An Otsu Image Segmentation Algorithm Based on Chaos Optimization of Two BSA

In order to improve the accuracy and stability of bird swarm image segmentation algorithm in finding the optimal threshold of image, a two-bird swarm chaos optimization image segmentation algorithm is proposed. The two-dimensional solutions obtained by two populations are cross-exchanged when the image two-dimensional otsu threshold is calculated, chaos disturbances are added to enhance the search capability. In order to reduce the influence of noise on the image segmentation results, an improved adaptive selection median-mean filter method is used to preprocess the image, which enhances the robustness to noise during image segmentation. Experimental results show that the two-bird swarm chaos-optimized image segmentation algorithm is superior to other algorithms in obtaining the one-dimensional and two-dimensional otsu thresholds, The image can be accurately segmented regardless of low noise pollution or high noise pollution.