Fuzzy edge detection with minimum fuzzy entropy criterion

In this paper, a new fuzzy logic-based edge detection technique is proposed, in which the drawbacks of the conventional gradient-based techniques are efficiently overcome. Using the relation of the probability partition and the fuzzy 2-partition of the image gradient, the best gradient-threshold is automatically and efficiently selected. The selection algorithm is based on the condition for the entropy to reach a minimum value, since our aim is to find the best compact image representation through edges. The excellent performance of the proposed technique is exercisable through simulation results on a set of test images. It is shown how the extracted, enhanced and purified edges provide an efficient edge-representation of images.