Published Paper Details:

In some medical applications where a tissue of interest covers a large fraction of the image or a prior knowledge on the Region of Interest (ROI) is available, extracting features from the image is sufficient. However in the general case, one would like to identify features for each tissue in the image. This would require prior image segmentation. Medical image segmentation is one of the most challenging problems in medical image analysis and a very active research topic. Therefore, there is no algorithm available in the general case for isolating medical image regions [1]. This paper presents an accurate method for extracting texture features from mammographic images for classification. As a first step, segmentation is used which is based on morphological and filtering operations. Extraction of 26 texture features from those regions. Classification of the images is done into two classes: normal and abnormal. SVM classifier is used for classification. Two kernels named Gaussian RBF kernel and Polynomial kernel are used. Experiments held on MIAS (Mammographic Images Analysis Society) dataset.