Enhancement of Nighttime Image Visibility Using Wavelet Fusion of Equalized Color Channels and Luminance with Kekre’s LUV Color Space

Abstract

The usage of digital images is growing because of the benefits possessed by digital images in many ways in day to day life. But not all the images captured have a filmic appearance that pleases the human eye. Dissatisfaction is mainly because of noise addition, bad illumination where the captured image is either extra dark or bright, which leads to the need of enhancement in the quality of images. The motivation behind enhancement of image is to grasp the hidden information which is unavailable during image acquisition due to improper light conditions. One way to do so is enhancing the contrast of poorly illuminated images. In this paper, a new technique is presented which fuses HE enhanced image with proposed algorithm using wavelet transform. The results are tested on 240 images of 12 different categories ExDark dataset. Performance measures used are Entropy, NIQE and BRISQUE.