reconstruction error for local features to achieve the state-of-the-art image classification performance, the large computational cost hinders the application of sparse coding-based image features. In this paper, we propose approximating a sparse code using the output of a simple neural network. The resulting parameter learning model for the neural network automatically incorporates non-negative and shift-invariant constraints, leading to an efficient normalized non-negative sparse coding (N3SC) sparse encoder. Without the use of the traditional iterative process to solve the sparse coding objective, the sparse encoder directly “converts” each local feature into a sparse code. We also introduce a method for training the encoder based on the auto-encoder method. In addition, we formally propose the corresponding sparse coding scheme called N3SC, which enforces both the non-negative constraint and the shift-invariant constraint in addition to the traditional sparse coding criteria. As demonstrated by several experiments, the obtained N3SC encoder requires only 3%–10% of the processing time for image feature extraction compared with the standard sparse coding scheme. At the same time, the features extracted using the exact solutions of the N3SC coding scheme and the N3SC encoder offer superior image classification accuracy compared to the accuracy of many existing sparse coding-based representations. [ABSTRACT FROM AUTHOR]

Guided image filtering has been applied widely in recent years as a solution to the ever-increasing demand of high-performance filtering, especially for real-time image/video processing. The lately proposed gradient domain guided image filter (GDGIF) is one of the typical works focusing on improving the quality of the filtering result of the original guided image filter (GIF), dealing with the halo-artifacts problem for edge-preserving smoothing. However, due to the involvement of global pixel values in the computation, high computation complexity, and additional complex operation, there is no existing VLSI design for the gradient guided filter. This paper presents a high-throughput VLSI architecture for real-time full-HD ($1920\times 1080$) GDGIF. Four techniques are used in the newly proposed design to reduce the computation complexity and increase the processing throughput. First, a pre-processing stage is introduced to address the problem of global parameters required in the GDGIF. Second, multi-scale down-samplings are adopted for reducing circuit size and processing time. Then, a parallel structure operated at a higher frequency is used at the output stage to restore the full image size and to achieve high throughput at the same time. At last, approximated computation is introduced to eliminate speed bottleneck by simplifying the complex exponentiation operation. Based on the STM 65-nm CMOS technology, the implementation results show that the proposed architecture is able to support full-HD image filtering at a throughput above 75 frame/s, with a design area of 586314 $\mu \text{m}^{2}$ and a power consumption of 18.5 mW. [ABSTRACT FROM AUTHOR]

Preserving projection-based methods are good for finding the manifold structure embedded in data. As they use the Euclidean distance as a metric, which is sensitive to noise and outliers in data, nuclear norm-based 2D locality preserving projection (NN-2DLPP) is thus proposed to improve the robustness of 2DLPP. However, NN-2DLPP does not consider the discriminant ability of data. In order to improve the discriminant ability of preserving projection methods, in this paper, we use preserving projection learning with structurally incoherence of data and propose structurally incoherent low-rank 2DLPP (SILR-2DLPP) for image classification. This approach provides a discriminative representation of preserving projection learning by recovering the distinct different classes of the data. SILR-2DLPP searches the optimal subspace and low-rank representation simultaneously. We further extend SILR-2DLPP to a kernel case and propose kernel SILR-2DLPP (KSILR-2DLPP) to obtain a nonlinear representation. The theoretical analysis including the convergence and computational complexity of SILR-2DLPP are presented. To verify the performance of SILR-2DLPP and KSILR-2DLPP, six well-known image databases were used in the experiments. The experimental results show that the proposed methods are superior to the previous preserving projection methods for image classification. [ABSTRACT FROM AUTHOR]

We introduce a novel method to automatically adjust camera exposure for image processing and computer vision applications on mobile robot platforms. Because most image processing algorithms rely heavily on low-level image features that are based mainly on local gradient information, we consider that gradient quantity can determine the proper exposure level, allowing a camera to capture the important image features in a manner robust to illumination conditions. We then extend this concept to a multi-camera system and present a new control algorithm to achieve both brightness consistency between adjacent cameras and a proper exposure level for each camera. We implement our prototype system with off-the-shelf machine-vision cameras and demonstrate the effectiveness of the proposed algorithms on practical applications, including pedestrian detection, visual odometry, surround-view imaging, panoramic imaging, and stereo matching. [ABSTRACT FROM AUTHOR]