A NOVEL APPROACH FOR EDGE DETECTION USING LATERAL INHIBITION & OTSU S THRESHOLDING

Abstract

For over 30 years researchers in computer vision have been proposing new methods for performing low-level vision tasks such as detecting edges and corners. Edge detection is an important aspect for image processing, and primary step of spatial data extraction in geography information system. It has been applied to solve various image processing problems such as image segmentation, classification, image analysis and edge detection. One key element shared by most methods is that they represent local image neighborhoods as intensity with deviations modeled as noise. Due to computational considerations that encourage the use of small neighborhoods where this assumptions holds, these methods remain popular. This thesis models the technique using the advantages of Lateral Inhibition and for the edge detection. Lateral inhibition is a technique to enhance the sharpness of images, which is developed from Hartline's research on sensory inhibition. Conventional lateral inhibition operates on the entire image like high-pass filter, which also strengthens noise besides edges. nonparametric and unsupervised method of automatic threshold selection for picture segmentation is presented. An optimal threshold is selected by the discriminant criterion, namely, so as to maximize the separability of the resultant classes in gray levels. The procedure is very simple, utilizing only the zeroth- and the first-order cumulative moments of the gray-level histogram. It is straightforward to extend the method to multi-threshold problems. Several experimental results are also presented to support the validity of the method. The experimental results have shown that it gives the better result with less errors and the performance is superior to the popular edge detection methods like Sobel and Canny.