STAR: A Structure and Texture Aware Retinex Model

Document Type

Article

Source of Publication

IEEE Transactions on Image Processing

Publication Date

1-1-2020

Abstract

© 2020 IEEE. Retinex theory is developed mainly to decompose an image into the illumination and reflectance components by analyzing local image derivatives. In this theory, larger derivatives are attributed to the changes in reflectance, while smaller derivatives are emerged in the smooth illumination. In this paper, we utilize exponentiated local derivatives (with an exponent γ ) of an observed image to generate its structure map and texture map. The structure map is produced by been amplified with γ > 1, while the texture map is generated by been shrank with γ < 1. To this end, we design exponential filters for the local derivatives, and present their capability on extracting accurate structure and texture maps, influenced by the choices of exponents γ. The extracted structure and texture maps are employed to regularize the illumination and reflectance components in Retinex decomposition. A novel Structure and Texture Aware Retinex (STAR) model is further proposed for illumination and reflectance decomposition of a single image. We solve the STAR model by an alternating optimization algorithm. Each sub-problem is transformed into a vectorized least squares regression, with closed-form solutions. Comprehensive experiments on commonly tested datasets demonstrate that, the proposed STAR model produce better quantitative and qualitative performance than previous competing methods, on illumination and reflectance decomposition, low-light image enhancement, and color correction. The code is publicly available at https://github.com/csjunxu/STAR.

ISSN

1057-7149

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Volume

29

First Page

5022

Last Page

5037

Disciplines

Computer Sciences

Keywords

color correction, low-light image enhancement, Retinex decomposition

Indexed in Scopus

no

Open Access

yes

Open Access Type

Green: A manuscript of this publication is openly available in a repository

Share

COinS