SUSAN Edge Detector Research Articles

Demarcating Z-line and Gastric Folds Boundary Based on the Segmentation of the Lower Esophageal Sphincter Images.

The endoscopic diagnosis of pathological changes in the gastroesophageal junction including esophagitis and Barrett's mucosa is based on the visual detection of two boundaries: mucosal color change between esophagus and stomach, and top endpoint of gastric folds. The presence and pattern of mucosal breaks in the gastroesophageal mucosal junction (Z line) classify esophagitis in patients and the distance between the two boundaries points to the possible columnar lined epithelium. Since visual detection may suffer from intra- and interobserver variability, our objective was to define the boundaries automatically based on image processing algorithms, which may enable us to measure the detentions of changes in future studies. To demarcate the Z-line, first the artifacts of endoscopy images are eliminated. In the second step, using SUSAN edge detector, Mahalanobis distance criteria, and Gabor filter bank, an initial contour is estimated for the Z-line. Using region-based active contours, this initial contour converges to the Z-line. Finally, by applying morphological operators and Gabor Filter Bank to the region inside of the Z-line, gastric folds are segmented. To evaluate the results, a database consisting of 50 images and their ground truths were collected. The average dice coefficient and mean square error of Z-line segmentation were 0.93 and 3.3, respectively. Furthermore, the average boundary distance criteria are 12.3 pixels. In addition, two other criteria that compare the segmentation of folds with several ground truths, i.e., Sweet-Spot Coverage and Jaccard Index for Golden Standard, are 0.90 and 0.84, respectively. Considering the results, automatic segmentation of Z-line and gastric folds are matched to the ground truths with appropriate accuracy.

A hybrid graph-based approach for right ventricle segmentation in cardiac MRI by long axis information transition

Right ventricle segmentation is a challenging task in cardiac image analysis due to its complex anatomy and huge shape variations. In this paper, we proposed a semi-automatic approach by incorporating the right ventricle region and shape information into livewire framework and using one slice segmentation result for the segmentation of adjacent slices. The region term is created using our previously proposed region growing algorithm combined with the SUSAN edge detector while the shape prior is obtained by forming a signed distance function (SDF) from a set of binary masks of the right ventricle and applying PCA on them. Short axis slices are divided into two groups: primary and secondary slices. A primary slice is segmented by the proposed modified livewire and the livewire seeds are transited to a pre-processed version of upper and lower slices (secondary) to find new seed positions in these slices. The shortest path algorithm is applied on each pair of seeds for segmentation. This method is applied on 48 MR patients (from MICCAI’12 Right Ventricle Segmentation Challenge) and yielded an average Dice Metric of 0.937 ± 0.58 and the Hausdorff Distance of 5.16 ± 2.88 mm for endocardium segmentation. The correlation with the ground truth contours were measured as 0.99, 0.98, and 0.93 for EDV, ESV and EF respectively. The qualitative and quantitative results declare that the proposed method outperforms the state-of-the-art methods that uses the same dataset and the cardiac global functional parameters are calculated robustly by the proposed method.

The Effect of Choice and Embarrassment on the Behavioral and Autonomic Correlates of Deception

Right ventricle segmentation is a challenging task in cardiac image analysis due to its complex anatomy and huge shape variations. In this paper, we proposed a semi-automatic approach by incorporating the right ventricle region and shape information into livewire framework and using one slice segmentation result for the segmentation of adjacent slices. The region term is created using our previously proposed region growing algorithm combined with the SUSAN edge detector while the shape prior is obtained by forming a signed distance function (SDF) from a set of binary masks of the right ventricle and applying PCA on them. Short axis slices are divided into two groups: primary and secondary slices. A primary slice is segmented by the proposed modified livewire and the livewire seeds are transited to a pre-processed version of upper and lower slices (secondary) to find new seed positions in these slices. The shortest path algorithm is applied on each pair of seeds for segmentation. This method is applied on 48 MR patients (from MICCAI’12 Right Ventricle Segmentation Challenge) and yielded an average Dice Metric of 0.937 ± 0.58 and the Hausdorff Distance of 5.16 ± 2.88 mm for endocardium segmentation. The correlation with the ground truth contours were measured as 0.99, 0.98, and 0.93 for EDV, ESV and EF respectively. The qualitative and quantitative results declare that the proposed method outperforms the state-of-the-art methods that uses the same dataset and the cardiac global functional parameters are calculated robustly by the proposed method.

Infrared and visible image fusion based on shiftable complex directional pyramid transform and SUSAN edge detector

Infrared and visible image fusion based on shiftable complex directional pyramid transform and SUSAN edge detector

Directional SUSAN image boundary detection of breast thermogram

Thermography of the breast has been shown to be well suited to detect early signs of breast cancer. This study proposes a novel method for boundary detection of breast thermography images using directional SUSAN method. Among breast thermography image processing steps, breast isolation from background and from each other is an essential stage for proper detection of breast cancer. For this purpose, in this study, breast boundary is grouped into three regions depending on the region property. The algorithm of boundary detection is different for each region. Specially, for bottom breast boundary, directional SUSAN edge detector is presented that uses two rectangle masks to create a directional SUSAN gradient image with emphasis on oblique useful edges and omitting undesirable ones. Then cubic parabolic interpolation is implemented to determine a set of edge points on the boundaries. At last, an effective search algorithm is executed to correct some false points in order to extract breast boundaries accurately. The performance of the proposed approach illustrated by applying on the images of three databases. Experimental results show that this method acts effectively and confirm the accurate boundary detection. Moreover, statistical measures are calculated to indicate the remarkable capabilities of the proposed approach.

Fast SUSAN edge detector by adapting step-size

The SUSAN algorithm is a popular edge detector for its high localization precision, noise-robustness and good connectivity at junctions. Straightforward implementation of SUSAN edge detector is performed by sliding a circular mask pixel by pixel on an image. For each pixel in the raster scan order, neighbor pixels in the circular mask around it are taken and used to compute the USAN area, according to which whether the current pixel is an edge point or not is judged. However, redundant computation exists in the direct implementation of SUSAN edge detector because of the pixel-by-pixel sliding way of the circular mask, which makes it somewhat inefficient. In this paper, we propose a fast implementation of SUSAN edge detector to decrease the redundancy. Instead of sliding the mask by one pixel every time, we propose an adaptive type of raster scan referred to as adaptive sliding mask which adjusts the sliding step-size adaptively according to USAN area. Experiments show that the proposed method can speed up the SUSAN edge detector effectively without spoiling its detection performance.

Automatic Crack Detection in Eggshell Based on SUSAN Edge Detector Using Fuzzy Thresholding

Among the defect found in the eggs, cracks are the most important in processing and grading table eggs. Eggshell cracks are a food safety concern because micro organism's can contamination of the egg causes pathogens, such as salmonella. Currently, In order to check and eliminate the cracked eggs quickly and exactly in production the process of egg, a non destructive testing system based on Digital Image Processing (DIP) with an efficient algorithm was developed. These algorithms are based on Fuzzy thresholding and SUSAN edge detector. The main advantage of this the method in comparison with other methods is less sensitive to noise, because no derivative operator was used. According to the experimental results, this algorithm had best binerization on the main image in comparison with algorithm Otsu and power law, also the results showed that with add Gaussian noise to the main input image with variable variance between 0.002 and 0.01; the accuracy of detection for proposed algorithm was 97% and 82%, also this algorithm had least value of error function (number of error pixel) on the gray level image toward other algorithms.

Randomized SUSAN edge detector

A speed up technique for the SUSAN edge detec- tor based on random sampling is proposed. Instead of sliding the mask pixel by pixel on an image as the SUSAN edge detector does, the proposed scheme places the mask ran- domly on pixels to find edges in the image; we hereby name it randomized SUSAN edge detector (R-SUSAN). Specifically, the R-SUSAN edge detector adopts three approaches in the framework of random sampling to accelerate a SUSAN edge detector: procedure integration of response computation and nonmaxima suppression, reduction of unnecessary process- ing for obvious nonedge pixels, and early termination. Experi- mental results demonstrate the effectiveness of the proposed method. C 2011 Society of Photo-Optical Instrumentation Engineers (SPIE).

Contour and boundary detection improved by surround suppression of texture edges

We propose a computational step, called surround suppression, to improve detection of object contours and region boundaries in natural scenes. This step is inspired by the mechanism of non-classical receptive field inhibition that is exhibited by most orientation selective neurons in the primary visual cortex and that influences the perception of groups of edges or lines. We illustrate the principle and the effect of surround suppression by adding this step to the Canny edge detector. The resulting operator responds strongly to isolated lines and edges, region boundaries, and object contours, but exhibits a weaker or no response to texture edges. Additionally, we introduce a new post-processing method that further suppresses texture edges. We use natural images with associated subjectively defined desired output contour and boundary maps to evaluate the performance of the proposed additional steps. In a contour detection task, the Canny operator augmented with the proposed suppression and post-processing step achieves better results than the traditional Canny edge detector and the SUSAN edge detector. The performance gain is highest at scales for which these latter operators strongly react to texture in the input image.

Comparison of Edge Detector Performance through Use in an Object Recognition Task

This paper presents an empirical evaluation methodology for edge detectors. Edge detector performance is measured using a particular edge-based object recognition algorithm as a “higher-level” task. A detector's performance is ranked according to the object recognition performance that it generates. We have used a challenging train and test dataset containing 110 images of jeep-like images. Six edge detectors are compared and results suggest that (1) the SUSAN edge detector performs best and (2) the ranking of various edge detectors is different from that found in other evaluations.