基于蚁群优化与细菌趋化性的图像边缘检测算法

为解决基于蚁群优化的图像边缘检测算法中信息素的作用不明显,难以获得全局最优解,从而降低目标边缘的检测精确度与效率等问题,提出一种基于细菌趋化性(BC)耦合蚁群优化(ACO)的边缘检测算法.通过细菌趋化性找到最佳解决方案,用于产生信息素的初值;将BC得到的信息素初值作为ACO的初始信息素,计算每只蚂蚁的行走概率,从而选择...

Image edge detection algorithm based on Ant Colony Optimization coupled with Bacterial Chemotaxis

The function of pheromone in image edge detection algorithm based on ant colony optimization is not obvious and it is difficult to obtain the global optimal solution, thus reducing the accuracy and efficiency of the target edge detection. An Ant Colony Optimization(ACO) based on Bacterial Chemotaxis(BC) is proposed to improve the performance of edge detection. Firstly, the best solution is found through bacterial chemotaxis to produce the initial value of pheromone. Then, the initial value of pheromone obtained from BC is used as the initial pheromone of ACO, to calculate the walking probability of each ant and choose the walking path. When ants experience a pixel, local pheromones are updated. After all the ants complete the iteration, they update the global pheromone and search for the global optimal solution. Finally, according to the relationship between the optimal solution of pheromone and the threshold, the edge and non-edge are obtained. The results show that the proposed method has a great improvement in search accuracy, optimization speed and stability. Compared with other edge detection algorithms, it has better edge continuity, clarity and detection accuracy for small edges with perfect convergence speed.