基于多态蚁群优化算法的图像边缘检测_中英文论文文档.doc

2010 International Conference on Broadcast Technology and Multimedia Communication Image Edge Detection based on Polymorphic Ant Colony Optimization Algorithm 基于多态蚁群优化算法图像检测 Abstract - Ant colony optimization algorithm is easy to fall into local optimum and converges slowly in high-dimensional space. Polymorphic ant colony optimization algorithm takes full use of multiple pheromones leaved by different ants to help searching globally and improving optimization ability. The paper introduces polymorphic ant colony optimization algorithm to edge detection and utilizes polymorphism in ant society to enhance the performance of edge detection. The experiments indicate that the algorithm proposed in the paper do not only extract the weak edges, but also suppress the influence e of noiseand texture I. INTRODUCTION Edge is one of the simplest and the most important features of image, and this feature is broadly used in image recognition, segmentation, enhancement and compression [1]. The purpose of edge detection is not only to extract the edges of the interested objects from an image, but also to lay the foundation for image fusion, shape extraction, image segmentation, image matching, and image tracking [2]. Numerous edge detectors, such as differential-based edge detection algorithm, clustering-based edge detection algorithm, multi-scale edge detection algorithm and their improved approaches have been proposed, and these approaches show their advantages and disadvantages when dealing with different images. In practice, no single edge detection algorithm, at present, has been devised which will successfully determine every different type of edge. So, an approach combing various algorithms may help solving the problem better. Ant colony optimization (ACO) which proposed by Dorigo in the 1990s is one of the most recent techniques for approximate optimization [3], which based on the foraging behaviour of real ants --- ants com