Abstract—Edge detection, the process of locating the edge of an image, is a basic and important subject in computer vision and image processing. There are different techniques for detecting the edges of images among which the evolvable hardware has drawn the attention of researchers for the case in the recent years. This paper is to describe the application of Evolvable Hardware (EHW) to detect the edges based on Sobel operator, the primary edge detection method. In this regard,the smoothing filter is applied to the images which are contaminated by Gaussian noise with the mean of 0 and different variance levels. Evolutionary design of edge detector performs Evolution of spatial masks and threshold. EHW filteris used to conduct the purpose of this paper and the relevant obtained results are compared with the ones gained using only Sobel operator which has constant threshold and spatial masks. According to the results, the edge detection is improved because of using EHW filter.

Index Terms—Edge detection, Evolvable hardware, Genetic algorithm, Sobel operator.

Maryam Hosseini is with the Department of Electrical Engineering, Iran University of Science and Technology, Tehran, Iran.(maryam.hosseini79@gmail.com)
Sattar Mirzakuchaki is with the Department of Electrical Engineering,Iran University of Science and Technology, Tehran, Iran.(m_kuchaki@iust.ac.ir)

Cite: M. Hosseini and S. Mirzakuchaki, "Edge Detection Based on Extrinsic Evolvable Hardware," International Journal of Computer and Electrical Engineering vol. 3, no. 2, pp. 271-276, 2011.