Contrast enhancement by object based Histogram Equalization

Abstract

Contrast enhancement techniques are used for improving visual quality of low contrast images. Histogram Equalization (HE) method is one such technique used for contrast enhance nt. As conventional HE processes the whole image, it may cause ill-effects such as washed out appearance and false contouring due to the significant change in brightness. So HE is not suitable for consumer electronic products directly. This paper proposes a variant of histogram equalization that tries to identify foreground and background pixels of an image and performs bi-histogram equalization on the means of them. The proposed method enhances the standard test images better than the methods available in the literature and has been validated by the performance measures like psnr, contrast and tenengrad.