Region Information Of Image Research Articles

Deep learning based fine-grained recognition technology for basketball movements

The technical essentials of basketball are very complex, in order to accomplish the identification of fine-grained basketball movements and improve the quality of basketball training, the study innovatively proposes a region screening strategy to obtain the local region information of image frames, and draws on the SlowFast network structure to design the static and dynamic detail models, and finally utilizes the 3D attention feature fusion module to complete the multi-feature relationship processing and recognition. Performance testing experiments have confirmed that the dual stream model based on region filtering has achieved a maximum improvement in average accuracy of 16.35 % and 60.36 % in the recognition of RGB images, preserving relatively complete local effective region information of RGB images. The model based on channel domain attention mechanism improves its average accuracy to over 60 %. The model recognition accuracy calculation time after dual stream fusion is reduced by about 50 %. The model based on 3D attention feature fusion module exhibits stronger robustness when the feature dimension changes. And the loss value of this model rapidly decreases and converges to the minimum loss value, with its accuracy and recall reaching 90.03 % and 88.47 % respectively, and its AUC value reaching a maximum of 0.761. The design of the study contributes to the digital development of teaching and training in basketball and enriches the theoretical body of knowledge on deep learning and action recognition.

Learning Structured Relation Embeddings for Fine-Grained Fashion Attribute Recognition

Fashion attribute recognition is a not-new topic, but rather a core task in understanding fashion from the perspective of computer vision. This paper proposes a structured relation-aware network (sRA-Net), which exploits multiple hidden relations in fashion images to enrich and achieve accurate attribute representations to boost the performance of fashion attribute recognition. Specifically, it deconstructs the features of a clothing fashion item into three levels, including low-level attribute-related image region information, mid-level attribute dependency information, and high-level clothing look information. To learn these multi-relational embeddings, we present three relation-aware attention mechanisms. The attribute attention mechanism describes the relationship among different attribute vectors through self-attention and uses the attention map to update the attribute embedding. Then, the spatial attention mechanism associates the attribute with the image features and enhances the attribute embedding by leveraging the attribute-related image region. Finally, the channel attention mechanism selects attribute-related image feature channels to obtain a more fine-grained attribute embedding. Furthermore, we introduce structure-aware embedding to constrain attribute recognition in images from a global perspective by identifying the inner structure of the clothing. Without bells and whistles, sRA-Net outperforms all state-of-the-art attribute recognition methods on two mainstream fashion attribute datasets, namely the DeepFashion-C dataset and iFashion-Attribute dataset, with over 1%-3% improvement.

Global Plus Local Jointly Regularized Support Vector Data Description for Novelty Detection.

In many practice application, the cost for acquiring abnormal data is quite expensive, thus the one-class classification (OCC) problem attracts great attention. As one of the solutions, support vector data description (SVDD) gains a continuous focus in outlier detection since it is based on the data description. For the sphere obtained by SVDD, both the center and the volume (or radius) strongly depend on the support vectors, while the support vectors are sensitive to the tradeoff parameter C. Hence, how to select this parameter is a rather challenging problem. In order to address this problem, we define several distance metrics relative to the image region in Gaussian kernel space. With the distance metrics, two probability densities relative to the global region and the local region are designed, respectively. Then, the information quantity and the information entropy are developed for regularizing the tradeoff parameter. This novel SVDD is called global plus local jointly regularized support vector data description (GL-SVDD), in which both the global region information and the local image region information jointly penalize the images as possible outliers. Finally, we use the UCI dataset and the hyperspectral data of cherry fruit to evaluate the performance of several OCC approaches. Experimental results show that GL-SVDD is encouraging.

LGST-Drop: label-guided structural dropout for spatial–temporal convolutional neural networks

Region dropout regularization strategies have proven to be highly effective at improving the generalization performance of convolutional neural networks (CNNs) in a variety of computer vision tasks including image classification, object detection, and semantic segmentation because these strategies enable models to focus on a wider range of image region information. However, for action recognition, models need to be able to extract not only useful spatial information but also important temporal and motion information, which cannot be satisfied by traditional regularization strategies. We propose a spatiotemporal dropout strategy to meet the need for regularization in spatial–temporal CNNs. We call it label guided spatial–temporal drop (LGST-Drop); it not only provides effectively structured dropout in the spatial dimension but also regularizes motion information in the temporal dimension. In addition, LGST-Drop’s mask is guided by the predicted categories of the model itself, which we called temporary labels. Extensive experiments on several standard datasets from action recognition domains show the usefulness of the proposed technique in comparison with the previous methods and theirstate-of-the-art variant algorithms.

Broad learning approach to Surrogate-Assisted Multi-Objective evolutionary fuzzy clustering algorithm based on reference points for color image segmentation

For some real-world problems, the objective function evaluation is time-consuming and computationally expensive in multi-objective evolutionary algorithms. Surrogate-assistance approaches can be used to estimate the objective function and solve the computationally expensive problem. Taking advantages of the flatted structure and incremental learning, broad learning system (BLS) has shown a great improvement of time efficiency on the premise of ensuring the performance on the classification and regression problems. In this paper, BLS is adopted to design a BLS surrogate-assisted evolutionary framework to boost the time efficiency of clustering-based image segmentation. A BLS-assisted multi-objective evolutionary fuzzy clustering algorithm with reference points (BLS-MOEFC) is proposed. Firstly, two fuzzy clustering objective functions integrating image region information are constructed as the optimized fitness functions for obtaining satisfactory segmentation quality. Secondly, in order to improve the optimization efficiency and reduce the computational time cost, a BLS surrogate model-assisted multi-objective evolutionary framework with reference points is designed to optimize the constructed objective functions. Thirdly, an adaptively updating strategy of parameters and a model update mechanism based on the non-dominated sorting are adopted to improve the prediction accuracy of the BLS surrogate model. Finally, a novel fuzzy clustering validity index integrating region information is designed to select an optimal solution from the final set of non-dominated solutions. Experimental results on Berkeley and Weizmann images show that the proposed algorithm behaves well in the segmentation performance and time cost.

Dark-Aware Network For Fine-Grained Sketch-Based Image Retrieval

Fine-grained sketch-based image retrieval (FG-SBIR) is an emerging topic in high-level computer vision. Among existing methods, edge-only information based ones are convenient to use but incompetent in distinguishing among ambiguous samples. On the other hand, even though the methods using additional color information can significantly improve the retrieval performance, they are not convenient for practical use as the increase of sketch complexity. This paper fills the gap between these two kinds of methods by proposing a novel method, namely dark-aware sketch-based image retrieval (DA-SBIR), which incorporates the dark region information of images into FG-SBIR without a sacrifice of convenience. Our model consists of two branches to process edge structure and dark region, respectively. Specifically, instead of using real color, DA-SBIR only requires some additional free-hand black sketch to represent the dark region. Besides, a Split Generative Adversarial Network is introduced to automatically split a sketch into edge-structure-only and dark-region-only sketches. Moreover, we build a new clothes dataset, SJTU-Cloth, with more ambiguous samples for FG-SBIR. Experimental results on the QMUL-Shoe dataset and our SJTU-Cloth dataset show that our approach achieves consistent improvements over state-of-the-arts. Code and dataset are available at https://github.com/y2242794082/SBIR.git.

An integrated two-stage approach for image segmentation via active contours

A novel integrated two-stage approach is proposed for image segmentation, where the edge, global and local region information of images are in turn incorporated to define the intensity fitting energy. In the first stage, the Chan-Vese model flexibly assimilates the edge indicator function in the beginning, and then the Laplace operator is introduced to regularize the level set function when minimizing the energy functional. As an edge-based and global region-based active contour, it can be inclined to rapidly produce a coarse segmentation result. In the second stage, we further segment the image by absorbing the local region fitting energy, where its initialization is acquired by the final active contour of the first stage. In addition, we present a generalized level set regularization term, which efficiently eliminates the periodically re-initialization procedure of traditional level set methods and maintains the corresponding signed distance property. Compared with the first stage, the local object details are accurately segmented in the second stage, which can acquire an accurate segmentation result. Qualitative and quantitative experimental results demonstrate the accuracy, robustness and efficiency of our approach with applications to some synthetical and real-world images.

Accurate image super-resolution using dense connections and dimension reduction network

Recently, the convolution neural network (CNN) has achieved significant performance improvements toward the image Super-Resolution (SR) problems. Yet, the existing benchmark arts exist multiple limitations, including make use of the feature information deficiently, accompany with the gradient disappearance phenomenon and have serious time consumption. The paper utilizes a newly designed fully convolutional neural network named Accurate Image Super-resolution Using Dense Connections and Dimension Reduction Network (DCDRN) to fully exploit the image features. Contextual information of image regions utilizes efficiently and accurately through uniting dense connections and cascading small filters multiple times. And such implementation can be regarded as feature extractors to fuse local and global image features. We newly introduce 1 × 1 CNNs parallelization structure in the image reconstruction section to reduce data dimensions of the previous layers, which alleviates the computational burden effectively while avoiding the context info losing. The calculation becomes more complex and the convergence becomes slower during training because of the pre-processed images. The proposed DCDRN invents a simple and effective method which processes the original image directly and the optimization of layers and filters of CNNs shorten the cost of training significantly. Experiments on benchmark datasets with different methods show that DCDRN achieves gratifying performance against state-of-the-art methods. Code is available at .

Zig-Zag Network for Semantic Segmentation of RGB-D Images.

Semantic segmentation of images requires an understanding of appearances of objects and their spatial relationships in scenes. The fully convolutional network (FCN) has been successfully applied to recognize objects' appearances, which are represented with RGB channels. Images augmented with depth channels provide more understanding of the geometric information of the scene in an image. In this paper, we present a multiple-branch neural network to utilize depth information to assist in the semantic segmentation of images. Our approach splits the image into layers according to the "scene-scale". We introduce the context-aware receptive field (CARF), which provides better control of the relevant context information of learned features. Each branch of the network is equipped with CARF to adaptively aggregate the context information of image regions, leading to a more focused domain that is easier to learn. Furthermore, we propose a new zig-zag architecture to exchange information between the feature maps at different levels, augmented by the CARFs of the backbone network and decoder network. With the flexible information propagation allowed by our zig-zag network, we enrich the context information of feature maps for the segmentation. We show that the zig-zag network achieves state-of-the-art performances on several public datasets.

Graph of Concepts for Semantic Annotation of Remotely Sensed Images based on Direct Neighbors in RAG

Image annotation is a challenging task and is widely studied in several fields such as image interpretation and retrieval. With the overwhelming volume of image data, manual annotation is no longer practical. Therefore, automatic image annotation (AIA) techniques have become a necessity where various approaches have been proposed mainly to resolve the semantic gap problem. Nevertheless, further efforts are still required in order to obtain more faithful semantic image annotations. In this paper, we propose a method to semantically annotate remote sensing (RS) images based on region adjacency graphs (RAG). Specifically, we simultaneously consider contextual, spatial and spectral information of image regions for AIA. Spectral libraries are used as a source of knowledge where several radiometric indices are computed to identify objects in the images. As a result, a graph of concepts representing objects is produced in scenes that exploit spatial and spectral attributes. Our approach is validated based on popular RS image datasets such as the Indian Pines and Jasper Ridge datasets. Promising results are reported based on the measurements of precision, recall, F1 and N + scores.

Hierarchical semantic segmentation of image scene with object labeling

Semantic segmentation of an image scene provides semantic information of image regions while less information of objects. In this paper, we propose a method of hierarchical semantic segmentation, including scene level and object level, which aims at labeling both scene regions and objects in an image. In the scene level, we use a feature-based MRF model to recognize the scene categories. The raw probability for each category is predicted via a one-vs-all classification mode. The features and raw probability of superpixels are embedded into the MRF model. With the graph-cut inference, we get the raw scene-level labeling result. In the object level, we use a constraint-based geodesic propagation to get object segmentation. The category and appearance features are utilized as the prior constraints to guide the direction of object label propagation. In this hierarchical model, the scene-level labeling and the object-level labeling have a mutual relationship, which regions and objects are optimized interactively. The experimental results on two datasets show the well performance of our method.

Automatic Detection of Optic Disc and Blood Vessel in Retinal Images using Morphological Operations and Ipachi Model

Automated detection of Optic disc and blood vessel fabrication is becoming of virtual interest for better management of diabetic disease. In this paper, we propose morphology technique and new infinite active contour model that uses hybrid region information of image to approach this problem. For optic disc detection scheme utilizes operations such as edge detection, binary threshold and morphological operation. For vessel detection we use an infinite perimeter regularize, provided by using L2 Lebesgue measure of the boundaries, allows for better detection of small oscillatory structures than the models based on length of a feature’s boundaries. The advantage of using different types of region information, Eigen based enhancement, such as the combination of image intensity information and local phase based enhancement. The local phase based enhancement map is used for preserving vessel edges while the given intensity information will give a correct feature’s segmentation.

A new image segmentation model with local statistical characters based on variance minimization

Chan–Vese (CV) model is a promising active contour model for image segmentation. However, CV model does not utilize local region information of images and thus segmentation method based on CV model cannot achieve good segmentation results for complex image with some in-homogeneity intensities. To overcome the limitation of CV model, this paper presents a new type of geometric active contour model using the strategy of variance minimization of image and introduced local statistics in the new energy formulation. The proposed model not only considers the first and second order moments of objective image statistical measurements, but also regularizes the level set function by incorporating the distance penalized energy function. The major contributions of this paper conclude two aspects. One is the new energy function based on variance minimization and another is the introduction of the local weighted averaging. In this paper, we get the local weighted averaging by the pieces smooth approximation through Gaussian convolution. Experimental results demonstrate that the proposed approach is effective in image segmentation, especially for the image with in-homogeneity intensity.

Local Minimum Energy of LBP Algorithm Concrete CT Image Segmentation

Concrete CT image segmentation is a hot civil engineering research field in recent years. An algorithm of minimizing the energy of local region is proposed to solve the problem of interaction fails to capture statistical property of natural image and to segment concrete CT image. At first, the algorithm utilizes local region information of image to construct the energy model of local region, establishes a segmentation model of local interaction region based on MRF. Then using loopy belief propagation (LBP) algorithm and other algorithms optimizes global energy. In process of optimization, local region energy is converged, and the label of local region is estimated based on MAP algorithm. Then the information of local region is transferred to the region of neighborhood. The result of experiment shows that comparing with standard LBP algorithm, the new algorithm has a better segmentation result, and efficiently restrained effect on image noise and texture for segmentation. Result of concrete CT image segmentation will simplify the following CT statistical analysis and provide an important method for reaching real meso-structure of concrete’s finite element network.

An Improved Image Segmentation Active Contour Model

The Chan-Vese (C-V) active contour model has low computational complexity, initialization and insensitive to noise advantagesand utilizes global region information of images, so it is difficult to handle images with intensity inhomogeneity. The Local binary fitting (LBF) model based on local region information has its certain advantages in mages segmentation of weak boundary or uneven greay.but , the segmentation results are very sensitive to the initial contours, In order to address this problem, this paper proposes a new active contour model with a partial differential equation, which integrates both global and local region information. Experimental results show that it has a distinctive advantage over C-V model for images with intensity inhomogeneity, and it is more efficient than LBF.

Point-pattern matching method using SURF and Shape Context

Point-pattern matching is an important topic in the fields of computer vision and pattern recognition. We present a novel point-pattern matching method based on Speeded Up Robust Feature (SURF) and Shape Context to increase the matching accuracy. In the original point-pattern matching method using SURF algorithm, incorrect matching point pairs are likely to be produced and are difficult to be eliminated only by using information of image regions around the feature points. In the proposed method, firstly, SURF bidirectional matching method is applied to match the feature points in two images preliminarily. Then Shape Context descriptors are calculated for the feature points so that the information of relative positions among the feature points can be integrated in this way. Finally, incorrect matching point pairs can be eliminated gradually by an iteration method. Experiment results show that the proposed method can eliminate incorrect matching point pairs effectively and increase the accuracy of point-pattern matching.

Information-Theoretic Active Polygons for Unsupervised Texture Segmentation

Curve evolution models used in image segmentation and based on image region information usually utilize simple statistics such as means and variances, hence can not account for higher order nature of the textural characteristics of image regions. In addition, the object delineation by active contour methods, results in a contour representation which still requires a substantial amount of data to be stored for subsequent multimedia applications such as visual information retrieval from databases. Polygonal approximations of the extracted continuous curves are required to reduce the amount of data since polygons are powerful approximators of shapes for use in later recognition stages such as shape matching and coding. The key contribution of this paper is the development of a new active contour model which nicely ties the desirable polygonal representation of an object directly to the image segmentation process. This model can robustly capture texture boundaries by way of higher-order statistics of the data and using an information-theoretic measure and with its nature of the ordinary differential equations. This new variational texture segmentation model, is unsupervised since no prior knowledge on the textural properties of image regions is used. Another contribution in this sequel is a new polygon regularizer algorithm which uses electrostatics principles. This is a global regularizer and is more consistent than a local polygon regularization in preserving local features such as corners.