M.Zhu, C. Wu, J.-F. Lu, and J. Zhao (PRC)
Image Segmentation, Maximum Fuzzy Entropy Membership Function, Adaptive Thresholding
In this paper, an image segmentation method under the condition of the low contrast and strong background noise based on fuzzy entropy principle is presented. According to the membership degrees for the objects in the fuzzy partition, the system selects a set of pixels and associates a set of candidate classes with each of them. We discuss the concept of fuzzy partition and the maximum fuzzy entropy principle to select threshold value for gray-level images first, then how to choose the membership function and window size are introduced. Based on the relationship between maximum gray-level gmax and the minimum gray-level gmin in the processing image, a new method for the automatic choice of window size of a predetermined membership function is provided. The performance of the proposed technique is demonstrated on several images in deferent environment. Segmented images obtained using other techniques are also presented for comparison.
Important Links:
Go Back
