Edge Detection Techniques for Image Segmentation – A Survey of Soft Computing Approaches N. Senthilkumaran1 and R. Rajesh2
School of Computer Science and Engineering, Bharathiar University, Coimbatore -641 046, India. 1 email@example.com, firstname.lastname@example.org logical reasoning. It has been applied to image processing in many ways. Segmentation aims at dividing pixels into similar region i.e. crisp sets. Fuzzy segmentation in turn divides pixels into fuzzy sets i.e. each pixel may belong partly to many sets and regions of image. The Second approach, Neural networks are computer algorithms inspired by the way information is processed in the nervous system. An important difference between neural networks and other AI techniques is their ability to learn. The network ”learns” by adjusting the interconnection (called weights) between layers. When the network is adequately trained, it is able to generalize relevant output for a set of input data. A valuable property of neural networks is that of generalization, whereby a trained neural network is able to provide a correct matching in the form of output data for a set of previously unseen input data. Learning typically occurs by example through training, where the training algorithm iteratively adjusts the connection weights . The third approach, Genetic algorithms derive from the evolution theory. They were introduced in 1975 by John Holland and his team as a highly parallel search algorithm. Later, they have been mainly used as an optimization device. According to the evolution theory, within a population only the individuals well adapted to their environment can survive and transmit some of their characters to their descendants. GA has been used to solve various problems in digital image processing, including image segmentation . This paper is organized as follows. Section II is for the purpose of providing some information about edge detection for Image Segmentation. Section III is focused on showing the different soft computing approaches to edge detection and also focused on comparison of various Edge Detection Methods. Section IV presents the conclusion. II. EDGE DETECTION FOR IMAGE SEGMENTATION Edge detection techniques transform images to edge images benefiting from the changes of grey tones in the images. Edges are the sign of lack of continuity, and ending. As a result of this transformation, edge image is obtained without encountering any changes in physical qualities of the main image. Objects consist of numerous parts of different color levels. In an image with different grey levels, despite an obvious change in the 250 © 2009 ACADEMY PUBLISHER
Abstract—Soft Computing is an emerging field that consists of complementary elements of fuzzy logic, neural computing and evolutionary computation. Soft computing techniques have found wide applications. One of the most important applications is edge detection for image segmentation. The process of partitioning a digital image into multiple regions or sets of pixels is called image segmentation. Edge is a boundary between two homogeneous regions. Edge detection refers to the process of identifying and locating sharp discontinuities in an image. In this paper, the main aim is to survey the theory of edge detection for image segmentation using soft computing approach based on the Fuzzy logic, Genetic Algorithm and Neural Network. Index Terms—Image Segmentation, Edge Detection, Fuzzy logic, Genetic Algorithm, Neural Network.
I. INTRODUCTION Image Segmentation is the process of partitioning a digital image into multiple regions or sets of pixels. Actually, partitions are different objects in image which have the same texture or color. The result of image segmentation is a set of regions that collectively cover the entire image, or a set of contours extracted from the...