BREAST TUMOR SEGMENTATION AND CLASSIFICATION USING SVM AND BAYESIAN FROM THERMOGRAM IMAGES

Breast cancer is one of the most important causes of death among women in the world. Mammography is so far the most common modality for the screening and diagnosis of breast tumor. However they have their limitations especially in young women with dense breasts and this necessitated the development of novel, more sensitive and specific strategies. There are no effective ways to prevent cancers and the only possible way of saving lives is early detection. Breast thermography uses thermal images of the breasts to help in the early diagnosis and detection of breast cancer. An abnormal thermogram has proven to be a reliable indicator of high risk of breast cancer in its early stages. Here initially the pre processing of the thermogram images are done wherein they are enhanced using the CLAHE method. The enhanced images after filtering are segmented using k means and fuzzy C means. The features have been extracted and these are used for classification for both the segmentation methods. Finally a comparison has been made by using the SVM and Bayesian classifiers.