Feature Extraction and Classification for Using Mammographic Images

Abstract

Abstract

One of the greatest threats prevailing among women is the breast cancer. According to the National Cancer Institute, 22% of new cases occur every year and it is considered to be the second most frequent type of cancer, worldwide. Mammogram is very important imaging technique that used diagnosis in early stages of breast cancer. Mammography is in this case the best diagnostic technique for screening, the radiology tool which gives better accuracy than clinical breast examination. In this method, the multistage morphological dilation continuously absorbs neighboring pixels into individual micro-calcification resulting in a change in the connectivity between micro-calcification within the cluster. The K-means clustering based segmentation and used histogram of oriented gradients (HOG) features extraction for classifying micro-calcification clusters into malignant and benign with the help of classical support vector machine (SVM) classifier is a popular and conceptually intuitive instance-based learning approach.

Keywords: K-means clustering, histogram of oriented gradients (HOG), support vector machine (SVM), neural network (NN)

Cite this Article

Srinivasan S, Sagayam R. Feature Extraction and Classification for Using Mammographic Images. Journal of Advances in Shell Programming. 2017; 4(2): 10–18p.