Edge Strength Map Research Articles

M2GF: Multi-Scale and Multi-Directional Gabor Filters for Image Edge Detection

An image edge detection algorithm using multi-directional and multi-scale Gabor filters is proposed in this paper. The main merit of this method is that high edge detection accuracy can be obtained while maintaining noise robustness. The approach proposed in this paper consists of three procedures: firstly, the transformation to the CIE L*a*b* color space, which has a wide shading area and uniform distribution; secondly, under different scales, the edge feature information of the image is extracted from several different directions by Gabor filters, and a new edge strength map is obtained by feature fusion; thirdly, the new fused edge strength map is enhanced with local features, and a noise-resistant image edge detector is obtained under a novel hysteresis threshold calculation. The experiments illustrate that, compared to the methods involved, the designed edge detector outperforms by about 2% to 4%, and also shows competitive performance regarding the ability to handle noise.

SAR Edge Detection Using Weighted Directional Bhattacharyya Coefficients

In this letter, an edge detector using weighted directional Bhattacharyya coefficients (WDBCs) is proposed to improve the edge detection performance on real synthetic aperture radar (SAR) images. The Bhattacharyya coefficient (BC) is a similarity measure that considers the grayscale distribution of pixels around edges and gives a better description of textured and nonuniform regions than the ratio of averages (ROAs). However, in addition to the grayscale distribution, the spatial distribution of pixels around the edges also has a significant impact on the edge strength. To consider both grayscale and spatial distribution, the weighted histograms are computed by Gaussian-Gamma-shaped (GGS) bi-windows to obtain WDBCs in eight directions. Then the edge strength map (ESM) and edge direction map (EDM) are defined by WDBCs. The edge detector can be obtained after non-maximum suppression and hysteresis thresholding. Experimental results on real SAR images compared with five existing detectors show the effectiveness of the proposed detector.

Hierarchical Superpixel Segmentation for PolSAR Images Based on the Boruvka Algorithm

Superpixel segmentation for polarimetric synthetic aperture radar (PolSAR) images plays a key role in remote-sensing tasks, such as ship detection and land-cover classification. However, the existing methods cannot directly generate multi-scale superpixels in a hierarchical style and they will take a long time when multi-scale segmentation is executed separately. In this article, we propose an effective and accurate hierarchical superpixel segmentation method, by introducing a minimum spanning tree (MST) algorithm called the Boruvka algorithm. To accurately measure the difference between neighboring pixels, we obtain the scattering mechanism information derived from the model-based refined 5-component decomposition (RFCD) and construct a comprehensive dissimilarity measure. In addition, the edge strength map and homogeneity measurement are considered to make use of the structural and spatial distribution information in the PolSAR image. On this basis, we can generate superpixels using the distance metric along with the MST framework. The proposed method can maintain good segmentation accuracy at multiple scales, and it generates superpixels in real time. According to the experimental results on the ESAR and AIRSAR datasets, our method is faster than the current state-of-the-art algorithms and preserves somewhat more image details in different segmentation scales.

Region-Level SAR Image Segmentation Based on Edge Feature and Label Assistance

This paper proposes a novel segmentation algorithm for synthetic aperture radar (SAR) images. The algorithm performs region-level segmentation based on edge feature and label assistance (REFLA). It demonstrates improved performance in terms of segmentation accuracy while better preserving image edges. Firstly, an edge detection scheme is implemented, which fuses information from two advanced edge detection methods, thereby obtaining a more precise edge strength map (ESM). Secondly, a Canny algorithm is performed to divide the SAR image into edge regions and homogeneous regions, and different smoothing templates are selected according to pixel positions. Therefore, an anisotropic smoothing on the SAR image can be achieved, aiming at suppressing the noise within targets while also accurately maintaining the target boundaries. Thirdly, K-means clustering is applied on the smoothed result, to generate an initial set of labels. Using ESM and the initial labels as inputs, a watershed transformation and a majority voting strategy are employed to realize an initial segmentation at the region level. Finally, a label-aided region merging (LaRM) strategy is used to correctly segment the wrongly labeled regions, to give the final segmentation result. The LaRM, with merging rules based on label rather than gray characteristics, can avoid the need for calculating a large number of complex formulae, thus accelerating the region merging. Results are presented of experiments, on both simulated and real SAR images, in which the proposed REFLA method is compared against six state-of-the-art algorithms from the literature. REFLA achieves higher accuracy, while better retaining the image edges.

Multiscale Anisotropic Morphological Directional Derivatives for Noise-Robust Image Edge Detection

Different types of noise interference lead to low accuracy of image edge detection and severe loss of feature extraction details. A new noise-robust edge detection method is proposed, which uses a set of multiscale anisotropic morphological directional derivatives to extract the edge map of an input image. The main advantage of the method is that high edge resolution is maintained while reducing noise interference. The following five parts form the whole framework of this paper. First, multiscale anisotropic morphologic directional derivatives (MSAMDDs) are proposed to filter and obtain the local gray value of the image. Second, the edge strength map (ESM) is extracted by using spatial matching filters. In the third stage, multiscale edge direction maps (EDMs) based on the directional matched filters are fused, and the new EDM is constructed. Fourth, edge contours are obtained by embedding the ESM and the EDM into the standard route of Canny detection. Finally, the precision-recall curve and Pratt’s figure of merit (FOM) are used to evaluate the proposed method against eight state-of-the-art methods on three data sets. The experimental results show that the proposed method can perform better for noise-free (F-measure value of 0.776) and Gaussian noise (FOM value of 95.75%) and attains the best performance in impulse noise images (highest FOM value of 98.90%).

Color edge detection by learning classification network with anisotropic directional derivative matrices

In this paper, a neural network-based color edge detector is constructed by learning a classifier using anisotropic directional derivative (ANDD) matrices of a color image as input. The training stage on a color edge dataset with ground truth (GT) edges includes calculation of ANDD matrices, generation of feature matrices, and training a classifier. For each training image, a set of ANDD matrices are calculated from the ANDDs with different parameter setups for training and from which a set of the color edge strength maps (CESMs) are extracted by the singular vector decomposition. The CESMs and the GTs on edges of the image are combined into a feature matrix for training. Using the feature matrices of all the training images as input, a classification neural network is trained and it outputs the probability of a pixel to be an edge pixel. In the detection stage, for a color image, its ANDD matrices, CESMs, and the color edge direction maps (CEDMs) are first computed and then the CESMs are input into the classification neural network to obtain the edge probability map (EPM) of the image. Finally, the non-maximum suppression and hysteresis thresholding are applied to the EPM and CEDMs to generate the binary edge map. The proposed detector attains better performance than the existing gradient-based detectors and is competitive with learning-based detectors on three commonly-used color image datasets for edge and contour detection.

SAR image segmentation with parallel region merging

In this paper, a parallel region merging strategy is proposed for partitioning Synthetic Aperture Radar (SAR) images into several disjoint regions, based on the region adjacency graph (RAG) of an initial partition and the nearest neighbor graph (NNG) produced from the RAG. Developed from the multi-direction ratio edge detector, a multi-scale-multi-direction (MSMD) one is used to extract edge strength map (ESM) of an initial SAR image, feeded into watershed transform to generate an initial partition result of the initial SAR image. Considering local image properties, which makes the generated NNG center around bi-node circles situated in interiors of homogeneous regions, many of which are independently located in different homogeneous regions, the predication of the parallelizability for bi-node circles is proposed to make the proposed parallel region merging strategy. The proposed parallel merging strategy simultaneously merges bi-node circles far away from boundaries of regions, characterized by the length of path from a node to the bi-node circle in the NNG. The performance of the proposed parallel merging strategy is analyzed theoretically and experimentally, and our experiments show that the proposed method outweighs other compared methods.

Refined extraction of buildings with the semantic edge-assisted approach from very high-resolution remotely sensed imagery

ABSTRACT Building extraction from very high-resolution (VHR) remotely sensed imagery has been an area of increased interest. One of the main purposes of building extraction is to generate polygonal representations of buildings and identify additional engineering applications. However, the complex backgrounds and defects of target images result in incomplete and false edge extraction, which severely reduces the extraction accuracy. To solve these problems, this paper proposes a refined building extraction method based on the semantic edge-assisted approach from VHR remotely sensed imagery. Object and edge detection models are trained to obtain bounding boxes and the edge strength map, respectively, and then the object detection results are used as constraints to refine the edge strength map and repair any unclosed boundaries. To this end, we propose an incomplete boundary repair algorithm for repairing unclosed boundaries. The Douglas–Peucker (D-P) algorithm is applied to simplify boundaries as a series of points and then further simplifies these points to regularize building boundaries and finally determines the repair lines that conform to the rule of boundary variation. The experimental results indicate that the proposed building extraction method and algorithm can obtain a complete and refined polygon boundary of the target building, which makes the approach very convenient in practical applications.

Multi-Scale Anisotropic Gaussian Kernels for Image Edge Detection

In this paper, a new edge detection method is proposed where multi-scale anisotropic Gaussian kernels (AGKs) are used to obtain an edge map from an input image. The main advantage of the proposed method is that high edge detection accuracy and edge resolution are attained while maintaining good noise robustness. The proposed method consists of three aspects: First, anisotropic Gaussian directional derivatives (AGDDs) are derived from the AGKs which are used to acquire local intensity variation from an input image with multiple scales. Second, multi-scale AGDD based edge strength maps (ESMs) are fused into a new ESM with high edge resolution and little edge stretch effect which has the ability to solve the contradiction issue between noise robustness and accurate edge extraction. Third, the fused ESM is embedded into the framework of Canny detection for obtaining edge contours. Finally, the criteria on precision-recall curve, detection accuracy, and noise robustness are used to evaluate the proposed detector against four state-of-the-art methods. The experimental results show that our proposed detector outperforms all the other tested edge detection methods.

Color Edge Detection Using the Normalization Anisotropic Gaussian Kernel and Multichannel Fusion

Color edge detection is a key technique in image processing for vision engineering. In this paper, a new edge detector based on normalized Anisotropic Gaussian Directional Derivative and Multi-channel Gradient Matrix Fusion is proposed. Firstly, the color image is decomposed into six components in the RGB model and the HSV model, respectively. The gradient amplitude of the image edge is emphasized by Contrast Limited Adaptive Histogram Equalization (CLAHE). A normalized Anisotropic Gaussian Derivative is constructed by Multi-direction ANGK to extract the edge strength map of original color image. Finally, Singular Value Decomposition (SVD) was adopted to fuse each channel component in combination with a Multi-channel Morphological Gradient Derivative Matrix to improve the accuracy of edge detection. The proposed detector is compared with three state-of-art edge detectors with the Berkeley dataset (BSDS500) as the database. The results show that the proposed algorithm is more prominent in the performance of noise robustness and edge detection resolution.

Improved ROEWA SAR Image Edge Detector Based on Curvilinear Structures Extraction

By introducing curvilinear structures extraction (CSE) instead of watershed algorithm (WA) or nonmaximum suppression (NMS) to edge strength map (ESM), an improved ratio of exponentially weighted averages (ROEWA) edge detector with better capacity for weak edges detection is proposed to extract smooth edges and edge direction of synthetic aperture radar (SAR) images. Using the ROEWA, the ESM is calculated. Then the CSE algorithm is employed to extracted edges, by acquiring eigenvectors and eigenvalues of the Hessian matrix, the improved ESM (IESM) is obtained, which ensures the good weak edge detection capacity and smoothness of edges. Experimental results on simulated and real SAR images show that the improved ROEWA based on CSE attains better performance than the one using WA or NMS.

Noise-robust color edge detection using anisotropic morphological directional derivative matrix

In this paper, a color edge detector using the anisotropic morphological directional derivatives (AMDDs) is presented to detect edges in color images corrupted by Gaussian or impulsive noise. The AMDD matrix, robust to impulsive noise owing to the underlying morphological operators, is constructed to represent edge information at each pixel of a color image. The color edge strength map and color edge direction map of a color image are extracted by spatial and directional matched filtering and singular value decomposition of the AMDD matrices. Embedding them in the route of the Canny detector yields a noise-robust color edge detector. Moreover, a color image database with groundtruths (GTs) of edges are built. The GT of a color image is generated in three steps. First, the contours and results of multiple color edge detectors are fused into a candidate edge map (CEM). Next, the CEM, the original image, and a special software for edge modification are sent to twenty experienced observers to modify the CEM. Finally, their results are used to yield the edge pixels, non-edge pixels, and don't care regions in the GT by the voting rule. The proposed detector is compared with existing color edge detectors on the database.

Contour detection based on anisotropic edge strength and hierarchical superpixel contrast

Contour detection is a fundamental problem in computer vision, yet existing methods usually suffer from the interference of noise and textures. To address this problem, we present an unsupervised contour detection method based on anisotropic edge strength and hierarchical superpixel contrast. The anisotropic edge strength is obtained through the first derivative of anisotropic Gaussian kernels which incorporates an adaptive anisotropy factor. The anisotropic kernel improves the robustness to noise, while the adaptive anisotropic factor attenuates the anisotropy stretch effect. Using a method based on region merging, we obtain a hierarchical set of superpixel maps and thus compute superpixel contrast maps at different hierarchy levels. Consequently, the contour strength map is obtained by multiplying the anisotropic edge strength map by the average of the hierarchical superpixel contrast maps. Experimental results on two publicly available datasets validate the superiority of the proposed method over the competing methods. On the Berkeley Segmentation Dataset & Benchmark 300 and the Berkeley Segmentation Dataset & Benchmark 500, our method obtains (optimal dataset scale) F-measure values of 0.63 and 0.67, respectively, an improvement of at least 0.06 over the competing methods.

Adaptive Superpixel Generation for SAR Images With Linear Feature Clustering and Edge Constraint

Due to the speckle noise and complex geometric distortions within SAR images, it is still a challenge to develop a stable method that can produce superpixels with both high boundary adherence and visual compactness with low computational costs at the same time. In this paper, we propose an adaptive superpixel generation approach with linear feature clustering and edge constraint for synthetic aperture radar (SAR) images, which consists of three stages. First, the local gradient ratio pattern of each pixel in SAR imagery is extracted as features, which was previously proposed by us for SAR target recognition and has been proven to be insensitive to speckle noise. Second, we propose to use the feature-ratio-based edge detector with Gauss-shaped window instead of the traditional rectangle-shaped window to obtain the edge strength map and final edges for SAR images. Finally, a modified normalized cut (Ncut)-based superpixel generation strategy is adopted using a distance metric that simultaneously measures both the feature similarity and space proximity. In this strategy, we approximate the similarity measure through a positive semidefinite kernel function rather than directly using the traditional eigen-based algorithm. Therefore, the objective functions of weighted local K- means and Ncuts can achieve the same optimum point by appropriately weighting each point in this feature space, which greatly reduces the computation cost. During the linear feature clustering, the coefficient of variation is used to automatically determine the tradeoff factor between the feature similarity and space proximity, which helps change the superpixel shape and size adaptively according to the image homogeneity. Furthermore, the edge information is also introduced to constrain the clustering for the sake of high boundary adherence. By bridging the local K-means clustering and Ncuts, as well as the benefits of edge constraint, our method not only produces superpixels with good boundary adherence but also captures the global image structure information. Experimental results with simulated and real SAR images demonstrate the effectiveness of our proposed method, which performs better than other state-of-the-art algorithms.

A Coarse-to-Fine Registration Strategy for Multi-Sensor Images with Large Resolution Differences

Automatic image registration for multi-sensors has always been an important task for remote sensing applications. However, registration for images with large resolution differences has not been fully considered. A coarse-to-fine registration strategy for images with large differences in resolution is presented. The strategy consists of three phases. First, the feature-base registration method is applied on the resampled sensed image and the reference image. Edge point features acquired from the edge strength map (ESM) of the images are used to pre-register two images quickly and robustly. Second, normalized mutual information-based registration is applied on the two images for more accurate transformation parameters. Third, the final transform parameters are acquired through direct registration between the original high- and low-resolution images. Ant colony optimization (ACO) for continuous domain is adopted to optimize the similarity metrics throughout the three phases. The proposed method has been tested on image pairs with different resolution ratios from different sensors, including satellite and aerial sensors. Control points (CPs) extracted from the images are used to calculate the registration accuracy of the proposed method and other state-of-the-art methods. The feature-based preregistration validation experiment shows that the proposed method effectively narrows the value range of registration parameters. The registration results indicate that the proposed method performs the best and achieves sub-pixel registration accuracy of images with resolution differences from 1 to 50 times.

SAR Image Segmentation Using Hierarchical Region Merging With Orientated Edge Strength Weighted Kuiper’s Distance

In this paper, a hierarchical region merging method is proposed for partitioning synthetic aperture radar (SAR) image into un-overlapping scene area, such as forest regions, urban regions, agricultural regions, and so on. The proposed method mainly consists of two steps: initial over-segmentation and hierarchical regions merging. The over-segmentation uses the watershed transform to the thresholded Bhattacharyya-coefficient-based edge strength map (BESM), and the hierarchical regions merging applies a new region merging cost weighted by a gradually increasing orientated edge strength penalty. There is a defect that the ratio-based edge detector widely used in homogeneous SAR image fails to distinguish the transitions between uniform and texture regions in high spatial resolution SAR image, and yields an initial over-segmentation result with some regions straddling multiple uniform or texture areas. To overcome this, the Bhattacharyya coefficient is used to replace the ratio-based edge detector for extracting the ESM of a SAR image by using a bi-rectangle-window configuration. Multi-scale windows are utilized to capture additional edge information. A new region merging cost is proposed based on the Kuiper’s distance, weighted by a new gradually increasing orientated edge strength penalty term. The hierarchical region merging criterion is obtained with the increasing of the strength of the edge penalty. The effectiveness of the proposed method is demonstrated by comparing it qualitatively and quantitatively with several state-of-the-art methods.

SAR Image Edge Detection Robust to Isolated Strong Scatterers Using Anisotropic Morphological Directional Ratio Test

Edge detection via anisotropic average directional ratio (AADR) for synthetic aperture radar (SAR) images produces unwanted and fragmentized edge pixels due to the speckle noise and sporadic highlight pixels from isolated strong scatterers in real scenes. In this paper, a novel robust edge detector is developed for SAR images. Anisotropic morphological directional ratio (AMDR) is proposed to describe the intensity variation in SAR images by combining rotated biwindows and the weighted median filter (WMF). Then, multiplicative spatial and directional matched filters are presented to improve edge localization and direction estimation of the AMDR. Based on the enhanced AMDR, the edge strength map (ESM) and the edge direction map (EDM) are embedded into the route of Canny detector to extract thin edges. Moreover, an edge remedy processing is given to improve the connectivity of edges near junctions. Finally, performance comparison is conducted with the existing AADR-based detectors on synthetic and real SAR images using the receiver-operating-characteristic (ROC) curves, which shows that the proposed AMDR-based detector possesses evidently more robust ability to counteract sporadic isolated highlight pixels in SAR images than the existing AADR-based detectors do. Moreover, in the case without sporadic isolated highlight pixels, its performance is also comparable with those of existing competitive AADR-based ones.

Anti-Impulse-Noise Edge Detection via Anisotropic Morphological Directional Derivatives.

Traditional differential-based edge detection suffers from abrupt degradation in performance when images are corrupted by impulse noises. The morphological operators such as the median filters and weighted median filters possess the intrinsic ability to counteract impulse noise. In this paper, by combining the biwindow configuration with weighted median filters, anisotropic morphological directional derivatives (AMDDs) robust to impulse noise are proposed to measure the local grayscale variation around a pixel. For ideal step edges, the AMDD spatial response and directional representation are derived. The characteristics and edge resolution of two kinds of typical biwindows are analyzed thoroughly. In terms of the AMDD spatial response and directional representation of ideal step edges, the spatial matched filter is used to extract the edge strength map (ESM) from the AMDDs of an image. The spatial and directional matched filters are used to extract the edge direction map (EDM). Embedding the extracted ESM and EDM into the standard route of the differential-based edge detection, an anti-impulse-noise AMDD-based edge detector is constructed. It is compared with the existing state-of-the-art detectors on a recognized image dataset for edge detection evaluation. The results show that it attains competitive performance in noise-free and Gaussian noise cases and the best performance in impulse noise cases.

Segmentation of the Synthetic Aperture Radar Image Using the Watershed Transformation and Region Merging Technique

This paper presents an efficient algorithm that segments the synthetic aperture radar (SAR) image into several homogeneous regions by combining edgeand region-based information. A multi-direction ratio edge detector is used to capture the locally directional variation information of a SAR image and construct the ratio edge strength map (RESM) of the SAR image. Watershed transformation is performed on the thresholded RESM to obtain an over-segmentation result. An efficient hierarchical region merging procedure based on the region adjacency graph representation of the image regions is proposed. A novel dissimilarity measurement between the two adjacent regions is derived from the multiplicative noise speckle model of the multi-look SAR image. Experimental results and the performance evaluation show that the proposed method outperforms two widely used SAR image segmentation approaches.

Noise-robust color edge detector using gradient matrix and anisotropic Gaussian directional derivative matrix

In this paper, a noise-robust color edge detector using gradient matrix and anisotropic Gaussian directional derivative (ANDD) matrix is proposed. In order to alleviate the conflict between high edge resolution and noise robustness in the color Canny detector where the isotropic Gaussian kernels and gradient matrix of the R, G, B components are used, the ANDDs of the three components of a color image are arranged into the ANDD matrix. From its singular value decomposition (SVD), the ANDD-based color edge strength map (CESM) is constructed and is relevant to the pixelwise optimal fusion of the ANDDs of the three components in the sense of color edge enhancement. The merits and defects of the ANDD-based CESM and gradient-based CESM are contrasted to show their complementarity in color edge detection. The two CESMs are fused to develop a new color edge detector. It is compared with the color Canny detector and two recent color edge detectors. The results show that the proposed detector attains better detection performance for noiseless and noisy color images corrupted by white Gaussian noise or impulsive noise of small percentage.