Modified active contour algorithm (MAXA) based on the edge direction information

A method named MACA was suggested. In the general Snake model, there is no required matching between orientation of the contour and edge direction in the grey-level image. This kind of Snake model may fail in the image with rich texture or with concave objects. To avoid it, two energy functions based on the above mentioned ideas were proposed to improve the Snake model. To reduce the time cost in the iteration of MACA, a fast Gready algorithm was proposed. Also, the first-order and second-order derivative, domain of searching area, contour resampling, and conditions of corner locking were redefined. Experimental results show that the proposed method is much better than the general Snake model, especially in searching for the concave objects.