A novel feature extraction method using spectral shape in digital mammogram image

The statistical Haralick features from the texture description methods GLCM, GLDM, SRDM, NGLCOM, NGLDM and Run-length features from the texture description method GLRLM are widely used to extract features in mammogram images for analysis and classification of abnormality. In this paper a novel feature extraction method based on spectral shape is proposed for classification of abnormality in mammogram image. The spectral shape features are extracted from the mammogram images and analyzed for classification performance. The classification performance of this method is compared with the Haralick features and the run-length features. A typical mammogram image processing system generally consists of mammogram image acquisition, pre-processing, segmentation, feature extraction, feature selection and classification. These processes are executed and the features analyzed. The performance of the proposed spectral shape feature is examined.