Search

In various countries worldwide, the incidence of colon cancer-related deaths has been on the rise in recent years. Early detection of symptoms and identification of intestinal polyps are crucial for improving the cure rate of colon cancer patients. Automated computer-aided diagnosis (CAD) has emerged as a solution to the low efficiency of traditional methods relying on manual diagnosis by physicians. Deep learning is the latest direction of CAD development and has shown promise for colonoscopic polyp segmentation. In this paper, we present a multi-level encoder-decoder architecture for polyp segmentation based on the Transformer architecture, termed NA-SegFormer. To improve the performance of existing Transformer-based segmentation algorithms for edge segmentation on colon polyps, we propose a patch merging module with a neighbor attention mechanism based on overlap patch merging. Since colon tract polyps vary greatly in size and different datasets have different sample sizes, we used a unified focal loss to solve the problem of category imbalance in colon tract polyp data. To assess the effectiveness of our proposed method, we utilized video capsule endoscopy and typical colonoscopy polyp datasets, as well as a dataset containing surgical equipment. On the datasets Kvasir-SEG, Kvasir-Instrument and KvasirCapsule-SEG, the Dice score of our proposed model reached 94.30%, 94.59% and 82.73%, with an accuracy of 98.26%, 99.02% and 81.84% respectively. The proposed method achieved inference speed with an Frame-per-second (FPS) of 125.01. The results demonstrated that our suggested model effectively segmented polyps better than several well-known and latest models. In addition, the proposed method has advantages in trade-off between inference speed and accuracy, and it will be of great significance to real-time colonoscopic polyp segmentation. The code is available at https://github.com/promisedong/NAFormer. [ABSTRACT FROM AUTHOR]

Leukemia is a type of blood tumour that occurs because of abnormal enhancement in WBCs (white blood cells) in the bone marrow of the human body. Blood-forming tissue cancer influences the lymphatic and bone marrow system. The early diagnosis and detection of leukaemia, i.e., the accurate difference of malignant leukocytes with little expense at the beginning of the disease, is a primary challenge in the disease analysis field. Despite the higher occurrence of leukemia, there is a lack of flow cytometry tools, and the procedures accessible at medical diagnostics centres are time-consuming. Distinct researchers have implemented computer-aided diagnostic (CAD) and machine learning (ML) methods for laboratory image analysis, aiming to manage the restrictions of late leukemia analysis. This study proposes a new Falcon optimization algorithm with deep convolutional neural network for Leukemia detection and classification (FOADCNN-LDC) technique. The main objective of the FOADCNN-LDC technique is to classify and recognize leukemia. The FOADCNN-LDC technique utilizes a median filtering (MF) based noise removal process to eradicate the image noise. Besides, the FOADCNN-LDC technique employs the ShuffleNetv2 model for the feature extraction process. Moreover, the detection and classification of the leukemia process are performed by utilizing the convolutional denoising autoencoder (CDAE) model. The FOA is implemented to select the hyperparameter of the CDAE model. The simulation process of the FOADCNN-LDC approach is performed on a benchmark medical dataset. The investigational analysis of the FOADCNN-LDC approach highlighted a superior accuracy value of 99.62% over existing techniques. [ABSTRACT FROM AUTHOR]

In order to improve the accuracy of granular image detection during image scaling, an image scaling algorithm combining the interpolation algorithm of protective features and Kalman filtering of neurons is proposed. Firstly, the interpolation algorithm of protective features is de‐designed according to the phenomenon of sudden change of edge grey values, and the difference and trend of grey values in horizontal and vertical directions are used to obtain the pre‐scaled image with maximum contrast. Then the grey value data input of the pre‐scaled image is introduced into the Kalman filter of neurons, and the filtering process is optimized by using the black‐box thinking of neurons, and the pre‐scaled image is smoothed. Finally, the scale transformation is implemented to obtain the final grey value to complete the final scaling, so that the image has both visual experience and features. Comparison with mainstream image scaling algorithms shows that the proposed algorithm can effectively overcome the degradation of granularity image detection accuracy due to image scaling, with point acutance value (PAV) improved by 10%–41%, and the granularity detection error caused by image scaling algorithms reduced from about 0.7% to about 0.1%, with a relative improvement of 85%. [ABSTRACT FROM AUTHOR]

Head pose estimation is an especially challenging task due to the complexity nonlinear mapping from 2D feature space to 3D pose space. To address the above issue, this paper presents a novel and efficient head pose estimation framework based on particle swarm optimized contrastive learning and multimodal entangled graph convolution network. Firstly, a new network, the region and difference‐aware feature pyramid network (RD‐FPN), is proposed for 2D keypoints detection to alleviate the background interference and enhance the feature expressiveness. Then, particle swarm optimized contrastive learning is constructed to alternatively match 2D and 3D keypoints, which takes the multimodal keypoints matching accuracy as the optimization objective, while considering the similarity of cross‐modal positive and negative sample pairs from contrastive learning as a local contrastive constraint. Finally, multimodal entangled graph convolution network is designed to enhance the ability of establishing geometric relationships between keypoints and head pose angles based on second‐order bilinear attention, in which point‐edge attention is introduced to improve the representation of geometric features between multimodal keypoints. Compared with other methods, the average error of our method is reduced by 8.23%, indicating the accuracy, generalization, and efficiency of our method on the 300W‐LP, AFLW2000, BIWI datasets. [ABSTRACT FROM AUTHOR]

Transformer possesses a broader perceptual scope, while the Convolutional Neural Network (CNN) excels at capturing local information. In this paper, the authors propose the Multi‐Sclale Feature Aggregation Network (MSFA‐Net) for single‐image dehazing which is fused with the advantages of Transformer and CNN. Our MSFA‐Net is based on the encoder–decoder structure, and there are four main innovations. Firstly, the authors make some improvements to the original Swin Transformer to make it more effective for dehazing tasks, and the authors name it Spatial Information Aggregation Transformer (SIAT). The authors place the SIAT in both encoder and decoder of MSFA‐Net for feature extraction. The authors propose an upsampling module called Efficient Spatial Resolution Recovery (ESRR) which is placed in the decoder part. Compared to commonly used transposed convolutions, the authors' ESRR module has fewer computational cost. Considering that the haze distribution is always uneven and the information from each channel is different, the authors introduce the Dynamic Multi‐Attention (DMA) module to provide pixel‐wise weights and channel‐wise weights for input features. The authors place the DMA module between the encoder and decoder parts. As the network depth increases, the spatial structural information from the high‐resolution layer tends to degrade. To deal with the problem, the authors propose the Multi‐Scale Feature Fusion (MSFF) module to recover missing spatial structural information. The authors place the MSFF module in both the encoder and decoder parts. Extensive experimental results show that the authors' proposed dehazing network achieves state‐of‐the‐art dehazing performance with relatively low computational cost. [ABSTRACT FROM AUTHOR]

As generative models become more advanced and essential, interest in using these models for image editing is growing. Nevertheless, conventional image editing methods still have many problems and can alter the intrinsic properties (e.g. geometry) of an object during the editing process. In this article, a novel geometry‐preserved image editing method is presented, where key points, keyframe, or canny edges are utilized as inputs for geometric constraints. A text prompt is fed into the inversion pipeline along with the input image and key points/keyframes/canny for editing. Then, new images are generated based on the editing pipeline of the denoising diffusion implicit model. Experiments demonstrate that the method outperforms its baselines. [ABSTRACT FROM AUTHOR]

Potholes and other road surface damages pose significant risks to vehicles and traffic safety. The current methods of in situ visual inspection for potholes or cracks are inefficient, costly, and hazardous. Therefore, there is a pressing need to develop automated systems for assessing road surface conditions, aiming to efficiently and accurately reconstruct, recognize, and locate potholes. In recent years, various methods utilizing (a) computer vision, (b) three-dimensional (3D) point clouds, or (c) smartphone data have been employed to map road surface quality conditions. Machine learning and deep learning techniques have increasingly enhanced the performance of these methods. This review aims to provide a comprehensive overview of cutting-edge computer vision and machine learning algorithms for pothole detection. It covers topics such as sensing systems for acquiring two-dimensional (2D) and 3D road data, classical algorithms based on 2D image processing, segmentation-based algorithms using 3D point cloud modeling, machine learning, deep learning algorithms, and hybrid approaches. The review highlights that hybrid methods combining traditional image processing and advanced machine learning techniques offer the highest accuracy in pothole detection. Machine learning approaches, particularly deep learning, demonstrate superior adaptability and detection rates, while traditional 2D and 3D methods provide valuable baseline techniques. By reviewing and evaluating existing vision-based methods, this paper clarifies the current landscape of pothole detection technologies and identifies opportunities for future research and development. Additionally, insights provided by this review can inform the design and implementation of more robust and effective systems for automated road surface condition assessment, thereby contributing to enhanced roadway safety and infrastructure management. [ABSTRACT FROM AUTHOR]

In maritime transportation, a ship's draft survey serves as a primary method for weighing bulk cargo. The accuracy of the ship's draft reading determines the fairness of bulk cargo transactions. Human visual-based draft reading methods face issues such as safety concerns, high labor costs, and subjective interpretation. Therefore, some image processing methods are utilized to achieve automatic draft reading. However, due to the limitations in the spectral characteristics of RGB images, existing image processing methods are susceptible to water surface environmental interference, such as reflections. To solve this issue, we obtained and annotated 524 multispectral images of a ship's draft as the research dataset, marking the first application of integrating NIR information and RGB images for automatic draft reading tasks. Additionally, a dual-branch backbone named BIF is proposed to extract and combine spectral information from RGB and NIR images. The backbone network can be combined with the existing segmentation head and detection head to perform waterline segmentation and draft detection. By replacing the original ResNet-50 backbone of YOLOv8, we reached a mAP of 99.2% in the draft detection task. Similarly, combining UPerNet with our dual-branch backbone, the mIoU of the waterline segmentation task was improved from 98.9% to 99.3%. The inaccuracy of the draft reading is less than ±0.01 m, confirming the efficacy of our method for automatic draft reading tasks. [ABSTRACT FROM AUTHOR]

Access to large image volumes through camera traps and crowdsourcing provides novel possibilities for animal monitoring and conservation. It calls for automatic methods for analysis, in particular, when re-identifying individual animals from the images. Most existing re-identification methods rely on either hand-crafted local features or end-to-end learning of fur pattern similarity. The former does not need labeled training data, while the latter, although very data-hungry typically outperforms the former when enough training data is available. We propose a novel re-identification pipeline that combines the strengths of both approaches by utilizing modern learnable local features and feature aggregation. This creates representative pattern feature embeddings that provide high re-identification accuracy while allowing us to apply the method to small datasets by using pre-trained feature descriptors. We report a comprehensive comparison of different modern local features and demonstrate the advantages of the proposed pipeline on two very different species. [ABSTRACT FROM AUTHOR]

Foundation models (FMs) have rapidly evolved and have achieved significant accomplishments in computer vision tasks. Specifically, the prompt mechanism conveniently allows users to integrate image prior information into the model, making it possible to apply models without any training. Therefore, we proposed a workflow based on foundation models and zero training to solve the tasks of photoacoustic (PA) image processing. We employed the Segment Anything Model (SAM) by setting simple prompts and integrating the model’s outputs with prior knowledge of the imaged objects to accomplish various tasks, including: (1) removing the skin signal in three-dimensional PA image rendering; (2) dual speed-of-sound reconstruction, and (3) segmentation of finger blood vessels. Through these demonstrations, we have concluded that FMs can be directly applied in PA imaging without the requirement for network design and training. This potentially allows for a hands-on, convenient approach to achieving efficient and accurate segmentation of PA images. This paper serves as a comprehensive tutorial, facilitating the mastery of the technique through the provision of code and sample datasets. [ABSTRACT FROM AUTHOR]

The salient object detection task tries to simulate the human visual system for most eye‐catching objects or regions detection. However, due to the complexity of the visual mechanisms, current methods will suffer from severe performance degradation, leading to inconsistent prediction results for the same regions, when directly adopting a model trained on a fixed resolution to evaluate at other different resolutions. Considering that consistency in predictions is essential for salient object detection, a cross‐scale resolution consistent salient object detection method, called RCNet, is proposed. Specifically, to enhance the model's capacity for generalization across images of varying resolutions and make the model implicitly learn the scale invariance, a multi‐resolution data enhancement module is constructed to generate images with arbitrary resolutions for the same scene. Moreover, to accomplish better multi‐level feature fusion, a cross‐scale fusion module is developed to fuse high‐level semantic features and low‐level detail features. Additionally, to explicitly learn the scale invariance of the salient scores, a hybrid salient consistency loss is formulated on salient object detection with different resolutions. Comprehensive evaluations on five benchmark datasets show that RCNet achieves a highly competitive result. [ABSTRACT FROM AUTHOR]

Image steganography is the art of concealing secret information within images to prevent detection. In deep‐learning‐based image steganography, a common practice is to fuse the secret image with the cover image to directly generate the stego image. However, not all features are equally critical for data hiding, and some insignificant ones may lead to the appearance of residual artifacts in the stego image. In this article, a novel network architecture for image steganography with hybrid attention mechanism based on generative adversarial network is introduced. This model consists of three subnetworks: a generator for generate stego images, an extractor for extracting the secret images, and a discriminator to simulate the detection process, which aids the generator in producing more realistic stego images. A specific hybrid attention mechanism (HAM) module is designed that effectively fuses information across channel and spatial domains, facilitating adaptive feature refinement within deep image representations. The experimental results suggest that the HAM module not only enhances the image quality during both the steganography and extraction processes but also improves the model's undetectability. Stego images are mixed with varying levels of noise in the training process, which can further improve robustness. Finally, it is verified that the model outperforms current steganography approaches on three datasets and exhibits good undetectability. [ABSTRACT FROM AUTHOR]

Lip‐reading deciphers speech by observing lip movements without relying on audio data. The rapid advancements in deep learning have significantly improved lip‐reading for both English and Chinese; however, research on dialects such as Cantonese remains scarce. Consequently, most Chinese lip‐reading datasets focus on Mandarin, with only a few addressing Cantonese. To bridge this gap, a sentence‐level Cantonese lip‐reading dataset, designated as Cantonese lip‐reading sentences are introduced, comprising over 500 unique speakers and more than 30,000 samples. To ensure alignment with real‐world scenarios, no restrictions are imposed on factors such as gender, age, posture, lighting conditions, or speech rate. A comprehensive description of the pipeline employed is provided for collecting and constructing the dataset and introduce an innovative visual frontend, 3D‐visual attention net. This frontend combines the advantages of convolution and self‐attention mechanisms to extract fine‐grained lip region features. These features are subsequently input into the conformer backend for temporal sequence modelling, achieving comparable performance on Chinese Mandarin lip reading dataset, lip reading sentences 2, lip reading sentences 3, and Cantonese lip‐reading sentences datasets. Benchmark tests on Cantonese lip‐reading sentences demonstrate the challenges it poses, providing a novel research foundation for dialect lip‐reading and fostering the advancement of Cantonese lip‐reading tasks. [ABSTRACT FROM AUTHOR]

Image denoising aims to remove noise from images and improve the quality of images. However, most image denoising methods heavily rely on pairwise training strategies and strict prior knowledge about image structure or noise distribution. While these methods exhibit significant results when handling known types of noise, their generalization performance diminishes when confronted with images containing unknown noise distributions. To address this issue, a two‐stage approach is introduced for enhancing the generalizability of image denoising. The proposed method does not rely on a large amount of paired data or prior knowledge of the noise type and level. Instead, it constructs a denoising pipeline with improved generalizability through an MLP‐based denoiser and generative diffusion prior. Specifically, in the first stage, an initial denoised image is predicted with a structure resembling that of the underlying clean image by introducing an MLP‐based U‐shaped denoising network aided by an implicit structural prior. In the second stage, the generalizability and quality of the denoiser are further enhanced by conditioning the result obtained from the previous stage on the pretrained denoising diffusion null‐space model. Extensive experimentation on multiple datasets demonstrates that this method exhibits better denoising performance and generalizability than other image denoising methods. [ABSTRACT FROM AUTHOR]

Accurate detection of algae in microscopic image plays a crucial role in water quality monitoring. However, the existing object detection methods still face challenges in accurately detecting different categories of algae in microscopic image. In order to improve the accuracy, an improved YOLOv5s model is proposed for microalgae detection, by combining a Receptive Field Enhancement (RFE) module, the Wise‐IoU v3 dynamic non‐monotonic focal loss function, and a Dynamic head (Dyhead), which is termed receptive field enhancement wise‐IoU dyhead (RWD)‐you only look once (YOLO). Firstly, to detect microalgae of various scales, the Bottleneck in the C3 module of YOLOv5s is replaced with a more reasonable RFE module. Secondly, Wise‐IoU v3 is applied to enhance detection accuracy by assigning varying weights between high‐quality and low‐quality images. Finally, Dyhead is introduced to enhance the representation capacity of the detection head by integrating three attention mechanisms: scale awareness, spatial awareness, and task awareness. The proposed RWD‐YOLO model significantly enhances the accuracy of algae detection in microscopic image. Specifically, the experimental results on the microalgae dataset show that the RWD‐YOLO achieves an mAP@0.5 of 93.2% and an mAP@0.5:0.95 of 65.1%. Compared to the original YOLOv5s, mAP@0.5 and mAP@0.5:0.95 are improved by 3.7% and 5.7%, respectively. [ABSTRACT FROM AUTHOR]

Micro‐expressions are spontaneous and unconscious facial movements that reveal individuals' genuine inner emotions. They hold significant potential in various psychological testing fields. As the face is a 3D deformation object, the emergence of facial expression leads to spatial deformation of the face. However, existing databases primarily offer 2D video sequences, limiting descriptions of 3D spatial information related to micro‐expressions. Here, a new micro‐expression database is proposed, which contains 2D image sequences and corresponding 3D point cloud sequences. These samples were classified using both an objective method based on the facial action coding system and a non‐objective emotion classification method that considers video contents and participants' self‐reports. A variety of feature extraction techniques are applied to 2D data, including traditional algorithms and deep learning methods. Additionally, a novel local curvature‐based algorithm is developed to extract 3D spatio‐temporal deformation features from the 3D data. The authors evaluated the classification accuracies of these two features individually and their fusion results under leave‐one‐subject‐out (LOSO) and tenfold cross‐validation. The results demonstrate that fusing 3D features with 2D features results in improved recognition performance compared to using 2D features alone. [ABSTRACT FROM AUTHOR]

Synthetic images facilitate stereo matching. However, synthetic images may suffer from image distortion, domain bias, and stereo mismatch, which would significantly restrict the widespread use of stereo matching models in the real world. The first goal in this paper is to synthesize real‐looking images for minimizing the domain bias between the synthesized and real images. For this purpose, sharpened disparity maps are produced from a mono real image. Then, stereo image pairs are synthesized using these imperfect disparity maps and the single real image in the proposed pipeline. Although the synthesized images are as realistic as possible, the domain styles of the synthesized images are always very different from the real images. Thus, the second goal is to enhance the domain generalization ability of the stereo matching network. For that, the feature extraction layer is replaced with a teacher–student model. Then, a constraint of binocular contrast features is imposed on the output of the model. When tested on the KITTI, ETH3D, and Middlebury datasets, the accuracy of the method outperforms traditional methods by at least 30%. Experiments demonstrate that the approaches are general and can be conveniently embedded into existing stereo networks. [ABSTRACT FROM AUTHOR]

Railway transportation has been integrated into people's lives. According to the "Notice on the release of the General Technical Specification of High-speed Railway Power Supply Safety Testing (6C System) System" issued by the National Railway Administration of China in 2012, it is required to install pantograph and slide monitoring devices in high-speed railway stations, station throats and the inlet and exit lines of high-speed railway sections, and it is required to detect the damage of the slider with high precision. It can be seen that the good condition of the pantograph slider is very important for the normal operation of the railway system. As a part of providing power for high-speed rail and subway, the pantograph must be paid attention to in railway transportation to ensure its integrity. The wear of the pantograph is mainly due to the contact power supply between the slide block and the long wire during high-speed operation, which inevitably produces scratches, resulting in depressions on the upper surface of the pantograph slide block. During long-term use, because the depression is too deep, there is a risk of fracture. Therefore, it is necessary to monitor the slider regularly and replace the slider with serious wear. At present, most of the traditional methods use automation technology or simple computer vision technology for detection, which is inefficient. Therefore, this paper introduces computer vision and deep learning technology into pantograph slide wear detection. Specifically, this paper mainly studies the wear detection of the pantograph slider based on deep learning and the main purpose is to improve the detection accuracy and improve the effect of segmentation. From a methodological perspective, this paper employs a linear array camera to enhance the quality of the data sets. Additionally, it integrates an attention mechanism to improve segmentation performance. Furthermore, this study introduces a novel image stitching method to address issues related to incomplete images, thereby providing a comprehensive solution. [ABSTRACT FROM AUTHOR]

Cracks are a common defect in civil infrastructures, and their occurrence is often closely related to structural loading conditions, material properties, design and construction, and other factors. Therefore, detecting and analyzing cracks in civil infrastructures can effectively determine the extent of damage, which is crucial for safe operation. In this paper, Web of Science (WOS) and Google Scholar were used as literature search tools and "crack", "civil infrastructure", and "computer vision" were selected as search terms. With the keyword "computer vision", 325 relevant documents were found in the study period from 2020 to 2024. A total of 325 documents were searched again and matched with the keywords, and 120 documents were selected for analysis and research. Based on the main research methods of the 120 documents, we classify them into three crack detection methods: fusion of traditional methods and deep learning, multimodal data fusion, and semantic image understanding. We examine the application characteristics of each method in crack detection and discuss its advantages, challenges, and future development trends. [ABSTRACT FROM AUTHOR]

In agriculture, crops are severely affected by illnesses, which reduce their production every year. The detection of plant diseases during their initial stages is critical and thus needs to be addressed. Researchers have been making significant progress in the development of automatic plant disease recognition techniques through the utilization of machine learning (ML), image processing, and deep learning (DL). This study analyses the recent advancements made by researchers in the field of ML techniques for identifying plant diseases. This study also examines various methods used by researchers to produce ML solutions, such as image preprocessing, segmentation, and feature extraction. This study highlights the challenges encountered while creating plant disease identification systems, such as small datasets, image capture conditions, and the generalizability of the models, and discusses possible solutions to cater to these problems. Still, the development of a solution that automatically detects various plant diseases for various plant species remains a big challenge. To address these challenges, there is a need to create a system that is trained on an extensive dataset that contains images of various types of diseases a plant can suffer from, and plant images should be taken at various stages of the disease's development. This study further presents an analysis of various methods used at different stages of plant disease identification. [ABSTRACT FROM AUTHOR]

The industrial manufacturing model is undergoing a transformation from a product-centric model to a customer-centric one. Driven by customized requirements, the complexity of products and the requirements for quality have increased, which pose a challenge to the applicability of traditional machine vision technology. Extensive research demonstrates the effectiveness of AI-based learning and image processing on specific objects or tasks, but few publications focus on the composite task of the integrated product, the traceability and improvability of methods, as well as the extraction and communication of knowledge between different scenarios or tasks. To address this problem, this paper proposes a common, knowledge-driven, generic vision inspection framework, targeted for standardizing product inspection into a process of information decoupling and adaptive metrics. Task-related object perception is planned into a multi-granularity and multi-pattern progressive alignment based on industry knowledge and structured tasks. Inspection is abstracted as a reconfigurable process of multi-sub-pattern space combination mapping and difference metric under appropriate high-level strategies and experiences. Finally, strategies for knowledge improvement and accumulation based on historical data are presented. The experiment demonstrates the process of generating a detection pipeline for complex products and continuously improving it through failure tracing and knowledge improvement. Compared to the ( 1.767 ° , 69.802 mm) and 0.883 obtained by state-of-the-art deep learning methods, the generated pipeline achieves a pose estimation ranging from ( 2.771 ° , 153.584 mm) to ( 1.034 ° , 52.308 mm) and a detection rate ranging from 0.462 to 0.927. Through verification of other imaging methods and industrial tasks, we prove that the key to adaptability lies in the mining of inherent commonalities of knowledge, multi-dimensional accumulation, and reapplication. [ABSTRACT FROM AUTHOR]

A horizontal towed linear coherent hydrophone array is often employed to estimate the spatial intensity distribution of incident plane waves scattered from the geological and biological features in an ocean acoustic waveguide using conventional beamforming. However, due to the physical limitations of the array aperture, the spatial resolution after conventional beamforming is often limited by the fat main lobe and the high sidelobes. Here, we propose a method originated from computer vision deblurring based on deep learning to enhance the spatial resolution of beamformed images. The effect of image blurring after conventional beamforming can be considered a convolution of beam pattern, which acts as a point spread function (PSF), and the original spatial intensity distributions of incident plane waves. A modified U-Net-like network is trained on a simulated dataset. The instantaneous acoustic complex amplitude is assumed following circular complex Gaussian random (CCGR) statistics. Both synthetic data and experimental data collected from the South China Sea Experiment in 2021 are used to illustrate the effectiveness of this approach, showing a maximum 700% reduction in a 3 dB width over conventional beamforming. A lower normalized mean square error (NMSE) is provided compared with other deconvolution-based algorithms, such as the Richardson–Lucy algorithm and the approximate likelihood model-based deconvolution algorithm. The method is applicable in various acoustic imaging applications that employ linear coherent hydrophone arrays with one-dimensional conventional beamforming, such as ocean acoustic waveguide remote sensing (OAWRS). [ABSTRACT FROM AUTHOR]

Direct laser deposition (DLD) requires high-energy input and causes poor stability and portability. To improve the deposited layer quality, conducting online measurements and feedback control of the dimensions, temperature, and other melt-pool parameters during deposition is essential. Currently, melt-pool dimension measurement is mainly based on machine vision methods, which can mostly detect only the deposition direction of a single melt pool, limiting their measurement range and applicability. We propose a binocular-vision-based online measurement method to detect the melt-pool width during DLD. The method uses a perspective transformation algorithm to align multicamera measurements into a single-coordinate system and a fuzzy entropy threshold segmentation algorithm to extract the melt-pool true contour. This effectively captures melt-pool width information in various deposition directions. A DLD measurement system was constructed, establishing an online model that maps the melt-pool width to the offline deposited layer width, validating the accuracy of the binocular vision system in measuring melt-pool width at different deposition angles. The method achieved high accuracy for melt-pool measurements within certain deposition angle ranges. Within the 30°–60° measurement range, the average error is 0.056 mm, with <3% error. The proposed method enhances the detectable range of melt-pool widths, improving cladding layers and parts. [ABSTRACT FROM AUTHOR]

Accurate detection of underwater objects is a key indicator technology to effectively enhance the field of marine development and application, and is of great importance to various fields including marine military defense and seafood aquaculture. Efficient and rapid detection of underwater targets is a crucial technological challenge in this field. To meet the challenges posed by these issues, this study applies the convolutional omni‐efficient layer aggregation network (CO‐ELAN) module to the detector backbone to improve the ability of the network structure to acquire underwater objects from image information. The module improves the feature representation of gradient branching through a multi‐dimensional dynamic convolution and attention mechanism. In terms of loss calculation, the optimized normalized Wasserstein distance approach is used to predict the box distribution probabilistic modelling method to determine comparable distances to the ground box and obtain better samples of small target labels. Here, an underwater image enhancement algorithm based on white balance and underwater blur fusion is used to obtain clear images that enable improved detector performance. After the verification experiment on the URPC2018 dataset, it is found that the detector has better underwater detection ability compared with other detectors in the complex underwater environment. The proposed method achieves a 2.4% improvement over the YOLOv7 baseline model, while reducing computation costs by 5%. [ABSTRACT FROM AUTHOR]

The discrepancy in data distribution between training and testing scenarios, as well as the inductive bias of convolutional neural networks towards image styles, reduces the model's generalization ability. Many unsupervised domain generalization methods based on feature decoupling suffer from an initial neglect of explicit decoupling of content and style features, resulting in content features that still contain considerable redundant information, thereby restricting improvements in generalization capability. To tackle this problem, this paper optimizes the learning process of domain‐invariant (content) features into an information compression issue, minimizing redundancy in content features. Furthermore, to enhance decoupled learning, this paper introduces innovative cross‐domain loss functions and image reconstruction modules that explicitly decouple and merge content and style across different domains. Extensive experiments demonstrate the method's significant enhancements over recent cutting‐edge approaches. [ABSTRACT FROM AUTHOR]

Current research on apron conflict detection is often limited to the interaction between the aircraft as a whole and other objects, making it difficult to accomplish targeted identification of vulnerable and high‐cost aircraft components. However, the implementation of detailed aircraft identification is of great significance to enhance the safety of airport surface operations. Based on the excellent performance of High‐Resolution Network (HRNet) in keypoint detection, a lightweight end‐to‐end keypoint detection network, namely Squeeze and Excitation High‐Resolution Network (SEHRNet), is proposed in this paper to solve the problems of HRNet's slower computation and more redundancy. First, the errors arising from coordinate transformations in the coding and decoding process are solved by an improved feature map coding and decoding process. Second, replace the BasicBlock in HRNet with the Depthwise separable convolutions based on the Squeeze‐and‐Excitation Networks, which drastically cuts the computational cost of the network. Third, the improved Bottleneck module is used to further enhance the capability of feature extraction. Experimental results prove that, based on the aircraft keypoint detection dataset, the SEHRNet proposed in this paper shows stronger applicability compared to the current mainstream networks. Compared with the original HRNet, the improved network has higher accuracy, faster speed, and lighter model for aircraft keypoint detection. [ABSTRACT FROM AUTHOR]

Lesion segmentation is a fundamental task in medical image processing, often facing the challenge of subtle lesions. It is important to detect these lesions, even though they can be difficult to identify. Convolutional neural networks, an effective method in medical image processing, often ignore the relationship between lesions, leading to topological errors during training. To tackle topological errors, move is made from pixel‐level to hypergraph representations. Hypergraphs can model lesions as vertices connected by hyperedges, capturing the topology between lesions. This paper introduces a novel dynamic hypergraph learning strategy called DHLS. DHLS allows for the dynamic construction of hypergraphs contingent upon input vertex variations. A hypergraph global‐aware segmentation network, termed HGSNet, is further proposed. HGSNet can capture the key high‐order structure information, which is able to enhance global topology expression. Additionally, a composite loss function is introduced. The function emphasizes the global aspect and the boundary of segmentation regions. The experimental setup compared HGSNet with other advanced models on medical image datasets from various organs. The results demonstrate that HGSNet outperforms other models and achieves state‐of‐the‐art performance on three public datasets. [ABSTRACT FROM AUTHOR]

Image denoising is a significant procedure in image processing, and a good denoising method can improve the image quality. This study focuses on enhancing the estimation model of wavelet coefficients by improving the threshold function. Thus, a general construction method for a class of threshold functions is introduced, and sufficient conditions are given to ensure that the threshold functions are continuous, first-order differentiable and higher-order differentiable. It makes an existing class of improved threshold functions a particular case and enables the construction of other needed threshold functions based on this general approach. Experiments have shown that using the new threshold functions yields better denoising results for images containing salt and pepper noise, Gaussian noise and speckle noise. Moreover, as the smoothness of the threshold function is enhanced, the denoising effect is also improved. The improved wavelet coefficients estimation model can effectively boost the quality of image denoising, further enhancing the accuracy and effectiveness of computer vision algorithms. [ABSTRACT FROM AUTHOR]

Simple Summary: This research addresses the problem of biomass estimation and fish development monitoring by developing and meticulously validating a computer-vision-interpretable methodology for fish biometrics based on the extraction of statistical features of shape and size through a signature function. This is done by comparing manually extracted features in machine learning predictions against the computer vision (image feature extraction) machine learning predictions. This research shows promising results in statistical accuracy and error metrics, especially the computer vision methodology plus artificial neural networks for biomass prediction. It is concluded that the signature-function-based methodology plus the neural networks regression is competitive for biomass estimation and provides a powerful interpretable tool for species morphology development research. As a result, from a better understanding of fish development and biomass estimation, the aquaculture sector can improve production, wasting less animal food and detecting fish welfare problems through deformity detection, which translates into reduced costs and improved quality of animal meat. Aquaculture requires precise non-invasive methods for biomass estimation. This research validates a novel computer vision methodology that uses a signature function-based feature extraction algorithm combining statistical morphological analysis of the size and shape of fish and machine learning to improve the accuracy of biomass estimation in fishponds and is specifically applied to tilapia (Oreochromis niloticus). These features that are automatically extracted from images are put to the test against previously manually extracted features by comparing the results when applied to three common machine learning methods under two different lighting conditions. The dataset for this analysis encompasses 129 tilapia samples. The results give promising outcomes since the multilayer perceptron model shows robust performance, consistently demonstrating superior accuracy across different features and lighting conditions. The interpretable nature of the model, rooted in the statistical features of the signature function, could provide insights into the morphological and allometric changes at different developmental stages. A comparative analysis against existing literature underscores the competitiveness of the proposed methodology, pointing to advancements in precision, interpretability, and species versatility. This research contributes significantly to the field, accelerating the quest for non-invasive fish biometrics that can be generalized across various aquaculture species in different stages of development. In combination with detection, tracking, and posture recognition, deep learning methodologies such as the one provided in the latest studies could generate a powerful method for real-time fish morphology development, biomass estimation, and welfare monitoring, which are crucial for the effective management of fish farms. [ABSTRACT FROM AUTHOR]

Human pose estimation (HPE) is a technique used in computer vision and artificial intelligence to detect and track human body parts and poses using images or videos. Widely used in augmented reality, animation, fitness applications, and surveillance, HPE methods that employ monocular cameras are highly versatile and applicable to standard videos and CCTV footage. These methods have evolved from two-dimensional (2D) to three-dimensional (3D) pose estimation. However, in real-world environments, current 3D HPE methods trained on laboratory-based motion capture data encounter challenges, such as limited training data, depth ambiguity, left/right switching, and issues with occlusions. In this study, four 3D HPE methods were compared based on their strengths and weaknesses using real-world videos. Joint position correction techniques were proposed to eliminate and correct anomalies such as left/right inversion and false detections of joint positions in daily life motions. Joint angle trajectories were obtained for intuitive and informative human activity recognition using an optimization method based on a 3D humanoid simulator, with the joint position corrected by the proposed technique as the input. The efficacy of the proposed method was verified by applying it to three types of freehand gymnastic exercises and comparing the joint angle trajectories during motion. [ABSTRACT FROM AUTHOR]

Simple Summary: Breast cancer is a significant cause of female cancer-related deaths in the US. Checking how severe the cancer is helps in planning treatment. Modern AI methods are good at grading cancer, but they are not used much in hospitals yet. We developed and utilized ensemble deep learning algorithms for addressing the tasks of classifying (1) breast cancer subtype and (2) breast cancer invasiveness from whole slide image (WSI) histopathology slides. The ensemble models used were based on convolutional neural networks (CNNs) known for extracting distinctive features crucial for accurate classification. In this paper, we provide a comprehensive analysis of these models and the used methodology for breast cancer diagnosis tasks. Cancer diagnosis and classification are pivotal for effective patient management and treatment planning. In this study, a comprehensive approach is presented utilizing ensemble deep learning techniques to analyze breast cancer histopathology images. Our datasets were based on two widely employed datasets from different centers for two different tasks: BACH and BreakHis. Within the BACH dataset, a proposed ensemble strategy was employed, incorporating VGG16 and ResNet50 architectures to achieve precise classification of breast cancer histopathology images. Introducing a novel image patching technique to preprocess a high-resolution image facilitated a focused analysis of localized regions of interest. The annotated BACH dataset encompassed 400 WSIs across four distinct classes: Normal, Benign, In Situ Carcinoma, and Invasive Carcinoma. In addition, the proposed ensemble was used on the BreakHis dataset, utilizing VGG16, ResNet34, and ResNet50 models to classify microscopic images into eight distinct categories (four benign and four malignant). For both datasets, a five-fold cross-validation approach was employed for rigorous training and testing. Preliminary experimental results indicated a patch classification accuracy of 95.31% (for the BACH dataset) and WSI image classification accuracy of 98.43% (BreakHis). This research significantly contributes to ongoing endeavors in harnessing artificial intelligence to advance breast cancer diagnosis, potentially fostering improved patient outcomes and alleviating healthcare burdens. [ABSTRACT FROM AUTHOR]

The aim of this article is to introduce a novel approach to identifying flow regimes and void fractions in microchannel flow boiling, which is based on binary image segmentation using digital image processing and deep learning. The proposed image processing pipeline uses adaptive thresholding, blurring, gamma correction, contour detection, and histogram comparison to separate vapor from liquid areas, while the deep learning method uses a customized version of a convolutional neural network (CNN) called U-net to extract meaningful features from video frames. Both approaches enabled the automatic detection of flow boiling conditions, such as bubbly, slug, and annular flow, as well as automatic void fraction calculation. Especially CNN demonstrated its ability to deliver fast and dependable results, presenting an appealing substitute to manual feature extraction. The U-net-based CNN was able to segment flow boiling images with a Dice score of 99.1% and classify the above flow regimes with an overall classification accuracy of 91%. In addition, the neural network was able to predict resistance sensor readings from image data and assign them to a flow state with a mean squared error (MSE) < 10−6. [ABSTRACT FROM AUTHOR]

In recent years, low‐light image enhancement has become increasingly active. However, in underground mine environments, acquiring high‐quality images is still challenging due to low light, low contrast, and occlusion. To address this problem, this study proposes a low‐light image enhancement method for underground mine based on generative adversarial networks (UM‐GAN), which aims to take full advantage of the ability of GAN to achieve the restoration of details, the reduction of noise, and the improvement of overall image quality. The model proposed in this paper is divided into three main parts. Initially, a generator network adopting an encoder–decoder structure is developed. Subsequently, a novel strategy is introduced to merge information by utilizing inverted greyscale images and low‐light images as inputs. Further image quality enhancement is achieved by incorporating a noise reduction module employing the diffusion model. To ascertain the efficacy of the UM‐GAN method, evaluations are conducted on diverse real‐world and synthetic datasets, juxtaposing the approach against superior methods. Through qualitative and quantitative comparative experiments, the method showcases noteworthy advancements through qualitative and quantitative comparative experiments, substantiating its effectiveness. This research provides new ideas and methods for overcoming image quality problems in underground mine environments and contributes to the development of underground mine image processing. [ABSTRACT FROM AUTHOR]

The demand for less complex and more accurate architectures has always been a priority since the broad usage of computer vision in everyday life, like auto‐drive cars, portable applications, augmented reality systems, medical image analysis etc. There are a lot of methods that have been developed to improve the accuracy and complexity of object detection, like the generations of R‐CNNs and YOLOs. However, these methods are not the most efficient architectures, and there is always room to improve. In this study, the 5th version of YOLO is employed and the improved architecture, Inception‐YOLO, is presented. The model significantly outperforms the SOTA YOLO family. Specifically, the improvements can be summarised as follows: impressive improvement of floating point operations (FLOPs) and number of parameters, as well as improvement in accuracy compared to the models with fewer FLOPs. All our presented approaches, like the optimized inception module, proposed structures for CSP and SPPF, and the improved loss function used in this research, work together to incrementally improve detection results, accuracy, demanded memory, and FLOPs simultaneously. For a glimpse of performance, the Inception‐YOLO‐S model hits 38.7% AP with 5.9M parameters and 11.5 BFLOPs and outperforms YOLOv5‐S with 37.4% AP, 7.2M parameters, and 16.5 BFLOPs. [ABSTRACT FROM AUTHOR]

Perception systems in autonomous vehicles need to accurately detect and classify objects within their surrounding environments. Numerous types of sensors are deployed on these vehicles, and the combination of such multimodal data streams can significantly boost performance. The authors introduce a novel sensor fusion framework using deep convolutional neural networks. The framework employs both camera and LiDAR sensors in a multimodal, multiview configuration. The authors leverage both data types by introducing two new innovative fusion mechanisms: element‐wise multiplication and multimodal factorised bilinear pooling. The methods improve the bird's eye view moderate average precision score by +4.97% and +8.35% on the KITTI dataset when compared to traditional fusion operators like element‐wise addition and feature map concatenation. An in‐depth analysis of key design choices impacting performance, such as data augmentation, multi‐task learning, and convolutional architecture design is offered. The study aims to pave the way for the development of more robust multimodal machine vision systems. The authors conclude the paper with qualitative results, discussing both successful and problematic cases, along with potential ways to mitigate the latter. [ABSTRACT FROM AUTHOR]

In recent years, many methods for image super‐resolution (SR) have relied on pairs of low‐resolution (LR) and high‐resolution (HR) images for training, where the degradation process is predefined by bicubic downsampling. While such approaches perform well in standard benchmark tests, they often fail to accurately replicate the complexity of real‐world image degradation. To address this challenge, researchers have proposed the use of unpaired image training to implicitly model the degradation process. However, there is a significant domain gap between the real‐world LR and the synthetic LR images from HR, which severely degrades the SR performance. A novel unsupervised image‐blind super‐resolution method that exploits degradation feature‐based learning for real‐image super‐resolution reconstruction (RDFL) is proposed. Their approach learns the degradation process from HR to LR using a generative adversarial network (GAN) and constrains the data distribution of the synthetic LR with real degraded images. The authors then encode the degraded features into a Transformer‐based SR network for image super‐resolution reconstruction through degradation representation learning. Extensive experiments on both synthetic and real datasets demonstrate the effectiveness and superiority of the RDFL method, which achieves visually pleasing reconstruction results. [ABSTRACT FROM AUTHOR]

This document is a guest editorial from the journal IET Computer Vision, discussing the topic of advanced image restoration and enhancement. The editorial highlights the challenges faced in this field, such as the complexity of degradation models for real-world low-quality images and the difficulty of acquiring paired data. It also introduces a special issue of the journal that includes five accepted papers, which focus on video reconstruction and image super-resolution. The editorial concludes by providing brief summaries of each accepted paper. The guest editors of the special issue are also mentioned, along with their research interests and affiliations. [Extracted from the article]

Recent advances in deep convolutional neural networks have shown improved performance in face super‐resolution through joint training with other tasks such as face analysis and landmark prediction. However, these methods have certain limitations. One major limitation is the requirement for manual marking information on the dataset for multi‐task joint learning. This additional marking process increases the computational cost of the network model. Additionally, since prior information is often estimated from low‐quality faces, the obtained guidance information tends to be inaccurate. To address these challenges, a novel Decoder Structure Guided CNN‐Transformer Network (DCTNet) is introduced, which utilises the newly proposed Global‐Local Feature Extraction Unit (GLFEU) for effective embedding. Specifically, the proposed GLFEU is composed of an attention branch and a Transformer branch, to simultaneously restore global facial structure and local texture details. Additionally, a Multi‐Stage Feature Fusion Module is incorporated to fuse features from different network stages, further improving the quality of the restored face images. Compared with previous methods, DCTNet improves Peak Signal‐to‐Noise Ratio by 0.23 and 0.19 dB on the CelebA and Helen datasets, respectively. Experimental results demonstrate that the designed DCTNet offers a simple yet powerful solution to recover detailed facial structures from low‐quality images. [ABSTRACT FROM AUTHOR]

In the drum mixing of particulate polymers, segregation may occur. By measuring the mixing status in real time, it is possible to implement corrective measures to prevent separation and improve the efficiency of the process. This study aims to develop and validate a real-time vision system designed to monitor the mixing process of polymeric particles in a rotary drum mixer, employing a novel centroid-based model for determining the mixing index. The proposed centroid-based model is capable of addressing the radial particle segregation issue without the need for extra image-processing procedures like image subdivision or pixel randomization. This innovative approach greatly improves computational efficiency by processing over 68 image frames per second. The new processing method is 2.8 times faster than the gray-level co-occurrence matrix method and 21.6 times faster than the Lacey index approach. This significantly improves real-time monitoring capabilities and enables real-time image processing using only affordable single-board computers and webcams. The proposed vision-based system for monitoring rotary drum mixing has undergone validation via cross-validation using discrete element method simulations, ensuring its accuracy and reliability. [ABSTRACT FROM AUTHOR]

The production of cheese, a beloved culinary delight worldwide, faces challenges in maintaining consistent product quality and operational efficiency. One crucial stage in this process is determining the precise cutting time during curd formation, which significantly impacts the quality of the cheese. Misjudging this timing can lead to the production of inferior products, harming a company's reputation and revenue. Conventional methods often fall short of accurately assessing variations in coagulation conditions due to the inherent potential for human error. To address this issue, we propose an anomaly-detection-based approach. In this approach, we treat the class representing curd formation as the anomaly to be identified. Our proposed solution involves utilizing a one-class, fully convolutional data description network, which we compared against several state-of-the-art methods to detect deviations from the standard coagulation patterns. Encouragingly, our results show F1 scores of up to 0.92, indicating the effectiveness of our approach. [ABSTRACT FROM AUTHOR]

Online detection of action start is a significant and challenging task that requires prompt identification of action start positions and corresponding categories within streaming videos. This task presents challenges due to data imbalance, similarity in boundary content, and real‐time detection requirements. Here, a novel Time‐Attentive Fusion Network is introduced to address the requirements of improved action detection accuracy and operational efficiency. The time‐attentive fusion module is proposed, which consists of long‐term memory attention and the fusion feature learning mechanism, to improve spatial‐temporal feature learning. The temporal memory attention mechanism captures more effective temporal dependencies by employing weighted linear attention. The fusion feature learning mechanism facilitates the incorporation of current moment action information with historical data, thus enhancing the representation. The proposed method exhibits linear complexity and parallelism, enabling rapid training and inference speed. This method is evaluated on two challenging datasets: THUMOS'14 and ActivityNet v1.3. The experimental results demonstrate that the proposed method significantly outperforms existing state‐of‐the‐art methods in terms of both detection accuracy and inference speed. [ABSTRACT FROM AUTHOR]

To address the challenges of detecting a large number of objects and a high proportion of small objects in aerial drone imagery, an aerial dense small object detection algorithm called coordinate position attention module you only look once (CPAM‐YOLO) is proposed based on the coordinate position attention module (CPAM). In the backbone network of CPAM‐YOLO, a CPAM is proposed and embedded that decomposes channel attention into two 1D feature encoding processes, and selectively combines the features of each position through the weighted sum of all position features. Finally, features are aggregated along two spatial directions, increasing the effective information utilization of input feature positions and channels. The backbone network, feature enhancement network, and detection heads have been optimized to improve detection accuracy while ensuring a lightweight detection network. Using lightweight backbone networks to significantly reduce the number of parameters while using high‐resolution feature enhancement networks to retain more semantic and detailed features. The algorithm's performance was evaluated using the publicly available VisDrone2019 dataset. Compared to the baseline network YOLOv5l, CPAM‐YOLO achieved a 4.5% improvement in mAP0.5 and a 3.2% improvement in mAP0.95. These experimental results demonstrate the strong practicality of the CPAM‐YOLO object detection network for detecting dense small objects in aerial image. [ABSTRACT FROM AUTHOR]

In order to balance accuracy and real‐time performance in semantic segmentation, this paper proposes a real‐time semantic segmentation algorithm model based on attention mechanism and multi‐branch feature fusion using Fast convolutional neural network model (Fast‐SCNN). In this method, the spatial detail feature enhancement branch is introduced to enhance spatial detail features firstly. Then, through rational design of fusion module, the feature information of each branch is optimized to achieve better fusion of deep and shallow features. At the end of the feature fusion module, an adaptive feature enhancement focus module is introduced to capture the interdependence between remote pixels. The experimental results show that the proposed algorithm achieves 71.55% segmentation accuracy on Cityscapes dataset, the reasoning speed FPS is 97.6 frames/s, and the number of parameters is 1.39 M, which verifies the effectiveness of the network model constructed by the algorithm. Code is available at https://github.com/ccchhheeennn/model. [ABSTRACT FROM AUTHOR]

The No‐Reference Image Quality Assessment (NR‐IQA) method can predict quality scores of distorted images without the reference image. However, due to the variability in both color and structure of images, existing NR‐IQA methods struggle to accurately predict quality scores of distorted images. Therefore, an NR‐IQA method based on a Dual‐Branch Residual Network (DBRIQA) for evaluating the quality scores of color‐distorted images is proposed. First, guided filtering is applied to the hue images in the HSV space to extract distortion information from the image's color. Then, due to significant differences in distorted images, enhancements are made to the traditional residual blocks, forming a feature extraction module that captures multi‐scale features from the image. In order to capture the global relationships in the distorted image, a Global‐Level Attention Block (GLAB) is introduced, facilitating the interaction of information among the extracted features. Experiments were conducted across four publicly available IQA datasets, including LIVE, CSIQ, TID2008, and TID2013. The experimental results demonstrate that the proposed method exhibits strong performance and generalization capabilities in predicting image quality compared to peer methods. [ABSTRACT FROM AUTHOR]

The synthesis of rain fields is essential in multiple research fields and applications, including Single‐image Derain. However, there is a lack of research on simulated rain fields, and the existing rain field generation models struggle to capture complex spatial distributions and generate truly random rain fields. To address this, the authors propose a generative adversarial networks‐based rain field generation network, which consists of a generator, a discriminator, and a feature extraction block that can produce realistic and complex rain fields. The authors' experiments demonstrate that this method achieves an average Frechet Inception Distance score of 0.035, and user studies indicate that the generated rain distribution looks naturally. [ABSTRACT FROM AUTHOR]

Existing segmentation‐based methods have made considerable progress in arbitrarily shaped text detection due to the advantage of dealing with shape variation. However, there still exist challenges to detecting accurate text instances with dense layouts, inaccurate annotations, and complex backgrounds. Many recent works have focused on improving arbitrary boundary prediction, but it may be difficult to accurately distinguish each instance of dense layouts because their boundary pixels may be mistakenly classified to produce inaccurate results (i.e., adhesive texts) with inaccurate annotation and complex backgrounds. Considering the local and long‐range dependencies, this paper proposes an efficient text detector, namely T‐Skeleton, to obtain more reliable segmentation detections. In the spirit of object skeletonization, we introduce the text instance skeleton highlighting the semantically significant structure (similar to the skeleton of a fish) to explicitly capture the long‐range dependencies of text instances. The key idea of T‐Skeleton is to calibrate the coarse text proposals by embedding text instance skeletons to separate crowd texts accurately and robustly. We further design a channel attention module to enlarge the performance margin between T‐Skeleton and the segmentation baseline. Experimental results on four publicly available datasets show the superiority of T‐Skeleton in handling long and curved texts. [ABSTRACT FROM AUTHOR]

Identifying saliency in high dynamic range (HDR) images is a fundamentally important issue in HDR imaging, and plays critical roles towards comprehensive scene understanding. Most of existing studies leverage hand‐crafted features for HDR image saliency prediction, lacking the capabilities of fully exploiting the characteristics of HDR image (i.e. wider luminance range and richer colour gamut). Here, systematical studies are carried out on HDR image saliency prediction by proposing a new framework to single out the contributions from multi‐exposure images. Specifically, inspired by the mechanism of HDR imaging, the method first utilizes graph neural networks to model the relations among multi‐exposure images and the tone‐mapped image obtained from an HDR image, enabling more discriminative saliency‐related feature representations. Subsequently, the saliency features driven by global semantic knowledge are aggregated from the tone‐mapped image through enhancing global context‐aware semantic information. Finally, a fusion module is designed to integrate saliency‐oriented feature representations originated from multi‐exposure images and the tone‐mapped image, producing the saliency maps of HDR images. Moreover, a new challenging HDR eye fixation database (HDR‐EYEFix) is created, expecting to further contribute the research on HDR image saliency prediction. Experiment results show that the method obtains superior performance compared to the state‐of‐the‐art methods. [ABSTRACT FROM AUTHOR]

Feature matching plays a crucial role in computer vision, with applications in visual localization, simultaneous localization and mapping (SLAM), image stitching, and more. It establishes correspondences between sets of feature points from multiple images, enabling various tasks. Over the years, feature matching has witnessed significant development, with an increasing number of methods being applied. However, different methods exhibit different degrees of applicability in different scenarios and requirements due to their different rationales. To cope with these issues, a comprehensive analysis and comparison of matching methods are essential. Existing reviews often lack coverage of deep learning models and focus more on feature detection and description, neglecting the matching process. This survey investigates feature detection, description, and matching techniques within the feature‐based image‐matching pipeline. Representative methods, their mechanisms, and application scenarios are also briefly introduced. In addition, comprehensive evaluations of classical and state‐of‐the‐art methods are conducted through extensive experiments on representative datasets. Particularly, matching‐based applications are compared to fully demonstrate the advantages of the methods. Lastly, this survey highlights current problems and development directions in matching methods, serving as a reference for researchers in the field. [ABSTRACT FROM AUTHOR]

Simple Summary: In the sorting process of Chinese softshell turtles, it is necessary to classify them based on their weight and accurately identify their plastron and carapace. This process requires heavy manual labor and complex mechanical processing methods. To improve processing efficiency and reduce costs, this article introduces machine vision technology, and a new image processing method is proposed. This method can estimate the weight of Chinese softshell turtles and accurately locate the positions of their plastron and carapace. The automation level of aquaculture can be greatly enhanced, and hardware costs can be reduced through software optimization through this approach. With the rapid development of the turtle breeding industry in China, the demand for automated turtle sorting is increasing. The automatic sorting of Chinese softshell turtles mainly consists of three parts: visual recognition, weight prediction, and individual sorting. This paper focuses on two aspects, i.e., visual recognition and weight prediction, and a novel method for the object detection and weight prediction of Chinese softshell turtles is proposed. In the individual sorting process, computer vision technology is used to estimate the weight of Chinese softshell turtles and classify them by weight. For the visual recognition of the body parts of Chinese softshell turtles, a color space model is proposed in this paper to separate the turtles from the background effectively. By applying multiple linear regression analysis for modeling, the relationship between the weight and morphological parameters of Chinese softshell turtles is obtained, which can be used to estimate the weight of turtles well. An improved deep learning object detection network is used to extract the features of the plastron and carapace of the Chinese softshell turtles, achieving excellent detection results. The mAP of the improved network reached 96.23%, which can meet the requirements for the accurate identification of the body parts of Chinese softshell turtles. [ABSTRACT FROM AUTHOR]

The Polar Qualification System (PQS) was applied on hue spectra fingerprinting to describe color changes in tomato during storage. The cultivar 'Pitenza' was harvested at six different maturity stages, and half of the samples were subjected to gaseous 1-methylcyclopropene (1-MCP) treatment. Reference color parameters were recorded with a vision system colorimeter instrument, and the fruit pigment concentration was assessed with the DA-index®. Additionally, acoustic firmness (Stiffness) was measured. All acquired reference parameters were used to grade fruit in the supply chain. The applied 1-MCP treatments were used to control the ripening of climacteric horticultural produce. Both the DA-index® and stiffness values, presented as chlorophyll concentration and acoustic firmness, showed significant differences among maturity stages and treated and control samples and in their kinetics during storage. The machine vision parameter PQS-X was significantly affected by 1-MCP treatment (F = 10.18, p < 0.01), while PQS-Y was primarily affected by storage time (F = 18.18, p < 0.01) and maturity stage (F = 11.15, p < 0.01). A significant correlation was achieved for acoustic firmness with normalized color (r > 0.78) and PQS-Y (r > 0.80), as well as for the DA-index® (r > 0.9). The observed color changes agreed with the reference measurements. The significant statistical effect on the PQS coordinates suggests that hue spectra fingerprinting with this data compression technique is suitable for quality assessment based on color. [ABSTRACT FROM AUTHOR]