A new operator for detecting edges in images based on modified Tsallis entropy

In both human and machine vision systems, edges in images are of crucial significance in understanding the contents of images. Edge detection has therefore become an important task in image processing. In this paper, we propose a new operator for detecting edges in images. This operator is based on the principle of evaluating the local fluctuation of the pixel values. We first normalize the pixel values within a mask so that they can be treated as probabilities. Then, a modified Tsallis entropy of the probabilities is calculated. Edges are detected where the value of this entropy is below a properly chosen threshold. The obtained edges are further refined by using a morphological operation. The proposed method is also generalized to the case of color images. In the simulation, the proposed operator exhibits promising performance compared with some well-known existing operators.