STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Image Processing & Pattern Recognition Progress

Enhancement of Digital Mammograms Using Intuitionistic Fuzzy Entropy Function

  1. Jyoti Dabass
  2. Manju Dabass
  3. Bhupender Singh Dabass

Abstract

A novel intuitionistic fuzzy entropy-based algorithm is developed for increasing the contrast of digital mammograms. The contrast enhancement helps in the early detection of masses and microcalcification in tissues thus paving the way for the auxiliary diagnosis of breast cancer. The current techniques for the enhancement of digital mammograms do not consider the uncertainty in pixel intensities of mammograms. The proposed technique aims at enhancing the mammograms using intuitionistic fuzzy entropy. To enhance contrast, Contrast Limited Adaptive Histogram Equalization (CLAHE) is implemented on small regions. The quantitative measures such as Discrete Entropy, Absolute Mean Brightness Error, Absolute Mean Brightness Coefficient, and Contrast Improvement Index and qualitative measure like visual quality are shown to be better than those of the state-of-the-art techniques. An application of the Hanman classifier on the enhanced images gives better classification accuracy than that of classifiers like support vector machine and convolutional neural network.

Keywords

Support