Search

Recent years have witnessed notable advancements in medical image segmentation through deep convolutional neural networks. However, a notable limitation lies in the local operation of convolution, which hinders the ability to fully exploit global semantic information. To overcome the challenges prevalent in medical image segmentation, the feature ensemble network with multi‐scale atrous transformer is proposed. At the core of the approach lies the multi‐scale contextual integration module, which is based on the multi‐scale atrous transformer and facilitates contextual integration of multi‐level features. To extract discriminative fine‐grained features of the target region, a hybrid attention mechanism that synergistically combines spatial and channel attention, thereby sharpening the model's focus on crucial target information within high‐level features, is incorporated. Additionally, the channel‐aware feature reconstruction module is introduced as an innovative component engineered to tackle feature similarity issues across different categories. This module performs feature reconstruction based on channel perception, effectively widening the feature gap between categories and enhancing the segmentation capability. It is worth mentioning that our approach surpasses the state‐of‐the‐art method using three benchmark datasets in medical image segmentation. [ABSTRACT FROM AUTHOR]

Image processing often requires filtering, which can be effectively performed by using B‐spline surface approximation. This article presents a fast method of approximating data in rectangular (image) form using such surfaces. The method considers dynamic changes of data by representing rows and columns in chordal parameterized form. To improve performance, after parametrization, lines are uniformly resampled using linear interpolation. It allows using the same basis functions with uniform parameterization for approximation of all processed lines. After approximation, reconstruction of original parameterization is required, but its computational complexity is also linear. [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]

Traditional dehazing algorithms have long been limited in their ability to remove fog effectively, especially in preserving details. This study proposes an improved dark channel prior dehazing algorithm designed to overcome the limitations of traditional algorithms by refining the transmission map and estimating atmospheric light intensity. The algorithm fully exploits the anti‐haze characteristics of the Gabor filter to extract multi‐directional texture features. By fusing these features to form a guidance map for guided filtering, it effectively reduces the blurring caused by guided filtering on the image edges, thereby producing a more accurate transmission map. Simultaneously, an enhanced atmospheric light successfully reduces interference from white objects in the image. The experiment phase utilized the publicly available RESIDE dataset for validation. The algorithm achieved a Peak Signal‐to‐Noise Ratio (PSNR) of 22.4 and a Structural Similarity Index (SSIM) of 0.88. These metrics indicate the algorithm's superior dehazing capabilities. [ABSTRACT FROM AUTHOR]

Automatic segmentation of renal tumours during renal cell carcinoma surgery can help doctors accurately locate the tumour region, protect the tissues and organs around the kidneys, enhance surgical efficiency, and reduce the possibility of leakage and misdiagnosis. However, since general polyp endoscopic image segmentation models have many problems when facing the task of renal tumour segmentation, there needs to be more research on the segmentation of endoscopic images of renal tumours. This paper proposes a multi‐scale dynamic segmentation kernel network for endoscopic image segmentation of kidney tumours. First, a spatial receptive field module is proposed to augment the feature information and improve the performance of the whole network. Second, an enhanced cross‐attention module is offered to attenuate the effect of a high‐similarity segmentation background. Finally, a multi‐scale dynamic segmentation kernel module is introduced to gradually refine the segmentation results from small to large sizes to obtain more accurate tumour boundaries. Extensive experiments on the established kidney tumour endoscopic dataset and publicly available endoscopic datasets show that this method exhibits enhanced performance and generalization capabilities compared to existing techniques. On this renal tumour dataset, MDSK‐Net achieved excellent results of 94.1% and 90.1% on mDice and mIoU. [ABSTRACT FROM AUTHOR]

Metaheuristic is one of the techniques to improve the security of image encryption. However, existing metaheuristic image cryptosystems based on metaheuristic may have convergence difficulties during the optimization process, which cause insecurity and slow convergence. Besides, the time cost of the parallel execution model applied to metaheuristic image cryptosystems is not low enough. Therefore, a parallel many‐objective optimized key generation framework is proposed. Firstly, if four or more security indicators of cryptosystem, which are the results of security test, need to be optimized, the many‐objective optimization algorithm is employed to the proposed framework. With method adjusts the chaotic system parameters as the optimization key, which effectively avoid the convergence difficulty of the encryption key. Secondly, a master‐slave parallel model is improved to metaheuristic encryption. The model allocates the most time‐consuming fitness calculation work to slave nodes, which makes the modified model more reasonable and thus reduces the encryption time. To evaluate the performance of the proposed framework, a specific encryption scheme is constructed, that utilizes a 2D quadric map and many‐objective optimization algorithm based on dominance and decomposition (MOEA/DD) to optimize five security indicators. Experimental results reveal that this scheme has good security performances and less parallel encryption time. [ABSTRACT FROM AUTHOR]

This research investigates the Circle of Willis, a critical vascular structure vital for cerebral blood supply. A modified novel dual‐pathway multi‐scale hierarchical upsampling network (HUNet) is presented, tailored explicitly for accurate segmentation of Circle of Willis anatomical components from medical imaging data. Evaluating both the multi‐label magnetic resonance angiography region of interest and the multi‐label magnetic resonance angiography whole brain‐case datasets, HUNet consistently outperforms the convolutional U‐net model, demonstrating superior capabilities and achieving higher accuracy across various classes. Additionally, the HUNet model achieves an exceptional dice similarity coefficient of 98.61 and 97.95, along with intersection over union scores of 73.32 and 85.76 in both the multi‐label magnetic resonance angiography region of interest and the multi‐label magnetic resonance angiography whole brain‐case datasets, respectively. These metrics highlight HUNet's exceptional performance in achieving precise and accurate segmentation of anatomical structures within the Circle of Willis, underscoring its robustness in medical image segmentation tasks. Visual representations substantiate HUNet's efficacy in delineating Circle of Willis structures, offering comprehensive insights into its superior performance. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) image change detection suffers from poor quality of the difference image and low detection accuracy. Hence, this paper proposes a SAR image change detection method based on a fused difference image and an optimized random forest scheme, termed LRN‐SSARF. Specifically, a fusion operator difference image LRN is proposed, which is generated using a weighted fusion of log‐ratio (LR), ratio (R), and normalized ratio (NoR). This difference image generation method reduces noise's influence. Then, the Otsu algorithm is applied to segment the difference image and select the training samples. The training samples are input into the random forest (RF) model optimised by the sparrow search algorithm (SSA) for training and classification. Finally, the region link is uesd to refine the detection results and generate the final result. The change detection results of six real SAR image scenes highlight that the proposed algorithm has a high detection accuracy, and affords appealing integrity and detailed information about the change regions. Specially, the detection accuracy advantage of the Bangladesh dataset is larger, with the accuracy and Kappa coefficient reaching 98.04% and 92.00%, much higher than the competitor methods. [ABSTRACT FROM AUTHOR]

Image hiding is a task that hides secret images into cover images. The purposes of image hiding are to ensure the secret images are invisible to the human and the secret images can be recovered. The current state‐of‐the‐art steganography methods run the risk of secret information leakage. A safe image hiding network (SIHNet) is presented to reduce the leakage of secret information. Based on some phenomena of image hiding methods which use invertible neural network, a reversible secret image processing (SIP) module is proposed to make the secret images suitable for hiding and make the stego images leak less secret information. Besides, a reversible lost information hiding (LIH) module is used to hide the lost information into the cover images, thus the method can recover the secret images better than the method that uses random noise to replace the lost information. Experimental results show that SIHNet outperforms other state‐of‐the‐art methods on the PSNR and SSIM values of the recovered secret images and the stego images. Besides, residual images of other state‐of‐the‐art methods all contain information about secret images while residual images of SIHNet leak almost no secret information. Thus the method can prevent the listener of transmission channel from obtaining the information of the secret image through the residual image, which means SIHNet performs better in security than other state‐of‐the‐art methods. [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]

Fires not only cause devastating consequences for human life and property, but also lead to soil erosion in forests. Therefore, it is necessary to design a novel algorithm that can quickly monitor smoke from fires. Most existing smoke segmentation methods do not consider the segmentation accuracy of algorithms under limited computational resources. To address this research gap, this paper proposes a lightweight smoke segmentation algorithm based on DeepLabV3+ that achieves fast inference speed and high accuracy for different sizes smoke. To reduce the number of parameters, the feature extraction network of the DeeplabV3+ algorithm is replaced by MobileNetV2, which enhances the extraction ability of the algorithm in segment smoke images. Then, the Convolutional Block Attention Module (CBAM) is added to the encoder part to enhance the perception of the algorithm for small smoke and effectively alleviates smoke mis‐segmentation. Furthermore, a newly designed loss function is used in the network. The experimental results show that the proposed method has improved by 1.27% in Smoke IoU and 1.21% in mPA compared with other methods. The weight size has been reduced to 10.76% of the original DeepLabV3+, and the inference time is only 33.71ms. Therefore, it is a more suitable early fire detection algorithm for resource‐constrained environments. [ABSTRACT FROM AUTHOR]

Doctors typically use non‐contrast‐enhanced computed tomography (NCECT) in the treatment of kidney cancer to map kidney and tumour structural information to functional imaging single‐photon emission computed tomography, which is then used to assess patient kidney function and predict postoperative recovery. However, the assessment of kidney function and formulation of surgical plans is constrained by the low contrast of tumours in NCECT, which hinders the acquisition of accurate tumour boundaries. Therefore, this study designed a radiomics feature‐enhanced level‐set evolution (RFLSE) to precisely segment small‐sample low‐contrast kidney tumours. Integration of high‐dimensional radiomics features into the level‐set energy function enhances the edge detection capability of low‐contrast kidney tumours. The use of sensitive radiomics features to control the regional term parameters achieves adaptive adjustment of the curve evolution amplitude, improving the level‐set segmentation process. The experimental data used low‐contrast, limited‐sample tumours provided by hospitals, as well as the public datasets BUSI18 and KiTS19. Comparative results with advanced energy functionals and deep learning models demonstrate the precision and robustness of RFLSE segmentation. Additionally, the application value of RFLSE in assisting doctors with accurately marking tumours and generating high‐quality pseudo‐labels for deep learning datasets is demonstrated. [ABSTRACT FROM AUTHOR]

Medical image colouring techniques enable to colourize grey‐scale medical images for assisting doctors in diagnosis. Benefiting from the non‐linear fitting ability of deep neural network, deep medical image colouring techniques have achieved remarkable results. However, existing methods are still facing content and structure feature leakage, unrealistic colouring and poor scale invariability. Thus, this paper, proposes a Transformer‐based medical image colouring algorithm with long‐term dependency to avoid feature leakage of coloured images. To be specific, this method employs two different Transformer encoders to generate and encode feature sequences for grey‐scale medical images and real human colour slice images, respectively. Then, a novel multi‐layer Transformer decoder is used to stylize grey‐scale map image features based on the real physical colour feature sequences. For colouring images at different scales, we implement content‐ aware positional encoding with scale invariance and propose style‐aware positional encoding strategy to take realistic and physical colour prior into account. Extensive experimental results indicate our method has achieved better colourization effects than recent state‐of‐the‐art medical image colourization methods. [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]

Due to differences in the quantity and size of observed targets, hyperspectral images are characterized by class imbalance. The standard deep learning classification model training scheme optimizes the overall classification error, which may lead to performance imbalance between classes in hyperspectral image classification frameworks. Therefore, a novel factor annealing decoupling compositional training method is proposed in this paper. Without requiring resampling or reweighting, it implicitly modulates the training process, so standard models can sufficiently learn the representation of the minority classes and further be trained as robust classifiers. Specifically, the label‐distribution‐aware margin loss is combined with the error‐rate‐based cross‐entropy loss via combination factor, which considers both imbalanced data representation learning and classifier overall performance. Then, a factor annealing optimization training scheme is designed to adjust the combination factor, which solves the stage division problem of two‐stage decoupling learning. Experimental results on two hyperspectral image datasets demonstrate that, as compared with other competing approaches, the proposed method can continuously and stably optimize the model parameters, achieving improvements in class average metrics and difficult classes without affecting overall classification performance. [ABSTRACT FROM AUTHOR]

Optic disc (OD) and optic cup (OC) segmentation is an important task in ophthalmic medicine and is crucial for aiding glaucoma screening. With the development of smart healthcare and the increase of large datasets, there is an increasing number of research efforts targeting OD and OC segmentation, making it particularly important to provide a systematic review of the latest advances in the field. This paper presents a systematic review of commonly used datasets, evaluation metrics, and related research results in the field of OD and OC segmentation. The advantages and disadvantages of segmentation techniques based on traditional and deep learning methods are comparatively analysed. In addition, this study emphasizes the importance of OD and OC segmentation efforts in smart healthcare. Despite the technological advances, the lack of generalization capability is still a major obstacle limiting its clinical application. To address this issue, this study explores unsupervised domain adaptation methods to enhance the generalization performance of segmentation techniques and provide new strategies for clinical diagnosis. Finally, this paper discusses the challenges and future research directions faced by OD and OC segmentation when applied in the medical field to help readers comprehensively grasp the research dynamics in this area. [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]

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]

Currently, deep learning methods for low‐light image enhancement tasks mainly focus on the illumination of images, while neglecting the problems of image noise and feature loss. To address this issue, this paper proposes a novel low‐light image enhancement network called DAF‐Retinex, based on the Retinex‐Net. To address the issue of image noise, different from traditional image denoise methods, this paper utilizes a fully convolutional neural network to denoise the reflection component, additionally, a denoising loss function is introduced to suppress noise. For preserving image details and extracting features, this paper creatively introduces self‐calibrated convolutions into low‐light image enhancement tasks, furthermore, a feature augmented attention block consisting of feature‐guided attention (FGA) is designed for feature learning to effectively enhance image illumination and extract image detail features. Experimental results demonstrate that the proposed algorithm in this paper effectively removes image noise and extracts detailed features, resulting in visually improved outcomes. On public datasets, the average improvement in objective evaluation metrics of image quality such as PSNR, SSIM, and NIQE are 1.13%, 4.12%, and 1.28%, respectively. [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]

Segmentation is crucial in diagnosing retinal diseases by accurately identifiying retinal vessels. This paper addresses the complexity of segmenting retinal vessels, highlighting the need for precise analysis of blood vessel structures. Despite the progress made by convolutional neural networsks (CNNs) in image segmentation, their limitations in capturing the global structure of retinal vsessels and maintaining segmentation continuity present challenges. To tackle these issues, our proposed network integrates graph convolutional networks (GCNs) and attention mechansims. This allows the model to consider pixel relationships and learn vessel graphical structures, significantly improving segmentation accuracy. Additionally, the attentional feature fusion module, including pixel‐wise and channel‐wise attention mechansims within the U‐Net architecture, refines the model's focus on relevant features. This paper emphasizes the importance of continuty preservation, ensuring an accurate representation of pixel‐level information and structural details during sefmentation. Therefore, our method performs as an effective solution to overcome challenges in retinal vessel segmentation. The proposed method outperformed the state‐of‐the‐art approaches on DRIVE (Digital Retinal Images for Vessel Extraction) and STARE (Structed Analysis of the Retina) datasets with accuracies of 0.12% and 0.14%, respecttively. Importantly, our proposed approach excelled in delineating slender and diminutive blood vessels, crucial for diagnosing vascular‐related diseases. Implementation is accessible on https://github.com/CVLab‐SHUT/VGA‐Net. [ABSTRACT FROM AUTHOR]

The surface quality of steel strip is a critical indicator of the quality of hot‐rolled strip, so accurate inspection of its surface is essential. However, the complex texture of steel strip surface defects makes the detection challenging. Here, a multi‐scale feature fusion and attention based YOLOv5 (MFFA‐YOLOv5) model is proposed. Specifically, the bottom layer features are up‐sampled and fused not only with the middle layer features, but also with the top layer features, so that the model better captures the surface texture information of the steel strip. Secondly, an improved attention mechanism module is introduced to deal with the global and local information of the steel strip surface by introducing down‐sampling and up‐sampling paths based on Convolutional Block Attention Module (CBAM). Meanwhile, a self‐attention mechanism path is added to improve the capability of feature representation. Experimental results on the NEU‐DET dataset show that the MFFA‐YOLOv5 model significantly outperforms other state‐of‐the‐art methods. [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]

In the realm of video salient object detection (VSOD), the majority of research has traditionally been centered on third‐person perspective videos. However, this focus overlooks the unique requirements of certain first‐person tasks, such as autonomous driving or robot vision. To bridge this gap, a novel dataset and a camera‐based VSOD model, CaMSD, specifically designed for egocentric videos, is introduced. First, the SalEgo dataset, comprising 17,400 fully annotated frames for video salient object detection, is presented. Second, a computational model that incorporates a camera movement module is proposed, designed to emulate the patterns observed when humans view videos. Additionally, to achieve precise segmentation of a single salient object during switches between salient objects, as opposed to simultaneously segmenting two objects, a saliency enhancement module based on the Squeeze and Excitation Block is incorporated. Experimental results show that the approach outperforms other state‐of‐the‐art methods in egocentric video salient object detection tasks. Dataset and codes can be found at https://github.com/hzhang1999/SalEgo. [ABSTRACT FROM AUTHOR]

Slug flow processes draw much attention in chemical and pharmaceutical manufacturing thanks to their ability to eliminate downtime costs and batch‐to‐batch variation. Using in‐line video can monitor the current process status and improve the stability of the slug flow. However, there are no effective image processing methods aiming at such videos from chemical experiments due to limited training sample size and the variety of experimental settings. The paper proposes a training‐free method to automatically detect and measure the slugs from in‐line videos. Multiple image features are fused to identify the slug shapes under various lighting conditions, a six‐point model is fitted to achieve better volume estimation, and a consistency score is estimated to quantify the detection uncertainty. The proposed algorithm achieves similar results to manual labeling for various types of slug flow processes, improving the accuracy of slug column estimation by a large margin compared to the existing automatic methods. Finally, using it to monitor the slug flow process's stability and the change of the slug volume in an injection point are demonstrated. The method not only shows that handcrafted image features have the capability for detection and segmentation from chemical experiment images but also paves the road for a training‐based algorithm for the task. [ABSTRACT FROM AUTHOR]

Low‐light image enhancement is a longstanding challenge in low‐level vision, as images captured in low‐light conditions often suffer from significant aesthetic quality flaws. Recent methods based on deep neural networks have made impressive progress in this area. In contrast to mainstream convolutional neural network (CNN)‐based methods, an effective solution inspired by the transformer, which has shown impressive performance in various tasks, is proposed. This solution is centred around two key components. The first is an image synthesis pipeline, and the second is a powerful transformer‐based pre‐trained model, known as the low‐light image enhancement transformer (LIET). The image synthesis pipeline includes illumination simulation and realistic noise simulation, enabling the generation of more life‐like low‐light images to overcome the issue of data scarcity. LIET combines streamlined CNN‐based encoder‐decoders with a transformer body, efficiently extracting global and local contextual features at a relatively low computational cost. The extensive experiments show that this approach is highly competitive with current state‐of‐the‐art methods. The codes have been released and are available at LIET. [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]

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]

An adaptively hybrid method was proposed to improve the performance of fractal coding methods. First, it is found that the range blocks with large variances (RBLVs) play a crucial role in degrading decoded images, and the effect of the remaining range blocks with small variances (RBSVs) can be ignored. Then, an adaptive method was proposed to divide the range blocks into the above two categories: RBLVs and RBSVs. Second, RBLVs were designed to be encoded in an extended domain block pool (EDBP). Then, better block‐matching effect can be obtained, which will result in better decoded image quality. Further, the no‐search fractal encoding method is adopted for RBSVs to achieve faster encoding speed and fewer bits per pixel (bpp). Finally, four fractal coding methods were adopted to assess the performance of the proposed method. Experimental results show that compared with the previous methods, the PSNR quality of decoded images in the proposed method can be improved by about 0.15–0.4 dB, about 20%–35% of the total computations in encoding process can be saved, and about 0.2 bpp can be saved. Moreover, under the same decoding time, the proposed method can achieve comparable or smaller deviations regarding the decoded 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]

Infrared object detection and tracking in dense urban traffic remain a challenge due to factors such as low contrast, small intra‐class differences, and frequent false positives and negatives. To overcome these, the authors introduce YOLO‐IR, an algorithm based on the enhanced YOLOv8s, and YOLO‐DeepOC‐IR, a comprehensive infrared multi‐object tracking method for urban traffic, integrating both detection and tracking. During preprocessing, three infrared image enhancement techniques, local contrast multi‐scale enhancement, non‐local means, and contrast limited adaptive histogram equalization, are applied for better reliability in dense scenes. To further improve the performance, the original YOLOv8s backbone is replaced with MobileVITv3 to enhance detection accuracy and robustness. This infrared feature extraction module, incorporated into the detector, combines canny edge detection, Gabor filtering, and open operation layers, significantly boosting object detection in infrared imagery. The tracker's feature processing capabilities are improved using the learned arrangements of three patch codes descriptor and locality‐sensitive hashing for feature extraction and matching. Experimental results on FLIR ADAS v2 and InfiRay datasets indicate superior performance of this method, achieving 78.6% mAP and 151.1 FPS in detection, and up to 80.8% moving object tracking accuracy, 78.6% identification F1 score, and 62.1% higher order tracking accuracy in multi‐object tracking. [ABSTRACT FROM AUTHOR]

Whole brain segmentation from magnetic resonance images (MRI) is crucial in diagnosing brain diseases and analyzing neuroimaging data. Despite advances through deep learning, challenges such as uneven gray distribution and the presence of artifacts still present hurdles in medical image processing. These limitations are often a result of insufficient spatial contextual information and lack of attention to important regions within existing models. To address these issues, this paper presents SSA‐UNet (Squeeze‐and‐Excitation and Self‐Attention UNet), a uniquely designed deep convolutional neural network that integrates spatial constraints by converting three consecutive 2D MRI slices into a single 2.5D image. This facilitates capturing inter‐slice dependencies effectively. Additionally, the newly formulated SSA block, which sequentially incorporates channel attention and Self‐Attention mechanisms, is placed before the decoders in the conventional U‐Net architecture. This enables the network to automatically weight different feature maps and focus more effectively on regions requiring precise segmentation. Rigorous evaluations on LPBA40 and IBSR18 datasets substantiate the remarkable improvements in accuracy and stability achieved by SSA‐UNet. Results indicate Dice coefficients of 98.38% and 97.47%, specificity of 99.69% and 99.57%, and sensitivity of 98.5% and 97.98% for the respective datasets. Compared to other existing models, SSA‐UNet shows significant improvements on both the LPBA40 and IBSR18 datasets. On the LPBA40 dataset, SSA‐UNet's Dice coefficient improved by 0.33% compared to the sub‐optimal model, while on the IBSR18 dataset, the improvement reached 1.78%. These empirical findings demonstrate SSA‐UNet's heightened capability in addressing the long‐standing challenges in MRI‐based whole‐brain segmentation. [ABSTRACT FROM AUTHOR]

Pixel‐level labeling of regions of interest in an image is a key step in building a labeled training dataset for supervised deep learning networks of images. However, traditional manual labeling of cancerous regions in digital pathological images by doctors is time‐consuming and inefficient. To address this issue, this paper proposes an automatic labeling method for whole slide images, which combines clustering and edge detection techniques. The proposed method utilizes the multi‐level feature fusion model and the Long‐Short Term Memory network to discriminate the cancerous nature of the whole slide images, thereby improving the classification accuracy of the whole slide images. Subsequently, the automatic labeling of cancerous regions is achieved by integrating a density‐based clustering algorithm and an edge point extraction algorithm, both based on the discriminated results of the cancerous properties of whole slide images. The experimental results demonstrate the effectiveness of the proposed method, which offers an efficient and accurate solution to the challenging task of cancerous region labeling in digital pathological images. [ABSTRACT FROM AUTHOR]

In the field of scientific visualization, the upscaling of time‐varying volume is meaningful. It can be used in in situ visualization to help scientists overcome the limitations of I/O speed and storage capacity when analysing and visualizing large‐scale, time‐varying simulation data. This paper proposes self‐attention residual network‐based spatial super‐resolution (SARN‐SSR), a spatial super‐resolution model based on self‐attention residual networks that can generate time‐varying data with temporal coherence. SARN‐SSR consists of two components: a generator and a discriminator. The generator takes the low‐resolution volume sequences as the input and gives the corresponding high‐resolution volume sequences as the output. The discriminator takes both synthesized and real high‐resolution volume sequence as the input and gives a matrix to predict the realness as the output. To verify the validity of SARN‐SSR, four sets of time‐varying volume datasets are applied from scientific simulation. In addition, SARN‐SSR is compared on these datasets, both qualitatively and quantitatively, with two deep learning‐based techniques and one traditional technique. The experimental results show that by using this method, the closest time‐varying data to the ground truth can be obtained. [ABSTRACT FROM AUTHOR]

The Intelligent Evaluation System for Calligraphy Characters (IESCC) is used for teaching calligraphy, and users can learn calligraphy through the modifications given by the system. Chinese character skeleton extraction is an important step in the intelligent evaluation algorithm of calligraphic characters. The skeletons of Chinese characters extracted by traditional refinement algorithms are prone to redundant branches and deformed skeletons, which can lead to skeleton extraction results that do not conform to the topology of the original character. In this study, the focus lies on hard‐pen regular script, and skeleton repair and extraction are performed for these characters. According to the writing characteristics of regular script, the redundant burs are removed and the deformation zone of the thinned skeleton is detected, and then the idea of first splitting is used, then restructuring, to propose a skeleton extraction algorithm based on stroke characterization and ambiguous zone detection for hard‐pen regular script, referred to as SCAD. First, a thinning algorithm is used to extract the skeleton of Chinese characters and remove redundant pixels. By analyzing the stroke characteristics of regular script, the burrs are classified and different conditions are set to detect and remove the burrs. Then the ambiguous zones are detected according to the different kinds of junction points. Then, curvature, stroke width and direction deviation are used to analyze the continuity of stroke segments, and the decision function is used to classify the stroke segments. Finally, the stroke segments with optimal pairings were compensated by interpolation according to the direction trend. This concludes the skeleton extraction. Skeleton extraction is performed on 1000 sample characters, and the SCAD algorithm can extract the skeleton of Chinese characters with an accuracy of up to 98.37%. It is proved that the SCAD method proposed here is a practical and effective method to extract the skeleton of hard‐pen regular script. [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]

Despite the existence of various super‐resolution (SR) methods, most of them focus on designing models for specific upscaling factors rather than fully exploiting inter‐scale correlation to improve efficiency. In contrast, multi‐scale SR methods can effectively reduce the redundancy of network parameters by aggregating the feature extraction processes corresponding to multiple scales into a unified process. The aim of this study is to enhance the compactness and efficiency of the SR model. Thus, an efficient multi‐scale SR method called the diverse branch feature refinement network (DBFRN) is proposed. By decoupling the training process and inference process based on the idea of structural re‐parameterization, multi‐branch topology is adopted to enrich multi‐scale learning and merge branches to achieve efficient inference with equivalent effects. Specifically, two re‐parameterization strategies are designed and two corresponding feature refinement blocks for different feature levels in multi‐scale SR network. Extensive experiments demonstrate that the proposed multi‐scale SR method is effective and efficient, and it can outperform advanced single‐scale methods in terms of quantity and quality. [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]