Local Edge Features Research Articles

Saliency and edge features-guided end-to-end network for salient object detection

The rapid development of the Vision Transformer backbones has enabled the capture of feature information with global dependencies, leading to excellent performance in salient object detection tasks. However, it fails to adequately emphasize fine local features of edges, resulting in coarse and blurry edges in the final output. Therefore, this paper proposes a set prediction method for salient object detection. The approach enables the model to simultaneously consider both saliency (salient object) and edge features, achieving an end-to-end edge feature fusion. There is no need to design multiple complex branch structures and multiple training as with other methods. The model integrates random edge neighborhood sampling to enhance the recognition accuracy of local edge features in images. This approach addresses the weak perception of local features by Transformers and the issue encountered during actual training, where edge pixels typically occupy a much smaller proportion of the image compared to the background, resulting in insufficient learning of edge features by the model. The proposed end-to-end model in this paper fuses multiple features, including edge and salient objects. They are extracted within a unified framework while simultaneously outputting edge and salient object maps. Experimental results on six public datasets show that the proposed method significantly improves model performance benchmarks for detecting salient objects.

Global-local manifold embedding broad graph convolutional network for hyperspectral image classification

Graph convolutional neural networks (GCNs) with domain-specific feature aggregation capabilities have unique advantages in hyperspectral image (HSI) classification. However, current GCN-based approaches frequently encounter the issue of node characteristics being over-smoothed while aggregating in higher-order domains. Furthermore, GCN linear classifiers focus solely on sample separability and ignore the potential manifold information of graph features, resulting in a failure to fully investigate extracted features. To address these problems, we propose a global-local manifold embedding broad graph convolutional network (GLMBG) for HSI classification. In GLMBG, we designed two modules from feature extraction and classification perspectives: The graph convolutional edge feature fusion extractor (GEFF) and the broad classifier of global-local manifold embedding (BGLME). GEFF is designed to learn graph node and local edge features from HSI through GCN and recursive filtering, combining them in a weighted manner to construct fused graph features. BGLME is designed to replace traditional linear classifiers with broad learning classifiers through manifold regularized embedding, fully utilizing the global and local manifold discriminant information of graph node features. The combination of GEFF and BGLME effectively reduces over-smoothing of graph node features while maximizing the utilization of manifold discriminant information, hence improving model feature discriminative ability. Experimental evaluations of three commonly used hyperspectral datasets show that our method surpasses state-of-the-art methods.

Learning Graph Representations Through Learning and Propagating Edge Features.

Graph convolutional networks have achieved considerable success in various graph domain tasks. Recently, numerous types of graph convolutional networks have been developed. A typical rule for learning a node's feature in these graph convolutional networks is to aggregate node features from the node's local neighborhood. However, in these models, the interrelation information between adjacent nodes is not well-considered. This information could be helpful to learn improved node embeddings. In this article, we present a graph representation learning framework that generates node embeddings through learning and propagating edge features. Instead of aggregating node features from a local neighborhood, we learn a feature for each edge and update a node's representation by aggregating local edge features. The edge feature is learned from the concatenation of the edge's starting node feature, the input edge feature, and the edge's end node feature. Unlike node feature propagation-based graph networks, our model propagates different features from a node to its neighbors. In addition, we learn an attention vector for each edge in aggregation, enabling the model to focus on important information in each feature dimension. By learning and aggregating edge features, the interrelation between a node and its neighboring nodes is integrated in the aggregated feature, which helps learn improved node embeddings in graph representation learning. Our model is evaluated on graph classification, node classification, graph regression, and multitask binary graph classification on eight popular datasets. The experimental results demonstrate that our model achieves improved performance compared with a wide variety of baseline models.

Local geometric edge features based registration for textureless object in augmented reality assisted assembly

Image-based methods have been widely used in augmented reality (AR) assistant assembly systems. However, due to the lack of sufficient texture information on the surface of assembly part, traditional image feature matching methods still face challenges. This paper proposes a coarse-to-fine AR registration method for textureless assembly part. In the first stage, a new feature matching method which is called line neighborhood edge descriptor (LNED) is presented to find the coarse camera pose from textureless image. The LNED take the contour line of assembly part as the description object, and use local geometric edge of assembly part to describe the contour line. During the image matching, the binary encoding is used to reduce the computational consumption for LNED. In the second stage, spatial points in the CAD model of assembly part are reverse projected to the textureless image based on the coarse camera pose. And the bundle adjustment method based on the edge distance of the textureless image is adopted to iteratively calculate the precise camera pose. In the experimental evaluation, the proposed registration method shows high accuracy and fast speed in comparison with conventional registration methods, which demonstrates that our method can effectively solve the problem of AR registration for textureless assembly part.

Research on Image Stitching Algorithm Based on Point-Line Consistency and Local Edge Feature Constraints.

Image stitching aims to synthesize a wider and more informative whole image, which has been widely used in various fields. This study focuses on improving the accuracy of image mosaic and proposes an image mosaic method based on local edge contour matching constraints. Because the accuracy and quantity of feature matching have a direct influence on the stitching result, it often leads to wrong image warpage model estimation when feature points are difficult to detect and match errors are easy to occur. To address this issue, the geometric invariance is used to expand the number of feature matching points, thus enriching the matching information. Based on Canny edge detection, significant local edge contour features are constructed through operations such as structure separation and edge contour merging to improve the image registration effect. The method also introduces the spatial variation warping method to ensure the local alignment of the overlapping area, maintains the line structure in the image without bending by the constraints of short and long lines, and eliminates the distortion of the non-overlapping area by the global line-guided warping method. The method proposed in this paper is compared with other research through experimental comparisons on multiple datasets, and excellent stitching results are obtained.

Retracted: Fast Extraction Algorithm for Local Edge Features of Super-Resolution Image

Retracted: Fast Extraction Algorithm for Local Edge Features of Super-Resolution Image

Structural Smoothing Low-Rank Matrix Restoration Based on Sparse Coding and Dual-Weighted Model.

Group sparse coding (GSC) uses the non-local similarity of images as constraints, which can fully exploit the structure and group sparse features of images. However, it only imposes the sparsity on the group coefficients, which limits the effectiveness of reconstructing real images. Low-rank regularized group sparse coding (LR-GSC) reduces this gap by imposing low-rankness on the group sparse coefficients. However, due to the use of non-local similarity, the edges and details of the images are over-smoothed, resulting in the blocking artifact of the images. In this paper, we propose a low-rank matrix restoration model based on sparse coding and dual weighting. In addition, total variation (TV) regularization is integrated into the proposed model to maintain local structure smoothness and edge features. Finally, to solve the problem of the proposed optimization, an optimization method is developed based on the alternating direction method. Extensive experimental results show that the proposed SDWLR-GSC algorithm outperforms state-of-the-art algorithms for image restoration when the images have large and sparse noise, such as salt and pepper noise.

Learning a Metric for Multimodal Medical Image Registration without Supervision Based on Cycle Constraints.

Deep learning based medical image registration remains very difficult and often fails to improve over its classical counterparts where comprehensive supervision is not available, in particular for large transformations—including rigid alignment. The use of unsupervised, metric-based registration networks has become popular, but so far no universally applicable similarity metric is available for multimodal medical registration, requiring a trade-off between local contrast-invariant edge features or more global statistical metrics. In this work, we aim to improve over the use of handcrafted metric-based losses. We propose to use synthetic three-way (triangular) cycles that for each pair of images comprise two multimodal transformations to be estimated and one known synthetic monomodal transform. Additionally, we present a robust method for estimating large rigid transformations that is differentiable in end-to-end learning. By minimising the cycle discrepancy and adapting the synthetic transformation to be close to the real geometric difference of the image pairs during training, we successfully tackle intra-patient abdominal CT-MRI registration and reach performance on par with state-of-the-art metric-supervision and classic methods. Cyclic constraints enable the learning of cross-modality features that excel at accurate anatomical alignment of abdominal CT and MRI scans.

Fast Extraction Algorithm for Local Edge Features of Super-Resolution Image

Image super-resolution is getting popularity these days in diverse fields, such as medical applications and industrial applications. The accuracy is imperative on image super-resolution. The traditional approaches for local edge feature point extraction algorithms are merely based on edge points for super-resolution images. The traditional algorithms are used to calculate the geometric center of gravity of the edge line when it is near, resulting in a low feature recall rate and unreliable results. In order to overcome these problems of lower accuracy in the existing system, an attempt is made in this research work to propose a new fast extraction algorithm for local edge features of super-resolution images. This paper primarily focuses on the super-resolution image reconstruction model, which is utilized to extract the super-resolution image. The edge contour of the super-resolution image feature is extracted based on the Chamfer distance function. Then, the geometric center of gravity of the closed edge line and the nonclosed edge line are calculated. The algorithm emphasizes on polarizing the edge points with the center of gravity to determine the local extreme points of the upper edge of the amplitude-diameter curve and to determine the feature points of the edges of the super-resolution image. The experimental results show that the proposed algorithm consumes 0.02 seconds to extract the local edge features of super-resolution images with an accuracy of up to 96.3%. The experimental results show that our proposed algorithm is an efficient method for the extraction of local edge features from the super-resolution images.

EMRA-Net: A Pixel-Wise Network Fusing Local and Global Features for Tiny and Low-Contrast Surface Defect Detection

The problem of tiny and low-contrast surface defect detection is a nontrivial one. To solve the problems, this article proposes an edge and multi-scale reverse attention network (EMRA-Net), of which includes feature extraction and feature fusion. In the process feature extraction, the global dynamic convolution features, global dynamic multi-scale fusion (MSF) feature, and local pyramid edge feature are obtained through the pre-training backbone Resnet 34, the fresh MSF module, and the innovative pyramid edge module, respectively. In the process of feature fusion, these features are blended by a new self-learning scale module and a novel spatial channel domain reverse attention (SCRA) module step by step. The experimental results of five widely used datasets show that the EMRA-Net outperforms the existing methods. In addition, the mean intersection of union (mIoU)<xref ref-type="fn" rid="fn1">¹</xref><xref ref-type="fn" rid="fn2">²</xref> on the printed circuit board (PCB) industry dataset reaches 95.31&#x0025;. Moreover, the results of EMRA-Net indicated that the local edge feature can improve the performance of the defect detection network. The EMRA-Net has great potential in the application in the detection of tiny and low-contrast defects.

Pedestrian Detection with EDGE Features of Color Image and HOG on Depth Images

The existing pedestrian detection algorithms are not robust in the case of noise, obstruction and illumination change. To solve the problem, we propose a pedestrian detection algorithm combining the edge features of color image with the features of Histogram of Oriented Gradient on Depth image (referred to as the HOD features). The algorithm describes overall structural features of pedestrians by using shearlet transform to extract their edge features from color images, and obtains local edge features of corresponding depth images by generating HOD features. The overall structural features and local edge features are combined to form new feature descriptors to train a SVM (support vector machine) classifier. Due to the full integration of the two types of features, the algorithm shows significant advantages in pedestrian detection in the case of interfering factors such as noise, obstruction, illumination, and similar colors. The experimental results show that the detection accuracy rate of this algorithm is 15% higher than that of other algorithms when the false-positive rate is 0.1.

LEFT: LOCAL EDGE FEATURES TRANSFORM

To detect point correspondence between images or 3D scenes, local texture descriptors, such as SIFT (Scale Invariant Feature Transform), SURF (Speeded-Up Robust Features), BRIEF (Binary Robust Independent Elementary Features), and others, are usually used. Formally they provide invariance to image rotation and scale, but this properties are achieved only approximately due to discrete number of evaluable orientations and scales stored into the descriptor. Feature points preferable for such descriptors usually are not belong to actual object boundaries into 3D scenes and so are hard to be used into apipolar relationships. At the same time, linking the feature point to large-scale lines and edges is preferable for SLAM (Simultaneous Localization And Mapping) tasks, because their appearance are the most resistible to daily, seasonal and weather variations.In this paper, original feature points descriptor LEFT (Local Edge Features Transform) for edge images are proposed. LEFT accumulate directions and contrasts of alternative strait segments tangent to lines and edges in the vicinity of feature points. Due to this structure, mutual orientation of LEFT descriptors are evaluated and taken into account directly at the stage of their comparison. LEFT descriptors adapt to the shape of contours in the vicinity of feature points, so they can be used to analyze local and global geometric distortions of a various nature. The article presents the results of comparative testing of LEFT and common texture-based descriptors and considers alternative ways of representing them in a computer vision system.

Multi-Scale Point-Wise Convolutional Neural Networks for 3D Object Segmentation From LiDAR Point Clouds in Large-Scale Environments

Although significant improvement has been achieved in fully autonomous driving and semantic high-definition map (HD) domains, most of the existing 3D point cloud segmentation methods cannot provide high representativeness and remarkable robustness. The principally increasing challenges remain in completely and efficiently extracting high-level 3D point cloud features, specifically in large-scale road environments. This paper provides an end-to-end feature extraction framework for 3D point cloud segmentation by using dynamic point-wise convolutional operations in multiple scales. Compared to existing point cloud segmentation methods that are commonly based on traditional convolutional neural networks (CNNs), our proposed method is less sensitive to data distribution and computational powers. This framework mainly includes four modules. Module I is first designed to construct a revised 3D point-wise convolutional operation. Then, a U-shaped downsampling-upsampling architecture is proposed to leverage both global and local features in multiple scales in Module II. Next, in Module III, high-level local edge features in 3D point neighborhoods are further extracted by using an adaptive graph convolutional neural network based on the K-Nearest Neighbor (KNN) algorithm. Finally, in Module IV, a conditional random field (CRF) algorithm is developed for postprocessing and segmentation result refinement. The proposed method was evaluated on three large-scale LiDAR point cloud datasets in both urban and indoor environments. The experimental results acquired by using different point cloud scenarios indicate our method can achieve state-of-the-art semantic segmentation performance in feature representativeness, segmentation accuracy, and technical robustness.

Object Contour Tracking Algorithm of Infrared Image Under Complex Background

Traditional image contour tracking algorithm has low tracking accuracy. To solve this problem, an object contour tracking algorithm based on local significant edge features in complex background is proposed. In the algorithm, the projective invariant is firstly introduced, to construct the geometric information descriptor between the edge positions of the infrared image, and set up the histogram of the feature number of each target contour. The geometric similarity between the features is measured by the pasteurized coefficient, the edge features of the neighbourhood around the object contour are established, and the object contour with significant features in the edge of the image is searched. Combining Shape-context operator with edge feature, the feature description vector can be formed, and Euclidean distance is defined to track measurement function. Using this function, the selected object contour is tracked preliminarily. The random consistency checking algorithm is used to eliminate the false tracking feature points and obtain the best tracking value of the object contour, thus the infrared image’s object contour tracking is carried out in the complex background. Experimental simulation shows that the proposed algorithm has high tracking accuracy and effectively improves the quality of infrared image analysis.

Robust building boundary extraction method based on dual-scale feature classification and decision fusion with satellite image

ABSTRACT Building edge or boundary extraction is always one of the most important issues for remote sensing application. In order to accurately extract the edges or boundary of a building, there are usually two problems. Firstly, strong interference edges from backgrounds such as road, trees and others cannot be avoided. Secondly, it is more difficult for the lower contrast building edges to be detected. In order to address these two problems to a certain extent, a Robust Building Boundary Extraction method (DS-RBBE) is proposed in this paper, which is based on dual-scale sparse SVM classification and decision fusion. First, training samples are automatically selected by employing prior knowledge of main direction and linearity information. Next, a sparse SVM classifier is trained using the dual-scale local edge features of the training samples. And then, the trained sparse SVM is employed to classify all extracted edges. Finally, a dual-scale decision fusion strategy is performed for final building boundary extraction. In order to evaluate the performance of proposed method, the experiments are conducted on different types of build regions. The results are shown that the proposed method can efficiently extract the building edges and boundaries.

Bayesian genetic programming for edge detection

In edge detection, designing new techniques to combine local features is expected to improve detection performance. However, how to effectively design combination techniques remains an open issue. In this study, an automatic design approach is proposed to combine local edge features using Bayesian programs (models) evolved by genetic programming (GP). Multivariate density is used to estimate prior probabilities for edge points and non-edge points. Bayesian programs evolved by GP are used to construct composite features after estimating the relevant multivariate density. The results show that GP has the ability to effectively evolve Bayesian programs. These evolved programs have higher detection accuracy than the combination of local features by directly using the multivariate density (of these local features) in a simple Bayesian model. From evolved Bayesian programs, the proposed GP system has potential to effectively select features to construct Bayesian programs for performance improvement.

Adaptive modularity maximization via edge weighting scheme

Modularity maximization is one of the state-of-the-art methods for community detection that has gained popularity in the last decade. Yet it suffers from the resolution limit problem by preferring under certain conditions large communities over small ones. To solve this problem, we propose to expand the meaning of the edges that are currently used to indicate propensity of nodes for sharing the same community. In our approach this is the role of edges with positive weights while edges with negative weights indicate aversion for putting their end-nodes into one community. We also present a novel regression model which assigns weights to the edges of a graph according to their local topological features to enhance the accuracy of modularity maximization algorithms. We construct artificial graphs based on the parameters sampled from a given unweighted network and train the regression model on ground truth communities of these artificial graphs in a supervised fashion. The extraction of local topological edge features can be done in linear time, making this process efficient. Experimental results on real and synthetic networks show that the state-of-the-art community detection algorithms improve their performance significantly by finding communities in the weighted graphs produced by our model.

Weighted Level Set Evolution Based on Local Edge Features for Medical Image Segmentation

Level set methods have been widely used to implement active contours for image segmentation applications due to their good boundary detection accuracy. In the context of medical image segmentation, weak edges and inhomogeneities remain important issues that may hinder the accuracy of any segmentation method based on active contours implemented using level set methods. This paper proposes a method based on active contours implemented using level set methods for segmentation of such medical images. The proposed method uses a level set evolution that is based on the minimization of an objective energy functional whose energy terms are weighted according to their relative importance in detecting boundaries. This relative importance is computed based on local edge features collected from the adjacent region located inside and outside of the evolving contour. The local edge features employed are the edge intensity and the degree of alignment between the image's gradient vector flow field and the evolving contour's normal. We evaluate the proposed method for segmentation of various regions in real MRI and CT slices, X-ray images, and ultra sound images. Evaluation results confirm the advantage of weighting energy forces using local edge features to reduce leakage. These results also show that the proposed method leads to more accurate boundary detection results than state-of-the-art edge-based level set segmentation methods, particularly around weak edges.

Edge feature based approach for object recognition

We address the problem of recognizing the object with distinctive edge features. For this purpose, a recognition approach based on local edge features is presented. First the edge features are detected in each image, and then its descriptor is computed to find the match features. Each match will give a vote with location, scale and orientation of the object. The recognition result can be found in the densest position in the vote space. Experimental results show that the presented method is robust and effective to the object with distinctive edge features.

Face sketch-photo recognition using local gradient checksum: LGCS

A new approach for matching of face sketch images with face photo images and vice versa has been presented here. For the extraction of local edge features from both the sketch and photo images, a new local feature called local gradient checksum (LGCS) has been developed. LGCS is a modality reduction local edge feature on gradient domain. It is calculated as the summation of four pairs of gradient differences between two local pixels that are at 180° with each other. The Euclidean distance between query sketch and gallery of photos are measured depending on extracted LGCS features. To further improve the result, a multi-scale LGCS is proposed. A rank-1 accuracy of 100 % is achieved in a gallery of 606 photos consisting of CUHK, AR, and XM2VTS face dataset. The proposed face sketch-photo recognition system requires neither learning procedures nor training data. Further, the experiment is extended to test the robustness of the proposed algorithm on blurred, noisy and disguised sketches, as well as photos. Under those situations also, LGCS has outperformed center-symmetric local binary pattern, directional local extrema pattern and weber local descriptor feature extraction techniques.