Contrast Enhancement Based on Intrinsic Image Decomposition

Abstract

In this paper, we propose to introduce intrinsic image decomposition priors into decomposition models for contrast enhancement. Since image decomposition is a highly ill-posed problem, we introduce constraints on both reflectance and illumination layers to yield a highly reliable solution. We regularize the reflectance layer to be piecewise constant by introducing a weighted `1 norm constraint on neighboring pixels according to the color similarity, so that the decomposed reflectance would not be affected much by the illumination information. The illumination layer is regularized by a piecewise smoothness constraint. The proposed model is effectively solved by the Split Bregman algorithm. Then, by adjusting the illumination layer, we obtain the enhancement result. To avoid potential color artifacts introduced by illumination adjusting and reduce computing complexity, the proposed decomposition model is performed on the value channel in HSV space.

Existing System

Single-Scale Retinex (SSR), Multiscale Retinex (MSR).

Proposed System

In this paper, we propose to enhance images by estimating illumination and reflectance layers through intrinsic image decomposition. On the one hand, we constrain the reflectance layer to be piecewise constant according to the color similarity. On the other hand, the illumination layer is enforced to be locally smooth. Since the decomposition model is nonconvex and non-differential, we adopt the Split Bregman algorithm to iteratively solve this problem. After decomposition, we perform Gamma correction on the illumination layer to boost the details globally. Then we adopt CLAHE to further enhance local details. Thus the contrast is enhanced by intrinsic image decomposition.

Architecture

BLOCK DIAGRAM