Classification of Micro Calcifications in Mammogram using Combined Feature Set with SVM

Abstract

Mammography is the only effective and viable technique to detect breast cancer especially in the case of minimal tumors. About 30% to 50% of breast cancers demonstrate deposits of calcium called micro calcifications. Our method proposes an approach for detecting microcalcification in mammograms based on combined feature set with Support Vector Machine (SVM) classifier. The diagonal matrix ‗S' obtained from the Singular Value Decomposition (SVD) of LL band of wavelet transform is used as one of feature set for the classification of mammogram The set of Jacobi polynomials are orthogonal and this ensures minimal information redundancy between the moments. Jacobi moments encompass the properties of well known Zernike, Legendre and Tchebichef moments. Thus Jacobi moments are used combined with ‗S' matrix to achieve the better classification result.