STAR: A Structure and Texture Aware Retinex Model

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 p...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing 2020-01, Vol.29, p.1-1
Main Authors: Xu, Jun, Hou, Yingkun, Ren, Dongwei, Liu, Li, Zhu, Fan, Yu, Mengyang, Wang, Haoqian, Shao, Ling
Format: Article
Language:English
Subjects:
abc
Algorithms
Decomposition
Derivatives
Illumination
Image enhancement
Optimization
Reflectance
Regression analysis
Retinex (algorithm)
Texture mapping
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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
1941-0042
DOI:10.1109/TIP.2020.2974060