Binary Edge Map Research Articles

Chainlet-Based Ear Recognition Using Image Multi-Banding and Support Vector Machine

This paper introduces the Chainlet-based Ear Recognition algorithm using Multi-Banding and Support Vector Machine (CERMB-SVM). The proposed technique splits the gray input image into several bands based on the intensity of its pixels, similar to a hyperspectral image. It performs Canny edge detection on each generated normalized band, extracting edges that correspond to the ear shape in each band. The generated binary edge maps are then combined, creating a single binary edge map. The resulting edge map is then divided into non-overlapping cells and the Freeman chain code for each group of connected edges within each cell is determined. A histogram of each group of contiguous four cells is computed, and the generated histograms are normalized and linked together to create a chainlet for the input image. The created chainlet histogram vectors of the images of the dataset are then utilized for the training and testing of a pairwise Support Vector Machine (SVM). Results obtained using the two benchmark ear image datasets demonstrate that the suggested CERMB-SVM method generates considerably higher performance in terms of accuracy than the principal component analysis based techniques. Furthermore, the proposed CERMB-SVM method yields greater performance in comparison to its anchor chainlet technique and state-of-the-art learning-based ear recognition techniques.

A Robust 3D Density Descriptor Based on Histogram of Oriented Primary Edge Structure for SAR and Optical Image Co-Registration

The co-registration between SAR and optical images is a challenging task because of the speckle noise of SAR and the nonlinear radiation distortions (NRD), particularly in the one-look situation. In this paper, we propose a novel density descriptor based on the histogram of oriented primary edge structure (HOPES) for the co-registration of SAR and optical images, aiming to describe the shape structure of patches more firm. In order to extract the primary edge structure, we develop the novel multi-scale sigmoid Gabor (MSG) detector and a primary edge fusion algorithm. Based on the HOPES, we propose the co-registration method. To obtain stable and uniform keypoints, the non-maximum suppressed SAR-Harris (NMS-SAR-Harris) and deviding grids methods are used. NMS-SSD fast template matching and fast sample consensus (FSC) algorithm are used to further complete and optimize matching. We use two one-look simulated SAR images to demonstrate that the signal-to-noise ratio (SNR) of MSG is more than 10 dB higher than other state-of-the-stage detectors; the binary edge maps and F-score show that MSG has more accurate positioning performance. Compared with the other state-of-the-stage co-registration methods, the image co-registration results obtained on seven pairs of test images show that, the correct match rate (CMR) and the root mean squared error (RMSE) improve by more than 25% and 15% on average, respectively. It is experimentally demonstrated that the HOPES is robust against speckle noise and NRD, which can effectively improve the matching success rate and accuracy.

Infrared Image Superpixel Segmentation Based on Seed Strategy of Contour Encoding

Superpixel segmentation has become a crucial pre-processing tool to reduce computation in many computer vision applications. In this paper, a superpixel extraction algorithm based on a seed strategy of contour encoding (SSCE) for infrared images is presented, which can generate superpixels with high boundary adherence and compactness. Specifically, SSCE can solve the problem of superpixels being unable to self-adapt to the image content. First, a contour encoding map is obtained by ray scanning the binary edge map, which ensures that each connected domain belongs to the same homogeneous region. Second, according to the seed sampling strategy, each seed point can be extracted from the contour encoding map. The initial seed set, which is adaptively scattered based on the local structure, is capable of improving the capability of boundary adherence, especially for small regions. Finally, the initial superpixels limited by the image contour are generated by clustering and refined by merging similar adjacent superpixels in the region adjacency graph (RAG) to reduce redundant superpixels. Experimental results on a self-built infrared dataset and the public datasets BSD500 and 3Dircadb demonstrate the generalization ability in grayscale and medical images, and the superiority of the proposed method over several state-of-the-art methods in terms of accuracy and compactness.

A Novel Pixel Orientation Estimation Based Line Segment Detection Framework, and Its Applications to SAR Images

In this paper we propose a new line segment detection framework based on a novel Pixel Orientation Estimation (POE) method, which detects line segments from binary edge maps and can be combined with any edge detectors. We show its efficiency by testing it in 1-look SAR images. The novel Pixel Orientation Estimation method estimates the orientation of each edge pixel by counting the number of edge pixels along a set of orientations. As the most edge pixels exist along the orientation of the line segment, the orientation of the edge pixel is given by the orientation that gives the maximum number of counts. Counting the number of edge pixels along different orientations is equivalent to convolving the local neighbourhood of an edge pixel with a set of carefully designed window functions with each window function corresponding to a fixed orientation. With the estimated orientations of pixels in the edge map, pixels can be grouped with a region growing step to form line support regions. Regions with their size larger than a size threshold will be accepted. Finally, rectangles are used to approximate the accepted regions and those rectangles are detected line segments. Experiments in both simulated SAR dataset and three 1-look Sentinel-1 images demonstrate the efficiency of the proposed method. In particular, we advance the state-of-the-art performances by 18 percent (F1-score) on the 1-look dataset simulated from YorkUrban-LineSegment Dataset.

Extraction of spatial-spectral homogeneous patches and fractional abundances for field-scale agriculture monitoring using airborne hyperspectral images

Farm scale information is crucial for large scale agricultural monitoring and policymaking. Therefore, per-field agricultural land-use statistics is more informative than per-pixel statistics. However, per-field segmentation of hyperspectral image (HSI) is challenging due to the variability in spectral responses of different spectral bands within the neighbourhood. Moreover, manual digitization and modification of the field map or field boundaries at each airborne campaign (at different spatial resolution) or each growing season is a challenging task. To overcome this challenge, we developed an unsupervised method for segmenting the spatial-spectral homogeneous pixels and its fractional abundances in airborne HSIs. In the proposed approach, morphological operations based local spectral similarity measure combined with edge detector was applied to produce edge intensity map. Watershed segmentation was applied on the binary edge map to generate the spatially homogeneous land segments in the HSI. Then, online-dictionary-learning and sparse-unmixing have been performed on the HSI to compute the fractional abundance map of vegetation, soil and crop residue and to mask the other targets. The proposed method was tested on simulated HSI, benchmark HSIs as well as the image obtained from Airborne-Visible-and-Infra-Red-Imaging-Spectrometer Next-Generation (AVIRIS-NG) sensor. Figure-of-merit, false-alarm-count and miss-count were applied to evaluate the performance of boundary detection methods. The results indicate that the fractional-spectral-similarity outperformed other distance measures in detecting spectrally homogeneous regions. It was also observed that integration of fractional-similarity with Sobel-edge-filter improved the performance of the edge detector. Edge-intensity-map generated using the fractional-similarity approach was employed as seed points for the watershed segmentation, which showed significant improvement in terms of accuracy as compared to other segmentation methods. We also demonstrated the robustness of our method on multiple HSI datasets spanning different regions. Moreover, the integration of spectral un-mixing with segmentation technique enables the identification of bare fields, harvested fields with crop-residues, and the fields with high vegetation canopy cover. The proposed method is automated with few parameters and it is operationally practical for large HSIs.

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.

Globally Measuring the Similarity of Superpixels by Binary Edge Maps for Superpixel Clustering

This paper proposes an edge-based superpixel similarity measurement, which globally evaluates the similarity between superpixels by binary edge maps. The basic idea is to assess whether the superpixels are surrounded by the same edges. To this end, we first describe the edge spatial distributions by directional regions and then use the directional regions to represent the surrounding relationships of superpixels and edges by their traverse relationships, which form the histogram feature. Finally, the similarity is simply calculated by the distances between the features. To verify the proposed similarity measurement, we use our global similarity measurement to perform superpixel clustering. Two clustering methods, the directed graph clustering (DGC) and spectral clustering (ultrametric contour map) are combined to achieve the clustering process. The combination of our global similarity measurement and DGC to form a new three-layer-based superpixel generation method, which can quickly generate the superpixel from edge maps, is highlighted. We verify the global similarity measurement by the BSDS500 dataset. The experimental results demonstrate that the proposed global similarity measurement can improve the clustering accuracy in terms of larger intersection-over-union-criterion-based values. The code can be downloaded from https://github.com/FanmanMeng/Superpixel-Similarity-Measurement .

Rapid Line-Extraction Method for SAR Images Based on Edge-Field Features

This letter proposes a rapid line-extraction (RLE) method for synthetic aperture radar (SAR) images. RLE first transforms an image in the space domain into an image in the frequency domain. Then, using the central-slice theorem, RLE skilfully maps the image in the frequency domain into a parameter space, which effectively accelerates the straight-line extraction process. Unlike the traditional Hough transform, RLE is performed directly on an edge-field image rather than on a binary edge map. Theoretical analysis proves the advantages of using the edge-field map. Notably, the computational complexity can be greatly reduced relative to the complexity of obtaining a binary edge map, and the method can efficiently avoid the negative influence of false edges in the binary edge map. More importantly, because speckle, clutter, and blurred edges in real-world images decrease the sharpness of peaks, edge-field images that include the strength and direction information of SAR images are adopted to reduce the diffusion of peaks and improve the detection accuracy. Experimental studies show that RLE works independently, is robust to noise, has low computational complexity, achieves high true-positive detection rates, and yields satisfactory detection precision.

An Optimal Fuzzy System for Edge Detection in Color Images Using Bacterial Foraging Algorithm

This paper presents a fuzzy system for edge detection, using smallest univalue segment assimilating nucleus (USAN) principle and bacterial foraging algorithm (BFA). The proposed algorithm fuzzifies the USAN area obtained from the original image, using a USAN area histogram-based Gaussian membership function. A parametric fuzzy intensification operator (FINT) is proposed to enhance the weak edge information, which results in another fuzzy set. The fuzzy measures, i.e., fuzzy edge quality factor and sharpness factor, are defined on fuzzy sets. The BFA is used to optimize the parameters involved in the fuzzy membership function and the FINT. The fuzzy edge map is obtained using optimized parameters. The adaptive thresholding is used to defuzzify the fuzzy edge map to obtain a binary edge map. The experimental results are analyzed qualitatively and quantitatively. The quantitative measures, i.e., Pratt's figure of merit, Cohen’ Kappa, Shannon's entropy, and edge strength similarity-based edge quality metric, are used. The quantitative results are statistically analyzed using t-test. The proposed algorithm outperforms many of the traditional and state-of-the-art edge detectors.

A full reference Morphological Edge Similarity Index to account processing induced edge artefacts in magnetic resonance images

An objective measure of edge similarity between the original and processed images to quantify the processing induced artefacts in medical image computing is proposed in this article. Globally accepted Image Quality Analysis (IQA) indices such as Peak Signal Noise Ratio (PSNR) and Structural Similarity Index Metric (SSIM) measure the structural similarity between the original and processed image and do not specifically reflect the resemblance of the edge content. Most of the IQA indices either do not comply with the subjective quality ratings or they are prone to noise level. In the proposed Morphological Edge Similarity Index (MESI), the binary edge maps of the reference and processed images are generated via gradient based threshold and these edge maps are objectively compared to yield a reliable edge quality metric. The index is found superior to Edge Preservation Index (EPI), Edge Strength Similarity based Image quality Metric (ESSIM) and SSIM in terms of dynamic variability, correlation with subjective quality ratings, robustness to noise and sensitivity to degradation in edge quality caused by blockiness artefacts in image compression. MESI exhibits a correlation of 0.9985, very close to unity, with the subjective quality ratings. It is useful for objectively evaluating the performance of denoising, sharpening and enhancement schemes and for the selection of optimum value of the arbitrary parameters used in them.

A New Bayesian Edge-Linking Algorithm Using Single-Target Tracking Techniques

This paper proposes novel edge-linking algorithms capable of producing a set of edge segments from a binary edge map generated by a conventional edge-detection algorithm. These proposed algorithms transform the conventional edge-linking problem into a single-target tracking problem, which is a well-known problem in object tracking. The conversion of the problem enables us to apply sophisticated Bayesian inference to connect the edge points. We test our proposed approaches on real images that are corrupted with noise.

Neighborhood geometry based feature matching for geostationary satellite remote sensing image

In this paper, we focus on Global Self-consistent, Hierarchical, High-resolution Geography (GSHHG) database registration for remote sensing images taken from geostationary meteorological satellites. While the accuracy of feature matching is the key component. To improve it, we propose a neighborhood geometry-based feature matching scheme which includes three steps: neighborhood coding, verification and fitting. (1) Neighborhood coding represents landmarks of GSHHG as a descriptive bit-matrix, and quantifies remote sensing images to a probability-based edge map and a binary geometry-based edge map. As a result, both gradient and geometry similarity of local features in the remote sensing image and GSHHG can be measured. (2) Neighborhood verification is to encode spatial relationship among local features in neighbor, and discover outliers. (3) Neighborhood fitting fits the shorelines of GSHHG with the landmarks registered by neighborhood verification to improve recall. Experimental results on 25 pairs of newly annotated images show that the proposed method is competitive to several prior arts with respect to matching accuracy. What is more, our method is significantly more efficient than others.

Extracting Line Features in SAR Images Through Image Edge Fields

Conventional line detection methods are mainly based on the binary edge map. This letter proposes a new line detection method that directly extracts line features from the image edge fields of the synthetic aperture radar (SAR) images. In the proposed method, the strength and direction of each field point are first obtained using a ratio-based edge filter. Then, the accumulation weight of the field point is jointly computed using its strength and direction. The direction of a field point on the line is essentially the orientation of the line. Furthermore, a field point on a strong line should be distinguished from a field point on a weak line. Thus, the accumulation weights of different field points are not equal. By summing up the accumulation weights, the straight lines in the SAR image space are directly converted into several local peaks in the parameter space. A sort-window peak detection method is proposed to suppress the spurious secondary peaks in the parameter space. The experimental results show that the proposed line detection method is robust to noise and has a good antiocclusion ability. The proposed method performs well in terms of true positive detection rate and detection accuracy for both synthetic and real-world images.

PEL: A Predictive Edge Linking algorithm

We propose an edge linking algorithm that takes as input a binary edge map generated by a traditional edge detection algorithm and converts it to a set of edge segments; filling in one pixel gaps in the edge map, cleaning up noisy edge pixel formations and thinning multi-pixel wide edge segments in the process. The proposed edge linking algorithm walks over the edge map based on the predictions generated from its past movements; thus the name Predictive Edge Linking (PEL). We evaluate the performance of PEL both qualitatively using visual experiments and quantitatively within the precision-recall framework of the Berkeley Segmentation Dataset and Benchmark (BSDS 300). Both visual experiments and quantitative evaluation results show that PEL greatly improves the modal quality of binary edge maps produced by traditional edge detectors, and takes a very small amount of time to execute making it suitable for real-time image processing and computer vision applications.

A new approach for edge detection in noisy images based on the LPGPCA technique

In this study, a new approach to edge detection on images, corrupted with Gaussian and impulsive noise, is presented. The concept, under the decomposition of image with its principal component being an analysis on local pixel grouping for noise suppression, called LPGPCA based denoising, is adopted in order to obtain noiseless gradient maps for edge extraction. As a result, an algorithm has been developed called LPGPCA-ED. Firstly, horizontal and vertical gradient images are computed; then the gradient images are decomposed into a noiseless phase by applying the LPGPCA algorithm. Once a single gradient map has been obtained, a smart nonmaximum suppression operation is carried out to obtain a binary edge map. To show the accuracy of the proposed edge detector objectively, F-measure and PFOM results of the proposed edge detector on images with different Gaussian and impulsive noise are compared with the results of traditional and certain recently published edge detectors. Objectively, the experimental results on RUG and receiver operating characteristic (ROC) curve databases show that our method has better performance than other corresponding edge detectors. Moreover, subjective experiments on a variety of noise contaminated images show that the LPGPCA-ED algorithm is more robust under high level noise conditions, and is able to reveal well-linked lines and also preserve the structural form of a processed image.

Multiscale edge detection and parametric shape modeling for boundary delineation in optoacoustic images.

In this article, we present a novel scheme for segmenting the image boundary (with the background) in optoacoustic small animal in vivo imaging systems. The method utilizes a multiscale edge detection algorithm to generate a binary edge map. A scale dependent morphological operation is employed to clean spurious edges. Thereafter, an ellipse is fitted to the edge map through constrained parametric transformations and iterative goodness of fit calculations. The method delimits the tissue edges through the curve fitting model, which has shown high levels of accuracy. Thus, this method enables segmentation of optoacoutic images with minimal human intervention, by eliminating need of scale selection for multiscale processing and seed point determination for contour mapping.

A novel multi-scale and multi-expert edge detector based on common vector approach

In this paper, an information fusion algorithm – MSME-CVAED – is proposed for multi-scale and multi-expert edge detection. Well-known operators, called experts, have been applied to distinct scales derived by smoothing the gray image with Gaussian functions having different variance values. Common characteristics of edge points are processed to merge the information obtained from each scale, based on the concept of common vector approach. Once a single gradient map obtained, a smart non-maximum suppression operation is carried out to obtain a binary edge map. Later, an edge segment validation process is introduced based on Helmholtz principle, a common method in which edge segment validation is carried out with the “a contrario” approach using the number of false alarms concept. Experiments on popular datasets of ROC curves and RUG show that the proposed method achieves superior results in terms of F-measure and Mathews correlation coefficient score, compared with some recently published edge detectors.

An integrated approach for image retrieval using local binary pattern

In this paper an integrated approach for image retrieval has been proposed that uses the concept of local binary pattern. The image is divided into a fixed number of blocks and from each block, LBP based color, texture and shape features are computed. LBP histogram is used for the extraction of color and texture features. Region code based scheme is used to support region based retrieval. Center pixel and its neighbors are used to improve the discrimination power of Local Binary Patterns. Shape feature computed using the binary edge map obtained using Sobel edge detector is combined with color and texture features to make a single completed binary region descriptor. To support region based retrieval, a more effective region code based scheme is employed. The approach is tested on different benchmark databases like COREL, CIFAR-10 and MPEG-7 CCD database. The experimental results have verified that the proposed scheme has impressive retrieval performance in comparison to state-of-the-art techniques.

TecLines: A MATLAB-Based Toolbox for Tectonic Lineament Analysis from Satellite Images and DEMs, Part 2: Line Segments Linking and Merging

Extraction and interpretation of tectonic lineaments is one of the routines for mapping large areas using remote sensing data. However, this is a subjective and time-consuming process. It is difficult to choose an optimal lineament extraction method in order to reduce subjectivity and obtain vectors similar to what an analyst would manually extract. The objective of this study is the implementation, evaluation and comparison of Hough transform, segment merging and polynomial fitting methods towards automated tectonic lineament mapping. For this purpose we developed a new MATLAB-based toolbox (TecLines). The proposed toolbox capabilities were validated using a synthetic Digital Elevation Model (DEM) and tested along in the Andarab fault zone (Afghanistan) where specific fault structures are known. In this study, we used filters in both frequency and spatial domains and the tensor voting framework to produce binary edge maps. We used the Hough transform to extract linear image discontinuities. We used B-spline as a polynomial curve fitting method to eliminate artificial line segments that are out of interest and to link discontinuous segments with similar trends. We performed statistical analyses in order to compare the final image discontinuities maps with existing references map.

Edge detection using ACO and F ratio

Edge detection is an important step for finding the discontinuities of images and detecting the boundaries of objects. This work presents a novel algorithm for image edge detection using ant colony optimization and Fisher ratio (F ratio)-based techniques. Ants generally search the food from the nest to the food source in the way that maximizes the intensity of pheromone (a chemical secretion). The proposed technique considers that the movements of the artificial ants are steered by the local intensity variation in the image pixel. The directions of ants movements in the image are determined using a direction probability matrix, computed by pheromone and heuristic information of possible directions. In this work, F ratio technique is utilized to determine the optimum threshold value from updated pheromone matrix. This threshold value is further used to extract binary edge map from pheromone matrix. The experiment is conducted on the different test images, i.e., Cameraman, Lena, Coins, Peppers, House and Pillsetc image. The proposed edge detection algorithm is evaluated on the basis of statistical parameters such as kappa, figure of merit, Baddeley’s delta metric and Hausdorff distance, and the experimental results show that the proposed method performs better as compared to earlier reported techniques in most of the cases.