Edge Detection using Distinct Particle Swarm Optimization

Abstract

Edge detection is long-established in computer perception approach such as object detection, shape matching, medical image classification etc. For this reason many edge detectors like, Sobel, Robert, Prewitt, Canny etc. has been progressed to increase the effectiveness of the edge pixels. All these approaches work fine on images having minimum variation in intensity. Therefore, a new objective function based distinct particle swarm optimization (DPSO) is proposed in this paper to identify unbroken edges in an image. The conventional edge detectors such as “Canny” & computational intelligent techniques like ACO, GA and PSO are compared with proposed algorithm. Precision, Recall & F-Score is used as performance parameters for these edge detection techniques. The ground truth images are taken as reference edge images and all the edge images acquired by different edge detection systems are contrasted with reference edge image with ascertain the Precision, Recall and F-Score. The techniques are tested on 500 test images from the “BSD500” datasets. The empirical results presented by the proposed algorithm performance better than other edge detection techniques in the images. The proposed method observes edges more accurately and smoothly than other edge detection techniques such as “Canny, ACO, GA and PSO” in different images.