Edge detection based on genetic algorithm and sobel operator in image

Abstract

ABSTRACT Genetic algorithm (GA) is widely used as the optimization problems using techniques inspired by natural evolution. In this paper we present a new edge detection technique based on GA and sobel operator. The sobel edge detection built in DSP Builder is first used to determine the boundaries of objects within an image. Then the genetic algorithm using SOPC Builder proposes a new threshold algorithm for the image processing. Finally, the performance of the new edge detection technique-based the best threshold approaches in DSP Builder and Quartus II software is compared both qualitatively and quantitatively with the single sobel operator. The new edge detection technique is shown to perform very well in terms of robustness to noise, edge search capability and quality of the final edge image. Keywords- genetic algorithm; sobel operator; DSP Builder; SOPC Builder; edge detection 1. INTRODUCTION As edge detection is an important task in computer image analysis and processing, it is the front-end processing stage in object recognition and image understanding systems [1]. Sobel operator is one of the most popular edge detection algorithms. This technique uses the first differential to formulate the edge of the object [2]. The new edge detection design is implemented using a combination of hardware and software components. The basic block of the design (see Fig. 1) is the sobel operator built in DSP Builder that functions as a co-processor to hardware accelerates the two-dimensional convolution