Ant Colony Optimization is one of the most used methods applied to complex problems. Image processing is a difficult task in particular when complex images are involved. This paper uses a fuzzy euclidean metric as a distance measure between pixels from two images. This is the first evaluation of Ant Colony Optimization image edge detection in the context of fuzzy index and fuzzy euclidean metrics. The Canny edge detection is considered as the ground truth when evaluating similarities between the considered fuzzy images including medical ones. Experiments were run and successful comparisons were conducted using existing data sets as well as well-known non-fuzzy similarity metrics such as Jaccard’s index, Dice’s coefficient and the Pratt’s Figure of Merit were applied.