Various subjects that are paired usually are not identically the same, asymmetry is perfectly normal but sometimes asymmetry can be noticeable too much. Breast asymmetry is one of such examples, which is a difference in breast size or shape, or both. Asymmetry analysis of beast has great importance because it is not only indicator for breast cancer but also predict future potential risk for the same. In our research work, we have concentrated to segment the anatomical regions of breast, isolate the border line of each to investigate the presence of abnormal mass and asymmetry of anatomical regions in a pair of mammogram. We used three techniques i.e. contrast enhancement, binary homogeneity enhancement with uniform color reduction and seeded region growing algorithm for the same. The proposed technique, we have obtained 90% of near accurate result including accurate results on selected 50 numbers different mammograms of MIAS Database. To summarize, the results obtained by the method show that it is a robust approach but it can be improved in terms of accuracy.

Mammogram MIAS Database CLAHE BHEA Seeded Region Growing