Enhancement of the Low-Light Digital Image through the Fuzzy Local Binary Pattern Technique

Abstract

This paper proposes a new technique that improves a low-light image’s contrast more effectively. First, the image has to be normalized with the help of the fuzzy normalization technique, to the fuzzy the image then the intensity of each pixel in the image is adjusted on the 33 neighborhood pixels according to a threshold value by using two fuzzy membership functions. Finally, the image is defuzzified to get an enhanced image. The proposed method is compared with the already existing enhancement methods, like histogram equalization (HE), contrast-limited adaptive histogram equalization (CLAHE), intuitionistic fuzzy sets (IFS), and interval-valued intuitionistic fuzzy sets (IVIFS). The resultant images are evaluated by the similarity measures, namely, Entropy, structural similarity index (SSIM), Pearson correlation coefficient (PCC), and feature similarity index measure (FSIM). The experimental results show that the proposed method gives a better enhancement when compared to other existing methods.