Image Segmentation Technology of the Ostu Method for Image Materials Based on Binary PSO Algorithm

The threshold segmentation technology is an important significance in image analysis and image recognition. The Ostu Method is widely used for calculating effective, simple and stable. But it has disadvantage of more complexity and time-consuming. In order to overcome the problem, the paper presents a new automatic threshold segmentation algorithm after studying the Ostu method and the BPSO algorithm. Firstly the Ostu method is extended to multi-threshold segmentation. Secondly taking the advantage of PSO algorithm and taking the maximal variance of gray image as the fitness, the algorithm can obtain the optimal thresholds. Finally the experiments show that compared with the traditional method, the algorithm is not only of better segmentation quality but also of faster computational speed.