Mammographic Image Enhancement analysis using Fuzzy Logic

Abstract

Breast cancer figures among the leading causes of cancer related deaths among women. Detection of cancer
at the initial stages increases the probability of survival of the patient. For this detection, mammography is done.
However most of the cases go unnoticed either due to lower contrast variations or due to noise in mammogram
images.The main objective of image enhancement is to improve desired characteristics of an image and make it visually
better. This paper proposes a method for quantifying the various enhancement techniques used for cancer detection in
mammogram images. The paper proposes the use of fuzzy logic to realize this objective. First the mammogram is
enhanced using different enhancement techniques. In next step, the frequency domain comparison of the original image
and each of the enhanced image is performed. Using this comparison we obtain the variation in the frequencies of the
enhanced image as compared with the original image. Finally these variations are then quantized using the fuzzy sets to
provide us the merit of the different techniques, of their degree of enhancement.