Retinex processing for automatic image enhancement

By Z. Rahman, D. J. Jobson, G. Woodell. IS&T/SPIE Electronic Imaging, 2002

902 citations recorded by the source corpus.

Subfields: Biophysics, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/4f809e9a024e85d1d83213cd6393168654c866f0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biophysics

1. Emmanuel Okafor
2. Xin Fan
3. Zhongxuan Luo
4. Jiaya Jia
5. Long Ma
6. Sabine Süsstrunk
7. Junaed Sattar
8. Lambert Schomaker

In Computer Vision and Pattern Recognition

1. Ming-Hsuan Yang
2. Chongyi Li
3. Jiaya Jia
4. Luc Van Gool
5. Chen Change Loy
6. Ling Shao
7. Dacheng Tao
8. Xiaogang Wang

In Media Technology

1. Chongyi Li
2. Risheng Liu
3. Peixian Zhuang
4. Emmanuel Okafor
5. Xin Fan
6. Zhongxuan Luo
7. Jiaya Jia
8. Long Ma

Citations in the corpus

• An analysis of rotation matrix and colour constancy data augmentation in classifying images of animals (2018, positive): “An improvement was made in the MSR by the authors in Rahman, Jobson, and Woodell (2004), who incorporated colour restoration to produce a multi-scale retinex for colour restoration (MSRCR).”
• High dynamic range image rendering with a retinex-based adaptive filter (2006, methodology): “Other the methods that are based on the same smooth illuminant assumption [5], [6], [12], [16] suffer from the same drawback.”
• Fast Underwater Image Enhancement for Improved Visual Perception (2019, methodology): “Classical approaches use hand-crafted filters to enforce local color constancy and improve contrast/lightness rendition [20].”
• Underwater Image Enhancement With Hyper-Laplacian Reflectance Priors (2022, positive): “Like center/surround retinex methods [37], [38], a Gaussian lowpass filtering of V is used to be an initialization of I 0 .”
• SNR-Aware Low-light Image Enhancement (2022, background): “Retinex-based methods, which treat the reflectance component as plausible approximation for image enhancement, are able to produce more realistic and natural results [28, 35].”
• Toward Fast, Flexible, and Robust Low-Light Image Enhancement (2022, positive): “Generally, Retinex theory [16] depicts the basic physical law for low-light image enhancement, that is, low-light observation can be decomposed into illumination and reflectance (i.e., clear image).”
• An Experiment-Based Review of Low-Light Image Enhancement Methods (2020, methodology): “…image, and panels (b)-(r) display the results of many enhancement methods: Gamma correction [3], AHE [78], WT [166], BIMEF [223], CegaHE [102], CRM [225], CVC [89], Dong et al. [229], MBLLEN [263], HMF [101], LIME [13], MF [219], HE [66], MSRCP [127], MSRCR [115], NPE [136], and SRIE [126].”
• A Probabilistic Method for Image Enhancement With Simultaneous Illumination and Reflectance Estimation (2015, methodology): “As shown in Table 2, the proposed method outperforms ACE, MSRCR, Kimmel’s method and Bayesian method in preserving the naturalness.”
• Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement (2020, positive): “There are also various classical methods consider Retinex theory [26] and introduce different prior regularized optimization models to characterize the structures of the illumination and reflectance image layers [6, 9, 13, 46, 20].”