Edge detection of texture image using genetic algorithms

Image segmentation is an important pre-processing step before object recognition and is a process of partitioning an image into different regions with homogeneity in some image characteristics. In the image segmentation problem, detection of the edge in the texture image with randomness is a very difficult and important task. We introduce a new edge detection method for the texture image with randomness using genetic algorithms (GAs). In this method, we formulate the edge detection problem as a combinatorial optimization problem and the detection of the edge is executed according to the variance of texture features in the local area. First, we elect the candidate edge regions and then apply GAs in order to decide the optimum edge regions. This method using GAs has an advantage that arrangement of the edge regions is fulfilled by a very simple architecture and it does not need much processing time