Hybrid wavelet transform I and II combined with contrast limited adaptive histogram equalization for image enhancement

Abstract

Image enhancement is one of the important part of image processing. Proposed research presents an image enhancement method, named CLAHE-HWT, which combines the Contrast Limited Adaptive Histogram Equalization (CLAHE) with Hybrid Wavelet Transform Type I and II (HWT I, II). The method includes, the original image is decomposed into low-frequency and high-frequency components by HWT II. Then, we enhance the low-frequency coefficients using CLAHE and keep the high-frequency coefficients unchanged to limit noise enhancement. Finally, reconstruct the image by taking inverse HWT of the new coefficients. In order to counteract over-enhancement, the recreated and original images are averaged using an originally proposed weighting factor. Two orthogonal transforms combine to form a hybrid wavelet. Here different orthogonal transforms are used like Kekre, Walsh, Cosine, Hartley and Haar in 5 × 4 combinations total 20 hybrid wavelets of type II. This research compares all the 20 combinations of HWT I and 20 HWT II to find out the best combination of HWT with CLAHE. Experimental results demonstrate CLAHE-HWT shows better results for noise depression and avoid over enhancement.