Abstract |
: |
This paper describes propose a method to detect bleeding regions from WCE video. To find bleeding regions we are using superpixel segmentation process. Image segmentation is the process of dividing an image into multiple parts that’s used to identify relevant information in digital images. Initially the video is converted into frames in that frames we are finding the edges using canny detector. Then we remove the edge by means of morphological dilation. After removing the edges, group the pixel based on color and location using superpixel segmentation. Finally we find the frame contain bleeding or not by using the classifier. |