Mammogram Classification Based Onk-Nearest Neighbor Classifier
Ganesh Kumar, A Arivazhagan · Indian Journal of Public Health Research & Development · 2017
The computer-aided detection system plays avery important task in early cancer analysis. In this paper, we have classified the breast tumor in mammogram images to benign and malignant classes using shearlet transform. First the region of interest (ROI) of the mammogram image is denoised using median filter then subjected to shearlet transform and various statistical features are extracted from different levels and orientations. Then the features are fed to K-Nearest Neighbor (K-NN) classifier using minimum features. Finally, the mammogram is classified as benign or malignant using K-NN classifier.