Image De-noising and Edge Segmentation using Bilateral Filtering and Gabor-cut for Edge Representation of a Breast Tumor

Abstract

Breast cancer is the globe’s initial highest death-causing cancer in women which is given to the international agency of analysis on cancer-the World Health organization and the American cancer society. This paper expounds on the classification of breast cancer from the mammogram images MLO view. This paper proposes a technique to de-noise the mammogram Images using the improved bilateral filter and improved canny edge detection for the breast tumor. The region from the image is then selected using the New Gabor cut algorithm. The Mean Square Error and Structural Similarity are proposed to be improved using the improved Bilateral filter. The approximation in the background and foreground extraction for the Region of Interest is performed proposing the New Gabor cut algorithm and so the Edges were drawn predominantly by using the improved Canny Edge Detection. The Mean Squared Error and Similarity Index is 15.65 and 0.91. Doing This Pre-processing will facilitate further research in the Feature Extraction process to detect breast cancer in an efficient way.