Fuzzy Entropy Clustering Image Segmentation Algorithm Based on Potential Two-Dimensional Histogram

摘要

Fuzzy c-means (FCM) algorithm has been widely used in image segmentation. However, the traditional FCM algorithm does not take into account any image spatial information, which makes it very sensitive to noise. In order to make improvements on the basis of FCM, we proposed a fuzzy entropy clustering image segmentation algorithm based on potential two-dimensional histogram. Firstly, the two-dimensional gray histogram is constructed by using the gray value of image pixels and its local spatial uniform gray value, and the potential function is used to map-the mutual influence between image pixels into the data field, so as to describe the interaction between pixels more accurately. Secondly, the kernel function will be used to map the data to a high dimensional space to complete the linear transformation, this makes the data in the original space linearly indivisible become linearly separable or approximately linearly separable, which overcomes the defect that FCM is not suitable for multiple data distributions in some extent. Finally, the iterative formula of image segmentation is obtained by Lagrange multiplier method. Experimental results show that the proposed algorithm has higher correct segmentation rate and stronger robustness.