A generalized fuzzy entropy-based image segmentation method

Image segmentation using fuzzy entropy is an important and common segmentation method. The threshold of fuzzy entropy is mostly selected at the gray value with fuzzy membership degree 0.5. It is a limitation in some cases. In order to solve this problem, we present a new definition of generalized fuzzy entropy and apply it to image segmentation. Compared with the traditional fuzzy entropy-based image segmentation method, the proposed method segments an image using the threshold with membership degree m (0<m<1), and increases the opportunity of choosing appropriate thresholds. Experiments show that our method can obtain better segmentation result than the traditional fuzzy entropy method.