Segmentation and Classification of Mammogram into Normal and Abnormal using Texture Features
B. V. Divyashree1, C. A. Soujanya2, M. R. Keerthana3, M. Naveen4, G. Hemantha Kumar5

1B. V. Divyashree, DOS in Computer Science, University of Mysore, Manasagangothri, Mysuru, Karnataka, India.
2C. A. Soujanya, DOS in Computer Science, University of Mysore, Manasagangothri, Mysuru, Karnataka, India.
3M. R. Keerthana, DOS in Computer Science, University of Mysore, Manasagangothri, Mysuru, Karnataka, India.
4M. Naveen, DOS in Computer Science, University of Mysore, Manasagangothri, Mysuru, Karnataka, India.
5G. Hemantha Kumar, DOS in Computer Science, University of Mysore, Manasagangothri, Mysuru, Karnataka, India.

Manuscript received on April 02, 2020. | Revised Manuscript received on April 21, 2020. | Manuscript published on May 30, 2020. | PP: 1005-1008 | Volume-9 Issue-1, May 2020. | Retrieval Number: A1964059120/2020©BEIESP | DOI: 10.35940/ijrte.A1964.059120
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. 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: Breast cancer is known to be a fatal disease since decades in women worldwide. Mammography is an effective tool used for the detection of breast cancer in the early stage. Computer aided tools helps medical field by ruling out the false identification of cancer cells in mammograms. Breast region extraction and classification of the extracted region into normal and abnormal is a crucial step in mammographic based diagnosis of breast cancer. Hence, in the proposed paper a method for segmentation of breast region and classification of breast region is presented. Breast region extraction is performed using Otsu’s thresholding method and intensity adjustments, enhancement is performed by Contrast Limited Adaptive Histogram Equalization (CLAHE). Gray Level Co-Occurrence Matrix (GLCM), Histogram of Oriented Gradients (HOG), Local Binary Pattern (LBP) features are extracted to classify the breast region using K-Nearest Neighbors (KNN) classifier. The proposed algorithm is tested on Mammographic Image Analysis Society (MIAS) dataset, obtained minimum Root Mean Square Error (RMSE) and maximum Peak Signal-to-Noise Ratio (PSNR). For classification, 80.12% of accuracy is obtained with TPR and FPR of about 0.8317 and 0.3412 respectively. 
Keywords: Mammogram, Segmentation, Feature extraction, Otsu’s thresholding, Gray Level Co-Occurrence Matrix (GLCM), Histogram of Oriented Gradients (HOG), Local Binary Pattern (LBP).
Scope of the Article: Classification