Paper Title
Gabor Wavelet Based Features For Mammogram Analysis And Classification Of Breast Cancer
Abstract
Breast cancer is the most commonly occurring cancer in women. Early detection of breast cancer is important step
in diagnosis of the abnormalities which may reduce the mortality rate. It can be achieved using digital mammography. Digital
mammography has become the most effective techniques for the early detection of breast cancer. . Mammography is most
reliable and widespread method for early detection of breast cancer. This system includes Preprocessing on mammogram
image and uses wavelet feature extraction to improve sensitivity. It involves three major steps-Preprocessing, Feature
Extraction and Classification. Gabor wavelets based features are extracted from medical mammogram images representing
normal tissues or benign and malign tumors. After completing preprocessing, Principal Component Analysis (PCA) is used to
extract feature vectors of all images in the database. PCA is a useful statistical technique that has found application in fields
such as face recognition and image compression, and is a common technique for finding patterns in data of high dimension.
These extracted features are used for classification of mammogram into malignant and benign. The SVM classifier is used for
classification.
Index Terms— Gabor Wavelet, Mammogram images, Principal Component Analysis , Suport Vector Machine.