A Robust Method to Enhance Degraded Color Images Under Diverse Conditions

This paper presents a Wavelet Transform and Multi-Scale Retinex (WT-MSR) based color image enhancement method. The proposed WT-MSR method initially transforms the colored RGB image into the HSI color space. In the HSI color space, the low-frequency coefficients in the wavelet domain are processed by using Contrast Limited Adaptive Histogram Equalization (CLAHE). Later, the high-frequency components are scaled and enhanced by expanding contrast in the wavelet domain. Meanwhile, the saturation component of the HSI converted image is processed through enhanced intensity factor followed by the conversion of the image into the RGB color space. In the RGB color space, the PCA is applied to isolate the luminance channel. The obtained luminance channel is further processed with three steps of the SSRs. Finally, the contrast stretching is used to further enhance the contrast of the image to obtain the pleasing effects. Simulation results on NASA Retinex dataset reveal that the proposed WT-MSR algorithm outperforms some of the existing methods in terms of the image quality and statistical methods compared therein.