Search

Underwater Image Enhancement (UIE) addresses challenges in marine resource exploitation such as absorption, noise, and low contrast. This paper employs bibliometric methods and data from Web of Science to analyze UIE literature. The analysis reveals that research on UIE entered a rapid development stage starting from 2017. Three main areas of technical support for research: underwater image enhancement methods, deep learning-based methods, and underwater image restoration and depth estimation. Hotspots in research include enhancement, deep learning, restoration, feature extraction, and quality assessment. Drawing from the bibliometric analysis, this paper proposes a conceptual framework for UIE research and presents five research suggestions: enhancing method robustness and adaptability, improving real-time performance, integrating software and hardware, establishing underwater image benchmark datasets, and refining quality evaluation systems for underwater images. This study offers valuable references and guidance for the future exploration and development of the UIE field. • Bibliometric analysis of underwater image enhancement (UIE) literature using Web of Science data. • Three main technical areas: enhancement methods, deep learning, restoration/depth estimation. • Research hotspots: enhancement, deep learning, restoration, feature extraction, quality assessment. • Proposes conceptual framework and five suggestions for future UIE research direction. • Recommendations include enhancing robustness, real-time performance, software–hardware integration, benchmark datasets, refined quality evaluation. [ABSTRACT FROM AUTHOR]

Domain adaptation has achieved great success in using labeled source domain samples to identify unlabeled target domain samples. Here, we aim to solve the open-set domain adaptation, which is different from the closed-set domain adaptation in that it contains categories in target domain that do not appear in source domain. To solve this problem, this paper proposes open-set domain adaptation model based on subdomain alignment, which uses variable weights for discriminative training of unknown samples in target domain. Aiming at the distribution differences between domains, the model aligns the distributions of the category subspaces of source and target domains, enhancing the distribution similarity within the subspaces of the same category. Through experiments on different domain adaptation datasets, the results show that the model proposed in this paper effectively improves the accuracy of open-set domain adaptation classification. [ABSTRACT FROM AUTHOR]

With the continuous development of urbanization, urban population, economy and other factors have a close impact on the geometry and distribution of urban buildings. Obtaining information of urban buildings from aerial images or satellite images quickly and accurately is not only conducive to updating geospatial data, but also of great significance for effective monitoring of new thematic information such as new buildings. Moreover, in recent years, the research and improvement of building recognition and contour extraction algorithms based on satellite images or aerial images are helpful to the recognition and classification of urban buildings. It is of great significance to the acquisition of GIS data, the understanding of images, large-scale mapping and many other applications of remote sensing data. With the development of artificial intelligence and computer technology, the image processing of intelligent building environment based on pattern recognition technology has become an important research direction in the field of intelligent building image recognition. Based on the concept, principle and technology analysis of pattern recognition technology, this paper studies the application of pattern recognition technology in the image processing of intelligent building environment. In this paper, based on image processing of intelligent building as the basic theoretical platform, with the pattern recognition technology as the basic research means, three problems of image processing, image extraction and image recognition in image processing of building intelligent environment are studied respectively, and corresponding reasonable solutions are put forward. [ABSTRACT FROM AUTHOR]

As the main media of human communication and understanding of the world, image is one of the important information sources of human intelligence activities. With the development of the times, the demand for image processing technology is increasing day by day. The rapid development of computer technology also provides a platform for the application of image processing. In order to achieve better image processing effect, this paper focuses on the application of artificial intelligence algorithm in image processing. Image segmentation is a technology that decomposes images into regions with different characteristics and extracts useful targets. It can be regarded as a combinatorial optimization problem. It is completely feasible to apply artificial intelligence algorithm to optimization problems. Firstly, this paper introduces the ant colony algorithm in artificial intelligence algorithm, elaborates the basic principle and mathematical model of the ant colony algorithm. Secondly, in order to improve the ability of global search of ant colony algorithm, this paper introduces the crowding degree function of fish into the ant colony algorithm. Finally, the improved ant colony algorithm is used in image segmentation to improve the effect of image segmentation. The simulation results show that it is feasible to use ant colony algorithm in image segmentation. And the optimization improvement of ant colony algorithm is effective. The improved ant colony algorithm applied in image segmentation can significantly improve the segmentation performance. [ABSTRACT FROM AUTHOR]

Abstract With the development of information technology, mechanical product design has become an important part of the enterprise and design community. In the traditional mechanical design process, the product not only has performance requirements, but also has many economic requirements such as manufacturing cost and sales profit. Many conditions also have great uncertainty. In addition, in design and evaluation, in addition to the existing theoretical analysis, in most cases, it is mainly judged based on the designer's experience. In view of the deficiencies in mechanical design, this paper proposes a key technology research of remote design of mechanical products based on artificial intelligence. The wireless communication technology is used to build a client/server wireless communication platform, which is convenient for designers to transmit remote information. The application of image processing and pattern recognition technology to target the components involved in mechanical products helps designers grasp many parameters of mechanical products. The research on the key technology of remote design of mechanical products based on artificial intelligence in this paper has certain reference value for the application of artificial intelligence technology in the field of mechanical product design with insufficient knowledge. [ABSTRACT FROM AUTHOR]

Abstract Financial paper is a note without reason debt or consideration acceptance, issued for obtaining money financing. Financial paper identification system is a hot issue of the current file analysis and identification system, it covers paper classification, image processing, character segmentation and identification, file image compression and other series of processes. A research on multiple aspects of financial paper identification system is made in this paper. On which basis, a financial paper identification system with applied value is established. Through substantive experimental test and practical application, the method has better classification performance and higher processing efficiency, and has been used in bank bill identification processing system in a large scale. [ABSTRACT FROM AUTHOR]

Abstract With the development of the game industry, and the new electronic consumption chain to promote the development of the game industry model continues to strengthen. Therefore, it is more necessary to make good use of good technology to do a good job of games. From the momentum of the development of mobile terminal games in recent years, the game industry has become a new economic growth point in China's economic transformation. With the development of computer and Internet, graphics and image processing technology has entered another unprecedented stage. In recent years, different image processing techniques have been used to process and analyze the game interface. Appropriate image processing methods include image enhancement, image binarization, image edge detection and image feature extraction. In this paper, by changing the mapping function from priority to probability and comparing the single mapping function of the previous algorithm, the mapping function of playback learning with higher probability of the important priority playback unit is found. In the experiment, the intuitive model strategy analysis of the improved algorithm is carried out firstly. Then the choice of CNN network layer structure, cost function analysis, efficiency analysis and game score comparison of each algorithm are carried out. Finally, the test results show that the new algorithm in this paper can make more effective decisions in video games and achieve the goal of winning higher scores and spending less time. [ABSTRACT FROM AUTHOR]

Highlights • A hierarchical framework is proposed to mimic humans for handling image tags. • A tree structure is constructed for image labels using a learning method. • Our model treats simple labels and complex labels separately. • Experiments results show promising performance on different datasets. Abstract Artificial Intelligence has attracted much of researchers' attention in recent years. A question we always ask is: "Can machines replace human beings to some extent?" This paper aims to explore the knowledge learning for an image-annotation framework, which is an easy task for humans but a tough task for machines. This paper's research is based on an assumption that machines have two systems of thinking, each of which handles the labels of images at different abstract levels. Based on this, a new hierarchical model for image annotation is introduced. We explore not only the relationships between the labels and the features used, but also the relationships between labels. More specifically, we divide labels into several hierarchies for efficient and accurate labeling, which are constructed using our Associative Memory Sharing method, proposed in this paper. [ABSTRACT FROM AUTHOR]

• Proposing a shift-insensitive perceptual feature based on GM and LoG signals, and theoretically selecting a ratio parameter to balance them. • Building FR-IQA models based on the proposed QGL feature maps that achieve good performance on three benchmark databases. • Achieving the best shift-insensitive performance on images with spatial changes compared with other metrics. • Combining QGL with deep neural networks and validating that QGL can help improving the accuracy in texture classification. Most existing full-reference (FR) Image quality assessment (IQA) models work in the premise of that the two images should be well registered. Shifting an image would lead to an inaccurate evaluation of image quality, because small spatial shifts are far less noticeable than structural distortion for human observers. To this regard, we propose to study an IQA feature that is shift-insensitive to the basic primitive structure of images, i.e., image edge. According to previous studies, the image gradient magnitude (GM) and the Laplacian of Gaussian (LoG) operator that depict the edge profiles of natural images are highly efficient structural features in IQA tasks. In this paper, we find that the Quadratic sum of the normalized GM and the LoG signals (QGL) has excellent shift-insensitive property in representing image edges after theoretically solving the selection problem of a ratio parameter to balance the GM and LoG signals. Based on the proposed QGL feature, two FR-IQA models can be built directly by measuring the similarity map with mean and standard deviation pooling strategies, named mQGL and sQGL, respectively. Experimental results show that the proposed sQGL and mQGL work robustly on four benchmark IQA databases, and QGL-based models show great shift-insensitive property to spatial translation and image rotation while judging the image quality. In addition, we explore the feasibility of combining QGL feature with deep neural networks, and verify that it can help to promote image pattern recognition in texture classification tasks. [ABSTRACT FROM AUTHOR]

Images taken in low-light conditions frequently encounter visibility problems, such as severe noise, reduced brightness, and low contrast. This paper introduces an approach to enhance low-light images using the Metropolis Theorem (MT). The method begins by applying a global gamma correction to the input image, followed by transforming the globally corrected image into the HSV (Hue, Saturation, Value - V) domain. To achieve multi-scale decomposition, an application of the MT is proposed, resulting in approximation and detail sub-images of the V component. Subsequently, local gamma correction is employed on both the final approximation and detail images to enhance local contrast. The refined approximation and detail images are then combined to reconstruct the refined V component. The reconstructed image is obtained by weighting each band of the image with the refined V component. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods, providing improved visual quality and more natural colors. [ABSTRACT FROM AUTHOR]

• A unified adversarial attack framework is designed to reveal the security of the state-of-the-art image tampering localization algorithms. • Two effective attack methods are proposed by relying on the optimization-based and gradient-based adversarial example strategies. • Extensive experimental evaluations verify that the proposed attacks can sharply reduce the tampering localization accuracy while preserving high visual quality for the attacked images. It is significant to evaluate the security of existing digital image tampering localization algorithms in real-world applications. In this paper, we propose an adversarial attack scheme to reveal the reliability of such deep learning-based tampering localizers, which would be fooled and fail to predict altered regions correctly. Specifically, two practical adversarial example methods are presented in a unified attack framework. In the optimization-based adversarial attack, the victim image forgery is treated as the parameter to be optimized via Adam optimizer. In the gradient-based adversarial attack, the invisible perturbation yielded by Fast Gradient Sign Method (FGSM) is added to the tampered image along gradient ascent direction. The black-box attack is achieved by relying on the transferability of such adversarial examples to different localizers. Extensive experiments verify that our attacks can sharply reduce the tampering localization accuracy while preserving high visual quality for attacked images. Source code is available at https://github.com/multimediaFor/AttackITL. [ABSTRACT FROM AUTHOR]

Despite the widespread availability of HDR (High Dynamic Range) display devices, the majority of video sources are still stored in SDR (Standard Dynamic Range) format, leading to an urgent need for UHD (Ultra High Definition) video reconstruction. A simple solution is to divide the task into two sub-tasks: video super-resolution (SR) and video Bit-Depth Enhancement (BDE). While some joint enhancement tasks led by SR have been explored in multiple dimensions, the quantitative dimension has often been overlooked. In this paper, we address the first joint task of BDE and SR and propose a succinct network called MSTG. We conduct a systematic analysis to explain how this effect can be achieved and overcome the core challenge arising from distortions exacerbated by the differing optimization directions of BDE and SR. This challenge is attributed to indistinguishable contours and detailed textures. To tackle this, we employ a dual-branch module that leverages both gradient and image information to discern between BDE and SR. Furthermore, we propose a novel model named Cross-scale Transformer (CTF) embedded with Cross-scale Attention (CSA). This model facilitates information aggregation while adaptively utilizing structural similarity features. It jointly extracts, aligns, and fuses frame features at multiple scales, forming the MST module. Experiments demonstrate that the proposed algorithm outperforms the cascaded video enhancement methods by large margins on both synthetic and realistic datasets. [ABSTRACT FROM AUTHOR]

The single image dehazing (SID) is challenging because of ill-posed characteristic, since there exist multiple possible dehazed images for a single hazy image due to multiple possible values of transmission. The SID is solved using scattering model, which requires computation of two parameters (transmission and atmospheric light) for its solution. The existing methods have presented priors and techniques to estimate transmission with limited focus on structure of the transmission. This paper proposes a lower bound on transmission using structural measure. The proposed lower bound is utilized to estimate the value of transmission, while preserving structural. Further, a quality control parameter is introduced to ensure non-negative value of the transmission for images with brighter objects than atmospheric light. The accuracy and efficiency of the proposed method is established by comparing with renowned SID methods using benchmark datasets. [ABSTRACT FROM AUTHOR]

Image inpainting is the process of restoring missing pixels in digital images in a plausible way. Research in image inpainting has received considerable attention in different areas, including restoration of old and damaged documents, removal of undesirable objects, computational photography, retouching applications, etc. The challenge is that the recovery processes themselves introduce noticeable artifacts within and around the restored image regions. As an alternative to subjective evaluation by humans, a number of approaches have been introduced to quantify inpainting processes objectively. Unfortunately, existing objective metrics have their own strengths and weaknesses as they use different criteria. This paper provides a thorough insight into existing metrics related to image inpainting quality assessment, developed during the last few years. The paper provides, under a new framework, a comprehensive description of existing metrics, their strengths, their weaknesses, and a detailed performance analysis on real images from public image inpainting database. The paper also outlines future research directions and applications of inpainting and inpainting-related quality assessment measures. [ABSTRACT FROM AUTHOR]

“What is this” and “where am I” are two common questions that arise when people travel abroad. Recently, landmark image identification has shown great promise for the addressed problems, where most previous approaches are either visual-based or location-based. However, regarding city-view image location identification, there could be a number of buildings in a close proximity. Moreover, it is common that photos were taken indoors. The conditions may degrade the performance of previous approaches. To remedy the deficiencies, this paper unifies visual features, geo-tags, and check-in data, based on cross-domain social media, for city-view image location identification. Besides, this paper shows an effective and memory-efficient implementation based on sparse coding, where a new dictionary selection approach is presented. Further, this paper proposes a location-aware graph-based regrouping approach, leveraging spanning graph construction, on clusters of photos to refine clustering results. Experimental results show the improvement over the baselines (location-based, visual-based, etc.). [ABSTRACT FROM AUTHOR]

The recent growth of multimedia content used in daily-life communication requires the development of image description techniques able to unequivocally identify observed objects, despite image transformations, demanding lighting conditions, or noise. This paper focuses on binary feature descriptors which are often used for this purpose. They have smaller memory footprint, and are faster to compute and match than their floating-point counterparts. Hand-crafted binary descriptors use an image patch around the detected keypoint and divide it into disjoint regions, or select pixels according to a sampling scheme. In this paper, an approach to binary, rotation and scale invariant descriptor is proposed. In the descriptor, a small number of scale-dependent patches are divided into overlapping blocks of pixels, and then binary tests are performed on blocks’ intensities and gradients. The extensive experimental evaluation of the approach on seven image benchmarks reveals that it outperforms compared state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

Low-light conditions present a myriad of intricacies for object detection, with many existing methods relying primarily on image enhancement before detection. Sometimes, the enhancement methods are unable to improve the detection performance in low-light conditions. In this paper, we present a new Multi-exposure refinement network for low-light object detection (MRN-LOD) to avoid the need for enhancement before detection. The MRN-LOD contains: multi-exposure feature extractor, adaptive refinement network, and detection head. The developed multi-exposure feature extractor extracts features from the multi-exposure images generated by the low-light image. We introduced the notion of feature extraction from multi-exposure images for object detection in low light. In addition, we proposed an adaptive refinement network to refine the features of low-light images for better detection performance. The detection head uses the refined features to perform object detection. Extensive experimentation on real-world and synthetic datasets shows the superiority of the proposed MRN-LOD. [ABSTRACT FROM AUTHOR]

Light field imaging can capture rich information of real scenes, but various distortions will inevitably be introduced in the process of light field image processing. Therefore, it is very important to effectively evaluate the quality of light field images. Due to the lack of commercial light field displays, this paper proposes a blind quality assessment method of light field image based on view and focus stack, based on the visualization technology used in the subjective evaluation of light field images and the human brain's perception process of visual information in the study of visual physiology. First, spatiotemporal Gabor filtering is performed on distorted sub-aperture images (SAIs) to extract the spatial and angular information. On the other hand, the SAIs are refocused to obtain the refocused images with different focusing depths, and then the focus stack is filtered by spatiotemporal Gabor filtering to extract the angular information. In addition, the focus stack is detected to form in-focus area and out-of-focus area, and the features related to spatial structure, depth and semantic information of the refocused images are extracted to evaluate the spatial quality. Finally, support vector regression (SVR) is performed to predict the objective scores by establishing the relationship between the features and subjective scores. Experimental results show that our method can well predict the human eye's perception quality of light field images. [ABSTRACT FROM AUTHOR]

Graphical Abstract of the proposed network, Module 1 shows the Global-local network, Module 2 shows RGB histogram equalizer, and Module 3 shows the attention module. (b) The structure of B_Block, and (c) The structure of C_block in the proposed network. [Display omitted] • An end-to-end synergetic integration of classic image processing and CNNs. • Using an attention module to emphasize meaningful parts of underwater images. • Proper employing histogram equalization to avoid producing color artifacts. • Introducing a lightweight model, suitable for different types of underwater images. This paper presents a deep learning-based underwater image enhancement method supported by a classical image processing technique. The proposed method includes an end-to-end three-module structure. The first module is a lightweight two-branch network that retrieves lost colors and to some extent overall appearance through the global and local image enhancement. The second module is the modified histogram equalization to improve the global intensity, contrast and local colors of the image by controlling over-intensity and artificial colors that may result from histogram equalization. The last part is the attention module, utilized to help the proposed framework have a synergistic combination of the previous modules. The attention module is designed to combine the advantages of the previous modules and evade their drawbacks. Experiments to objectively and subjectively evaluate the performance of the proposed model show that the proposed model is superior to existing underwater image enhancement methods. [ABSTRACT FROM AUTHOR]

The existing deraining methods have obtained noteworthy improvements, but it is a challenging problem to extend the methods for complicated rain conditions where rain streaks exhibit different distribution densities, sizes, shapes , etc. The main challenges are the ability to fully explore and utilize the multi-scale context information of rain streaks that maintain both global structure completeness and local detail accurateness. To this end, this paper proposes an E xploring C ontext- G ated N etwork, known as ECG Net. To adequately explore the richer context information, the proposed method consists of two key elements: context-enhanced feature block (CEFB) and multi-scale-gated aggregation block (MGAB). Specifically, the various scale features can be captured by CEFB with the multi-scale operation, to better remove the rain streaks and effectively restore the local detail textures. Subsequently, the captured features from different spaces are sent to MGAB, to aggregate and transmit these different scale features from the encoder to the decoder and reduce the transmission loss of information. Massive experiments on the commonly used benchmarks have demonstrated that the proposed method obtains more appealing performances against other competitive methods. • Capturing multi-scale features and enhancing contextual information, obtaining local modeling and long-range dependency. • Gated aggregation information from different levels, reducing redundant features and loss of informational transmission. • Better rain streaks removal and recovering image details and textures. [ABSTRACT FROM AUTHOR]

Domain Generalization (DG) model is an important tool to improve the robustness of person re-identification algorithm, but the domain gap makes it difficult to transfer knowledge cross-domain effectively. To solve the above problems, this paper proposes a generalization model based on a Meta-Bond Domain Alignment (M−BDA) model. To learn a generalizable model, a meta -learning strategy is introduced to simulate the training–testing process of the domain generalization. Then a bond-domain module is constructed in the training to align the source domain, which can reduce the domain gap between the source domain and the target domain, and facilitate the knowledge transfer. Finally, the bond-domain loss is counted on the feature space of the bond-domain to prevent the generated bond-domain from overfitting to the source domain. The experimental results show that the proposed algorithm achieves better performance in DukeMTMC-ReID, Market1501 and MSMT17 alternating as the source and the target domain tasks. In the generalization experiments of Market-1501 → DukeMTMC-ReID, mAP and Rank-1 increased by 7.7 % and 3.6 %, respectively, and in the generalization experiments of DukeMTMC-ReID → Market-1501, mAP and Rank-1 are increased by 9.3 % and 3.5 %, respectively, which are significantly better than the newer representative algorithms. [ABSTRACT FROM AUTHOR]

Domain generalizable person re-identification (DG ReID) aims to obtain a model that can be applied directly to unseen domains once trained on a set of source domains (datasets collected from different camera networks). Among current DG ReID methods, instance normalization is a promising solution to reduce the effect of domain bias, but it inevitably filters out some discriminative information. Besides, since most pioneering approaches cannot effectively address the loss of discriminative information, this paper proposes a Style Elimination and Information Restitution (SEIR) module and constructs a generalizable framework. Specifically, we utilize instance normalization to reinforce the generalization capability on unseen domains. Then, the instance-specific mean and variance are employed to construct a feature vector that includes discriminative and style information. Besides, an encoder–decoder structure is designed to restitute the discriminative information to ensure a high recognition rate. Finally, a dual optimization strategy is devised to update the proposed module by simulating a real train-test process to enhance the generalization robustness further and prevent SEIR from overfitting to the source domain. Extensive experimental results demonstrate that the proposed method outperforms the state-of-the-art methods by a large margin on the public DG ReID benchmarks. • A Style Elimination and Information Restitution module for handling domain bias. • An optimization strategy for improving the generalization ability. • We propose a framework for generalizable person re-identification. • Significant results were achieved for addressing the generalizable person re-identification. [ABSTRACT FROM AUTHOR]

In the last decade, the exploration of deep-sea ecosystems has surged, offering exciting prospects for discovering untapped resources such as medical drugs, food and energy sources, and renewable energy products. Consequently, research in underwater image processing has witnessed substantial growth. However, underwater imaging poses significant challenges, particularly without sophisticated, specialized cameras. Traditional cameras are impacted by absorption and scattering in the aquatic environment, producing hazy images with a blue–green tint. This phenomenon holds implications for marine research and other disciplines that rely on underwater imaging. While hardware advancements have been made over the years, image processing remains a valuable, cost-effective, and practical approach for underwater enhancement. Despite the existence of state-of-the-art techniques for underwater enhancement and restoration, their performance is often inconsistent. While some methods excel in contrast restoration, color restoration remains a pervasive challenge. In this paper, we introduce Sea-Pix-GAN, a Generative Adversarial Network (GAN)-based model that addresses these issues in underwater image enhancement. We redefine the problem as an image-to-image translation task and tailor the objective and loss functions to achieve color, content, and style transfer. The model is trained on a large dataset of underwater scenes, encompassing the diverse color dynamics of underwater subjects. Sea-Pix-GAN demonstrates promising results in restoring color, contrast, texture, and saturation. To validate its effectiveness, we compare the performance of Sea-Pix-GAN quantitatively based on metrics like PSNR, SSIM, and UIQM and qualitatively against several existing techniques. [ABSTRACT FROM AUTHOR]

Transformer has achieved impressive successes for various computer vision tasks. However, most of existing studies require to pretrain the Transformer backbone on a large-scale labeled dataset (e.g., ImageNet) for achieving satisfactory performance, which is usually unavailable for medical images. Additionally, due to the gap between medical and natural images, the improvement generated by the ImageNet pretrained weights significantly degrades while transferring the weights to medical image processing tasks. In this paper, we propose Bootstrap Own Latent of Transformer (BOLT), a self-supervised learning (SSL) approach specifically for medical image classification with the Transformer backbone. Our BOLT consists of two networks, namely online and target branches, for self-supervised representation learning. Concretely, the online network is trained to predict the target network representation of the same patch embedding tokens with a different perturbation. To maximally excavate the impact of Transformer from limited medical data, we propose an auxiliary difficulty ranking task. The Transformer is enforced to identify which branch (i.e., online/target) is processing the more difficult perturbed tokens. Overall, the Transformer endeavours itself to distill the transformation-invariant features from the perturbed tokens to simultaneously achieve difficulty measurement and maintain the consistency of self-supervised representations. The proposed BOLT is evaluated on three medical image processing tasks, i.e., skin lesion classification, knee fatigue fracture grading and diabetic retinopathy grading. The experimental results validate the superiority of our BOLT for medical image classification, compared to ImageNet pretrained weights and state-of-the-art SSL approaches. [ABSTRACT FROM AUTHOR]

• A two-branch end-to-end dehazing network is proposed, which can solve the imbalances weight distribution problem between the detail and structural features. • Coordinate channel attention module is employed to extract the structural features and the dense pixel attention modules is employed to extract the detail features. • Extensive experiments are conducted on both synthetic and real-world dataset and performed well. Image dehazing is an ill-posed problem that has been extensively studied in recent years. Unfortunately, most existing deep dehazing models have high computational complexity and lack the dynamic adjustment of details, which hinders their application to high-resolution images in computational vision tasks. In this paper, we propose an efficient dual-path adaptive fusion dehazing network (DPAFD-Net) to directly restore a clear image from a hazy input. Moreover, we propose a pure subnetwork with encoder and decoder structures to further extract the structural information and progressively restore the haze-free image. To evaluate the effectiveness of the proposed method, we validate our approach on synthetic and real hazy images, where our method performs favourably against the state-of-the-art dehazing approaches. [ABSTRACT FROM AUTHOR]

In social networks, people usually communicate online by posting and passing images, people will find that there are many similar or even visually identical images. When the images determine whether the published information is true or false, original images became crucial, and at the same time, deep learning excelled in image identification. Combining the original image identification and deep learning methods, this paper proposes the original image identification method based on the deep network models, aiming to use the deep network models to identify the original images between the original images and a bunch of variant images of the original images, and obtain satisfactory results. In this way, through the trained network models, the original images can be identified and can help the viewers to determine the correctness of the information. Experimental results verify the feasibility, effectiveness and security of the proposed method. • The method can prevent the images from being stolen during transmission. • The method can achieve good identification results on the image databases. • The method is feasible and flexible in actual operation. [ABSTRACT FROM AUTHOR]

• An image fusion method is proposed that can effectively highlight infrared target features and retain visible visual information. • Infrared targets are analyzed based on the saliency weight map. • The target contour and background texture are refined by a method based on weight refinement of guided filtering. • A multi-layer fusion strategy is used to fuse saliency weight maps at multiple scales. Image fusion is the fusion of multiple images from the same scene to produce a more informative image, and infrared and visible image fusion is an important branch of image fusion. To tackle the issues of diminished luminosity in the infrared target, inconspicuous target features, and blurred texture of the fused image after the fusion of infrared and visible images. This paper introduces a novel effective fusion framework that merges multi-scale Convolutional Neural Networks (CNN) with saliency weight maps. First, the method measures the source image features to estimate the initial saliency weight map. Then, the initial weight map is segmented and optimized using a guided filter before being further processed by CNN. Next, a trained Siamese convolutional network is used to solve the two key problems of activity measure and weight assignment. Meanwhile, a multi-layer fusion strategy is designed to effectively retain the luminance of the infrared target and the texture information in the visible background. Finally, adaptive adjustment of the fusion coefficients is achieved by employing saliency. The experimental results show that the method outperforms the state-of-the-art algorithms in terms of both subjective visual quality and objective evaluation effects. [ABSTRACT FROM AUTHOR]

• A small target detection algorithm based on feature interaction and guided learning. • A feature guided alignment module is designed to obtain more effective features. • Gaussian distribution sample allocation strategy is introduced to obtain better samples. • Feature interaction and decoupling detection enhance the detection task capability. • A new regression loss function is used to optimize the localization ability to a certain extent. At present, for the diverse target sizes, different angles, and complex environment in aerial images, how to detect small objects effectively in aerial images is still a challenge task. In order to further improve the detection accuracy and reduce the missing rate, in this paper, we proposes a small target detection algorithm based on feature interaction and guided learning. Firstly, the feature guided alignment module is designed to deal with the problem of information loss and overlap. Secondly, the misallocation of small object samples is optimized by introducing gaussian sample allocation strategy. Then the interactive parallel detection header is designed to solve the detection task conflict problem. Finally, the new regression loss function is designed to enhance the localization ability of the target. The experimental results on the Tinyperson dataset and Visdrone dataset show that this model can improve the detection accuracy and reduce the missing rate of small targets effectively. [ABSTRACT FROM AUTHOR]

This paper focuses on the task of human-object interaction (HOI) recognition, which aims to classify the interaction between human and objects. It is a challenging task partially due to the extremely imbalanced data among classes. To solve this problem, we propose a language-guided graph parsing attention network (LG-GPAN) that makes use of the word distribution in language to guide the classification in vision. We first associate each HOI class name with a word embedding vector in language and then all the vectors can construct a language space specified for HOI recognition. Simultaneously, the visual feature is extracted from the inputs via the proposed graph parsing attention network (GPAN) for better visual representation. The visual feature is then transformed into the linguistic one in language space. Finally, the output score is obtained via measuring the distance between the linguistic feature and the word embedding of classes in language space. Experimental results on the popular CAD-120 and V-COCO datasets validate our design choice and demonstrate its superior performance in comparison to the state-of-the-art. • This paper proposes a language-guided graph parsing attention network (LG-GPAN). • We leverage the relationship of the visual and language to the HOI recognition. • LG-GPAN outperforms the previous human-object interaction recognition methods both on CAD-120 and V-COCO dataset. [ABSTRACT FROM AUTHOR]

It is known that the rotations of real-world color textures will vary arbitrarily. This paper presents a novel, simple, yet powerful method for rotation-invariant color texture classification. Firstly, we define a Distance-based Local Binary Pattern (DLBP) descriptor to characterize the color texture. By learning the joint distribution of the rotation-invariant DLBP and color intensity information, we define our Multiple Sub-DLBPs ( MS _ DLBP ) descriptor. The MS _ DLBP features defined in this paper are invariant to rotation. Here, we also compared seven important color spaces in terms of their effectiveness in our proposed MS _ DLBP approach. The experimental results on the Outex and CUReT databases show the defined DLBP descriptor performs better than the existing color LBP descriptors and the proposed MS _ DLBP approach is very robust to rotation invariance and outperforms state-of-the-art texture analysis methods. Also, HSV color space is shown to outperform the other color spaces in many cases. [ABSTRACT FROM AUTHOR]

Saliency detection has extensive applications in daily life. In this paper, an efficient saliency-detection method based on wavelet transform and entropy theory is proposed. In the algorithm proposed in this paper, salient regions are viewed as uncommon regions in the background of an image. The uncommon regions can be caused by differences in color, orientation, texture, shape, or other factors. Considering the fact that wavelet coefficients can represent the local features of an image in different scales and orientations, the wavelet transform is therefore employed to identify the salient regions. Unlike those conventional wavelet-based methods, our proposed method need not perform the inverse wavelet transformation; this can reduce the computational requirements. In addition, because the different factors (i.e. color, orientation, texture, shape, etc.) stimulate different aspects of the human visual system, a saliency-map combination scheme based on the entropy theory is devised in this paper, which can evaluate the influence or significance of the different factors. Experimental results show that our method, based on wavelet transformation and entropy theory, can achieve excellent performance in terms of the area under the receiver operating characteristic curve (AUC) score, the linear correlation coefficient (CC), the normalized scan-path saliency (NSS) score, and visual performance, as compared to existing state-of-the-art methods. [ABSTRACT FROM AUTHOR]

As the high-dimensional heterogeneous visual features extracted from images are intrinsically embedded in a non-linear space, some kernel methods such as SVM have been proposed to solve this problem. Since different kinds of heterogeneous features in images have different intrinsic discriminative powers for image understanding, how to enforce grouping sparsity penalty to effectively select out discriminative heterogeneous visual features is critical for image understanding. Most existing approaches are using a convex penalty for feature selection, which easily leads to inconsistent selection. To guarantee a consistent selection for heterogeneous features embedded in a non-linear space, this paper proposes a new approach called MKL-NOVA (Multiple Kernel Learning with NOn-conVex group spArsity). Because MKL-NOVA conducts a non-convex penalty for the selection of groups of features, it achieves the consistent selection. Furthermore, considering the contextual correlation between multi labels, sparse canonical correlation analysis is conducted to boost the image annotation performance by MKL-NOVA. We have demonstrated the superior performance of MKL-NOVA via two experiments in the paper. First, we showed that MKL-NOVA converges to the true underlying model by using a ground-truth-available generative-model simulation. Second, we compare the proposed MKL-NOVA and the state-of-the-art approaches which showed that MKL-NOVA achieved the best performance. [ABSTRACT FROM AUTHOR]

Image denoising is a low-level computer vision task that aims to reconstruct high-quality images from noisy ones. However, large networks with a high computational burden have been employed in existing works in pursuit of high-quality images. This paper introduces an Information Fusion Guided Lightweight Transformer (IFGLT) that can lessen the computational burden and achieve superior restoration results. The Feature Enhancement Module (FEM) optimizes the computing cost of the Transformer layer by layer using various techniques such as group mapping, channel generation, fusion convolution, and window rearrangement. The Information Compensation Module (ICM) gradually compensates for missing information by leveraging the original image. The Lightweight Sample Module (LSM) performs up-sampling and down-sampling with the minimal computing cost by altering the order of feature transformation. The experimental results demonstrate that our proposed IFGLT attains higher objective indices and achieves better visual effects with reduced computing cost in comparison to conventional methods. • Optimize the Transformer using four strategies. • Compensate for missing information by leveraging the original image. • Perform sampling by altering the order of feature transformation. [ABSTRACT FROM AUTHOR]

• We propose a novel IQA method for underwater images by extracting five types of quality-aware features. • We design a color-cast weighted colorfulness measurement and a saliency-weighted contrast measurement. • We construct an underwater image dataset with MOS values. In this paper, we propose a novel no-reference evaluator based on quality-aware features, called QA-UIQE, for underwater image quality assessment. QA-UIQE extracts and fuses a set of quality-aware features including naturalness, color, contrast, sharpness, and structure. Technically, we first present a new color-cast weighted colorfulness measurement as well as color consistency measurement to characterize color, and design a saliency-weighted contrast measurement to improve the distinguishing ability of measuring contrast. Also, the locally mean subtracted and contrast normalized, maximum local variation, and local entropy are incorporated to measure naturalness, sharpness and structure, respectively. Afterward, we integrate the feature vectors extracted from the training set into Gaussian process regression to predict the image quality. Moreover, we collect a real-world underwater image dataset for testing the generalization ability of our method. The experimental results illustrate that our QA-UIQE has a superior prediction accuracy and is highly consistent with human visual perception. [ABSTRACT FROM AUTHOR]

Previous deep learning-based single image dehazing methods are implemented by using real-valued convolutional neural network (RV-CNN), which ignore the phase information of the image, and tend to cause models to perform well on synthetic datasets but low generalization on real-world datasets. In this paper, we propose a novel Complex-Valued convolutional Dehazing Network (CVD-Net), which considers both amplitude and phase information of image for haze removal in real-world scenes. Specifically, we construct complex-valued transformation module, including complex-valued convolutional layer and residual block embedded into the middle of the network to extract features of image efficiently, and also design a complex-valued selected fusion module (CVSF) and complex-valued attention module (CVAM) to promote the interaction between different scale features for preserving image detailed information. Both qualitative and quantitative experimental results show that the proposed CVD-Net can effectively remove the haze, and has good generalization in real-world hazy images. [ABSTRACT FROM AUTHOR]

Due to the limitations of autoencoders and generative adversarial networks, the performance of reconstruction-based unsupervised image anomaly detection methods are not satisfactory. In this paper, we aim to explore the potential of a more powerful generative model, the diffusion model, in the anomaly detection problem. Specifically, we design a Reconstructed Diffusion Models (RecDMs) based on conditional denoising diffusion implicit models for image reconstruction. To eliminate the stochastic nature of the generation process, our key idea is to use a learnable encoder to extract meaningful semantic representations, which are then used as signal conditions in an iterative denoising process to guide the model in recovering the image, while avoiding falling into an "identical shortcut" to meaningless image reconstruction. To accurately locate anomaly regions, we introduce a discriminative network to obtain the pixel-level anomaly segmentation map based on the reconstructed image. Our experiments demonstrate the effectiveness of the proposed method, achieving a new state-of-the-art image-level AUC score of 98.1% and a pixel-level AUC score of 94.6% on the MVTec AD dataset, among all reconstruction-based methods. We also show the significant potential and promising future of our method on the challenging real-world dataset, the CHL AD dataset. • A novel reconstruction-based unsupervised anomaly detection framework. • Research on image reconstruction technology based on conditional diffusion models. • Our approach can efficiently model complex data distributions. [ABSTRACT FROM AUTHOR]

• To avoid poor generality and long encryption time caused by overflow processing, the positive DC prediction error modulo encryption is designed. • For the first time, the concept of AC groups based on undivided RSV (ACG-URSV) is proposed. It can effectively preserve file size when encryption since the unchanged run length of non-zero AC coefficient ensure the integrity of original entropy encoding. • To change different block feature values, ACG-URSVs permutation is divided into two categories: complete ACG-URSVs permutation and ending ACG-URSVs permutation. The former type is mainly used to change non-zero coefficients count and energy of AC coefficients, while the latter type is mainly used to change position of last non-zero coefficients. • ACG-RSVs permutation can improve the security of statistics analysis since it has highest change rates of block feature values compared to existing JPEG image encryption schemes. In the existing JPEG image encryption schemes, the block feature values that can be used to reduce key search space are either difficult to be changed or need to be changed through overflow processing which leads to low generality and high encryption runtime. To change block feature values without overflow processing, a novel JPEG image encryption scheme is proposed. For AC encryption, the complete and end AC groups based on undivided RSV (run/size, value) (ACG-URSV) are permuted separately to change different features. Complete ACG-URSV containing different number of RSVs is used to change the non-zero coefficients count (NCC) and energy of AC coefficients (EAC). End ACG-URSV containing the zero coefficients after position of last non-zero AC coefficient (PLZ) is mainly used to change PLZ. Besides, the intra-block RSV permutation and block permutation are used to further destroy correlation. For DC encryption, the positive DC prediction error (PDC-PE) groups modulo encryption is proposed to avoid overflow processing. The experimental results show that this paper reduces encryption runtime by more than half, improves generality by at least 20%. When quality factor of 90, the average change rates of NCC, EAC and PLZ values are increased by 96.28%, 11.68% and 29.15%, respectively. [ABSTRACT FROM AUTHOR]

Different parts of an image have a strong or weak guiding effect on emotions. The key to emotion recognition of images is to fully exploit the regions associated with emotions. Therefore, this paper proposes a visual sentiment classification model with two branches based on visual transformer, termed as Enhanced Effective Region and Context-Aware Vision Transformers (EERCA-ViT). This model includes a primary branch and an auxiliary branch. The primary branch simulates interdependencies between patches by squeezing and stimulating patches (P-SE), thereby highlighting effective region features in the global feature. The auxiliary branch removes feature patches that have been tagged by the primary branch through the context-aware module (CAM), forcing the network to discover different sentiment discriminative regions. At the same time, a two-part loss function is constructed to improve the robustness of the model. Finally, extensive experiments on six benchmark datasets show that the proposed method outperforms the state-of-the-art image sentiment analysis methods. Furthermore, the effectiveness of the different modules of the framework (P-SE and CAM) has been well demonstrated through extensive comparative experiments. • Removing focused regions can guide the network to capture effective contextual sentiment features. • Fully mining the features of sentiment-related regions is one of the key approaches to sentiment classification. • The method's effectiveness and generalisability were confirmed through extensive experiments on eight datasets. [ABSTRACT FROM AUTHOR]

• A layout plane is a closed loop surrounded by layout keypoints. • The wall structure can be parametrization as an undirected graph. • Layout keypoint prediction is relative to human pose estimation. • Cuboid room assumption is limited in real life. Room layout estimation aims to predict the spatial structure of a room from a single image. Most existing methods relying on 2D cues are suitable for cuboid rooms, but non-cuboid rooms. 3D layout estimation methods can reconstruct 3D models of general rooms, but they are trained with depth information on high collection costs, consume large computation resources, and run slowly. This paper considers an undirected graph representation method of the general room layouts, which includes cuboid and non-cuboid rooms consisting of a single ceiling, a single floor, and multiple walls. To this end, we first predict the positions of the layout vertices and then use the network automatically learn the connection relationship between the vertices. The final layout is obtained through a simple layout inference post-processing algorithm. The experimental results both on cuboid and non-cuboid datasets validate the effectiveness and efficiency of our method. The code is available at https://github.com/Hui-Yao/2D-graph-layout-estimation. [ABSTRACT FROM AUTHOR]

Inspired by the generative adversarial networks EnlightenGAN, this paper proposes a novel low-light images Enhancement and Denoising model based on unsupervised learning Multi-Stream feature modeling (MSED). The model has two stages: generator network and discriminator network. Generator network includes global and local feature modeling network. First, Swin Transformer Block is innovatively introduced in the global feature modeling of generator network stage. It makes the interaction between the image and the convolutional kernel related to the image content. Its shift window mechanism can model the global feature dependency of the input image with less memory consumption, and extract the color, texture, and shape features of the image, thereby effectively suppressing noise and artifacts. Second, in the local feature modeling, a multi-scale image and feature fusion branch is added. It not only extracts reduced features from large-scale low-light images, but also extracts features from multiple downsampled low-light images, and then combines the two through attention and DSFF. By utilizing the complementary information of the reduced features and downsampled images, various underexposure/ overexposure phenomena caused by low-light images can be effectively avoided. In the discriminator network stage, the deep/shallow feature aggregation module is added to enhance the discrimination ability, and the inconsistencies are suppressed by learning the contradictory information of spatial filter, so that the shallow representation of information and the deep semantic information can guide each other. Thanks to the synergy of the above three innovative work, compared with many existing advanced low-light images enhancement models, MSED can achieve SOTA level performance on several public datasets. However, when dealing with low-light images with blurry content caused by rapid motion, MSED still cannot effectively restore their detailed information. [ABSTRACT FROM AUTHOR]

Person Re-Identification (PR-Id) encounters misclassification issues when re-identifying persons with different backpacks. These bags manifest as large and distinct regions in the images surpassing other finer details of a person. As a result, a CNN model swiftly detects and prioritizes these image regions for re-identification. However, the bags are subject to alterations or may be similar among multiple persons, resulting in misclassification. To ensure that a CNN model does not consider bags as unique features of specific persons and prioritize them for re-identification, images of persons with diverse backpacks are crucial in the training dataset. Moreover, these images enhance the model's focus on other unique regions of a person. Although the current datasets show potential, incorporating such images could enhance their effectiveness. Therefore, in this paper, we propose an indoor PR-Id dataset named "With Bag/Without Bag-ReID" (WB/WoB-ReID). The set "with_bag" in WB/WoB-ReID dataset includes identities with different backpacks for the first time. We also incorporate identities without bags and with varying numbers of image counts in three other sets, namely "without_bag", "both_small," and "both_large". We assess WB/WoB-ReID and three other PR-Id datasets: Market1501, CUHK03, and DukeMTMC-reID on various existing approaches. The highest mAP achieved on the"with_bag" is 74%, "without_bag" is 96.7% and other datasets are 97.78%, 95.20% and 92.4%. The results show that incorporating identities with diverse bags reduces the mAP, highlighting the misclassifications that arise specifically in the presence of bags. [ABSTRACT FROM AUTHOR]

Despite the remarkable results achieved by deep convolutional neural networks (CNNs) in single image super-resolution (SISR), their computational cost increase exponentially as CNN models get deeper and wider. Consequently, depthwise separable convolutions (DSConvs) have emerged as the fundamental building basis for various contemporary lightweight network architectures. However, depthwise convolution is sub-optimal for restoring missing high-frequency details. In this paper, we commence with the vanilla depthwise convolution and progressively develop it to alleviate the above problem. Specifically, we introduce an effective method, kernel attention injection, to integrate intra-kernel correlation into the depthwise convolution layer by incorporating the learned kernel attention into the depthwise kernel. We find that the determinant is capable of capturing the correlation between diagonal elements of the depthwise kernel by summing the products of the diagonals. Therefore, we utilize the determinant as the kernel pooling method. Furthermore, we propose to remove the non-linear activation function behind the depthwise convolution (i.e. , linear depthwise convolution) to preserve informative features for reconstructing faithful high-resolution (HR) images. Built on this recipe, we introduce kernel-attentive linear depthwise separable convolutions (KDSConvs), which exhibits promising super-resolution performance. Our experimental results underline the potential of depthwise convolution in super-resolution tasks by demonstrating that the proposed KDSConvs significantly outperforms DSConvs in terms of both quantitative measurements and visual quality. The code will be released at https://github.com/AwesomeHwang/KALDN. • We propose kernel attention injection to integrate intra-kernel correlation. • We utilize the determinant as the kernel pooling method. • We introduce kernel-attentive linear depthwise separable convolutions. [ABSTRACT FROM AUTHOR]

Underwater images often suffer from severe distortion, which seriously affects the image quality and the application. Current underwater image enhancement methods have poor generalization capability and cannot be adapted to all types of underwater images. In recent years, the diffusion model based on the denoising diffusion probabilistic model (DDPM) has achieved excellent results in various fields of computer vision. Inspired by the DDPM, an underwater image enhancement method based on the DDPM (UW-DDPM) was proposed in this paper. The UW-DDPM trained on paired datasets and utilized two U-Net networks to complete image denoising as well as image distribution transformation, which effectively improved the quality of underwater images. By testing on real underwater image datasets, UW-DDPM achieved better improvement in visual effects and evaluation metrics than the existing model. • A new model for underwater image enhancement tasks. • An improved inference strategies. • Impressive experimental results. [ABSTRACT FROM AUTHOR]

• The point cloud (PC) quality assessment problem is converted into the joint quality assessment problem of texture projection map (TPM) and geometry projection map (GPM). • Through the geometric and texture distortion representations in the GPM and TPM inherited from colored PC in 3D space, some perceptual features are mined from these maps, to achieve the purpose of evaluating the visual quality of colored PC. • Handling with both geometry and texture attributes in compression distortion and noise pollution, a multi-distorted Colored PC Database (denoted as CPCD2.0) with subjective scoring is constructed. • Experimental results demonstrate the superiority of the proposed method. Colored point cloud (PC) will inevitably encounter distortion during its acquisition, processing, coding and transmission, which may affect the visual quality of the colored PC. Therefore, it is necessary to design an effective tool for colored PC quality assessment (PCQA). In this paper, considering the mapping relationship of perception between the colored PC and its corresponding projection images, we propose a novel PCQA method based on texture and geometry projection (denoted as TGP-PCQA). The main idea of the proposed TGP-PCQA method is to obtain texture and geometry projection maps from different perspectives for evaluating the colored PC. Specifically, 4D tensor decomposition is used to obtain the combination and difference information between the reference and distorted texture projection maps for mainly characterizing texture distortion of colored PC. Meanwhile, the edge features of the geometry projection map are calculated to measure the global or local geometry distortion. All of the extracted features are combined to predict an overall quality of colored PC. In addition, this paper establishes a multi-distorted colored PC database named CPCD2.0 with compression distortions and Gaussian noise, which orients to the influence of both geometry and texture components in distortion. Experimental results on two open subjective evaluation databases (IRPC and SJTU-PCQA) and the self-built CPCD2.0 database show that the proposed TGP-PCQA method outperforms the state-of-the-art PCQA methods. We are also providing the self-built CPCD2.0 database free of charge at https://github.com/cherry0415/CPCD2.0. [ABSTRACT FROM AUTHOR]

Analysis of human behavior through visual information has been one of the active research areas in computer vision community during the last decade. Vision-based human action recognition (HAR) is a crucial part of human behavior analysis, which is also of great demand in a wide range of applications. HAR was initially performed via images from a conventional camera; however, depth sensors have recently embedded as an additional informative resource to cameras. In this paper, we have proposed a novel approach to largely improve the performance of human action recognition using Complex Network-based feature extraction from RGB-D information. Accordingly, the constructed complex network is employed for single-person action recognition from skeletal data consisting of 3D positions of body joints. The indirect features help the model cope with the majority of challenges in action recognition. In this paper, the meta -path concept in the complex network has been presented to lessen the unusual actions structure challenges. Further, it boosts recognition performance. The extensive experimental results on two widely adopted benchmark datasets, the MSR-Action Pairs, and MSR Daily Activity3D indicate the efficiency and validity of the method. [ABSTRACT FROM AUTHOR]

Abstract: Semi-supervised learning (SSL) is widely-used to explore the vast amount of unlabeled data in the world. Over the decade, graph-based SSL becomes popular in automatic image annotation due to its power of learning globally based on local similarity. However, recent studies have shown that the emergence of large-scale datasets challenges traditional methods. On the other hand, most previous works have concentrated on single-label annotation, which may not describe image contents well. To remedy the deficiencies, this paper proposes a new graph-based SSL technique with multi-label propagation, leveraging the distributed computing power of the MapReduce programming model. For high learning performance, the paper further presents both a multi-layer learning structure and a tag refinement approach, where the former unifies both visual and textual information of image data during learning, while the latter simultaneously suppresses noisy tags and emphasizes the other tags after learning. Experimental results based on a medium-scale and a large-scale image datasets show the effectiveness of the proposed methods. [Copyright &y& Elsevier]

Abstract: In this paper, inspired by the idea of overlapping rectangular region coding of binary images, we extend the SDS design, which is based on overlapping representation from binary images to gray images based on the non-symmetry and anti-packing model (NAM). A novel gray image representation is proposed by using the overlapping rectangular NAM (RNAM) and the extended Gouraud shading approach, which is called ORNAM representation. Also, we present an ORNAM representation algorithm of gray images. The encoding and the decoding of the proposed algorithm can be performed in O(n log n) time and O(n) time, respectively, where n denotes the number of pixels in a gray image. The wrong decoding problem of the hybrid matrix R for the overlapping RNAM representation of gray images is solved by using the horizontal, vertical, and isolated matrices, i.e., H, V and I, respectively, which are used to identify the vertex types. Also, we put forward four criteria of anti-packing homogeneous blocks. In addition, by redefining a codeword set for the three vertices symbols, we also propose a new coordinate data compression procedure for coding the coordinates of all non-zone elements in the three matrices H, V and I. By taking some idiomatic standard gray images in the field of image processing as typical test objects, and by comparing our proposed ORNAM representation with the conventional S-Tree Coding (STC) representation, the experimental results in this paper show that the former has higher compression ratio and less number of homogeneous blocks than the latter whereas maintaining a satisfactory image quality, and therefore it is a better method to represent gray images. [Copyright &y& Elsevier]

Abstract: In this paper, we study the problem of feature extraction for pattern classification applications. RELIEF is considered as one of the best-performed algorithms for assessing the quality of features for pattern classification. Its extension, local feature extraction (LFE), was proposed recently and was shown to outperform RELIEF. In this paper, we extend LFE to the nonlinear case, and develop a new algorithm called kernel LFE (KLFE). Compared with other feature extraction algorithms, KLFE enjoys nice properties such as low computational complexity, and high probability of identifying relevant features; this is because KLFE is a nonlinear wrapper feature extraction method and consists of solving a simple convex optimization problem. The experimental results have shown the superiority of KLFE over the existing algorithms. [Copyright &y& Elsevier]

• We present a novel discriminative model to learn similarity measurement between source domain and target domain. • We freeze part of the network layers to extract well-defined representations from source domain to target domain. • We use auxiliary images labelled by perspective-class to improve categorization performance. Fine-grained categorization is challenging due to its small inter-class and large intra-class variance. Moreover, requiring domain expertise makes fine-grained labelled data much more expensive to acquire. Existing models predominantly require extra information such as bounding box and part annotation in addition to the image category labels, which involves heavy manual labor. In this paper, we propose a novel hierarchical deep transfer learning model, based on a compression convolutional neural network. Our model transfers the learned image representation from large-scale labelled fine-grained datasets to micro fine-grained datasets, which avoids using expensive annotations and realizes visual categorization task effectively. Firstly, we introduce a cohesion domain to measure correlation degree between source domain and target domain. Secondly, the source-domain convolutional neural network is adjusted according to its metrical feedback, in order to select task-specific features that are suitable for transferring to the target domain. Finally, we make most of perspective-class labels, which are inherent attributes of fine-grained data for multi-task learning and learn all the attributes through joint learning to extract more discriminative representations. The proposed model not only economizes training time effectively and achieves high categorization accuracy, but also verifies that the inter-domain feature transition can accelerate learning and optimization. [ABSTRACT FROM AUTHOR]