Infrared Electric Image Segmentation Using Fuzzy Renyi Entropy and Chaos Differential Evolution Algorithm

Infrared thermograph is of great significance in electric equipment monitoring, but infrared images are by nature fuzzy and thus the segmentation of infrared electric image is a challenging task. To handing this ambiguity, the histogram of image is transformed into fuzzy domain employing fuzzy membership, and the fuzzy entropy of object and background is computed respectively according to the definition of Fuzzy Renyi Entropy(FRE). Then, with combinations of the membership function´s parameters as individual vectors, a chaos differential evolution (CDE) algorithm based on Logistic map was presented to find the optimum threshold following maximum entropy principle. Compared with other typical methods, the presented method is verified to be more effective and less time-consuming.