Segmentation of breast cancer using fuzzy C means and classification by SVM based on LBP features

Abstract

Recent years many women are affected by breast cancer. Mammogram is one of the early breast cancer diagnosis techniques used to identify the abnormal regions of breast. The recommended research work uses Fuzzy C-means segmentation algorithm to locate the wound area of mammogram breast image. Further the features of abnormal regions were extracted using Local Binary pattern (LBP) techniques. The statistical features are Entropy, Mean, RMS (Root Mean Square), correlation helps to train the neural network. Finally SVM (Support Vector Machine) classifier is utilized to categorize the abnormal regions of mammogram images with the accuracy rates of 86%.