ABSTRACT

Magnetic Resonance Images (MRI) are used by Physician to analyse the body structures to find the diseases & to monitor the treatments. For effective analysis, they should consist of all relevant information in a better visualization format. However, MRI images suffer from poor dynamic range which affects the visible quality due to low contrast. Medical Image enhancement is a powerful tool to increase the perception of information to provide better diagnosis. In this study, different histogram equalization techniques like Global Histogram Equalization (GHE), Brightness Preserving Bi-Histogram Equalization (BBHE), Dualistic Sub-Image Histogram Equalization (DSIHE), Recursive Mean Separate Histogram Equalization (RMSHE), Brightness Preserving Dynamic Histogram Equalization (BPDHE), Brightness Preserving Dynamic Fuzzy Histogram Equalization (BPDFHE)and Contrast-limited Adaptive Histogram Equalization (CLAHE) are applied to proton density weighted magnetic resonance image to enhance the contrast and their performance is compared in terms Discrete Entropy (DE), Measure of Enhancement (EME), Average Brightness (AB) and Pixel Distance (PD). Based on the performance metrics, the best histogram equalization technique in enhancing the contrast of PD weighted MRI images is determined.

Keywords: - Average Brightness, Contrast Enhancement, Discrete Entropy, Histogram Equalization, Magnetic Resonance Images, Measure of Enhancement and Pixel Distance