Nonsubsampled Contourlet Transformation Based Image Enhancement with Spatial and Statistical Feature Extraction for Classification of Digital Mammogram
K. Sankar1, K.Nirmala2
1K. Sankar, Research scholar in Manonmaniam Sundaranar University, Tirunelveli, Tamil Nadu, India.
2Dr. K.Nirmala, Computer Science, Quaid-e-Millet College, Chennai Tamil Nadu, India.
Manuscript received on August 02, 2013. | Revised Manuscript received on August 27, 2013. | Manuscript published on September 05, 2013. | PP: 108-110 | Volume-3, Issue-4, September 2013. | Retrieval Number: D1787093413/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In this paper, an efficient automated microcalcification classification system for breast cancer in mammograms using Non Subsampled Contourlet Transform (NSCT), Single Value Decomposition (SVD), Jacobi Moments and Support Vector Machine (SVM) is presented. The image is enhanced by using the preprocessing technique Non Subsampled Contourlet Transform (NSCT). The classification of microcalcification is achieved by extracting the features by using SVD and Jacobi moments and the outcomes are used as an input to the SVM classifier for classification.
Keywords: Clustering, K-means, NSL-KDD Dataset, WEKA.