Interactive Image Segmentation and Edge Detection of Medical Images

In computer vision and object recognition, effective and efficient image segmentation is an important task. This paper presents an Interactive Segmentation of Medical Images. Since fully automatic image segmentation is usually very hard for natural and medical images, interactive schemes with a few simple user inputs are good solutions. The users only need to roughly indicate the location and region of the object and background by using strokes, which are called markers. For Interactive Segmentation, maximal similarity based region merging algorithm is used. Secondly, an auto adaptive Edge-Detection algorithm is used to detect the edges. Compare to other edge detection algorithm (Sobel, Prewitt, Canny, Laplacian), an autoadaptive is efficient and robust.