Detection of cervical cancer by using thresholding & watershed segmentation

Cervical cancer is an abnormal growth of tissues at cervix which is the lower part of the uterus (womb) that opens at the top of the birth canal. An efficient and practical algorithm to detect the cervical cancerous area is presented in this paper. Edge detection is applied on the image to find edges of tumour area. The hybrid segmentation is done on the sampled image i.e. combination of thresholding and watershed segmentation to extract the tumor infected area. The image is then processed using morphological image processing tools to detect the accurate dimensions of the tumour. The fine detection of tumorous area is a challenging task in medical image science. Using this proposed method it is possible to detect infected area.