A Probabilistic Method for Image Enhancement With Simultaneous Illumination and Reflectance Estimation

Fu, Xueyang; Liao, Yinghao; Zeng, Delu; Huang, Yue; Zhang, Xiaoping; Ding, Xinghao

doi:10.1109/tip.2015.2474701

Cited by 360 publications

(199 citation statements)

References 38 publications

Supporting

Mentioning

197

Contrasting

Unclassified

Order By: Relevance

“…Comparison Methods and Datasets. We compare the proposed STAR model with previous competing low-light image enhancement methods, including HE [47], MSRCR [19], Contextual and Variational Contrast (CVC) [48], Naturalness Preserved Enhancement (NPE) [5], LDR [49], SIRE [32], MF [50], WVM [7], LIME [6], and JieP [8]. We evaluate these methods on 35 images collected from [6]- [8], [32], [50], and on the 200 images in [5].…”

Section: Other Applicationsmentioning

confidence: 99%

See 1 more Smart Citation

STAR: A Structure and Texture Aware Retinex Model

Hou

Ren

et al. 2020

IEEE Trans. on Image Process.

202

114

View full text Add to dashboard Cite

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 propose to utilize the exponentiated derivatives (with an exponent γ) of an observed image to generate a structure map when being amplified with γ > 1 and a texture map when being 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 on the local derivatives. 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 in an alternating minimization manner. Each sub-problem is transformed into a vectorized least squares regression with closed-form solution. Comprehensive experiments demonstrate that, the proposed STAR model produce better quantitative and qualitative performance than previous competing methods, on illumination and reflectance estimation, low-light image enhancement, and color correction.

show abstract

Section: Other Applicationsmentioning

confidence: 99%

“…We compare the proposed STAR model on the two sets of images previously mentioned. From [8], [32], [50] and 200 low-light images provided in [5].…”

Section: A Low-light Image Enhancementmentioning

confidence: 99%

STAR: A Structure and Texture Aware Retinex Model

Hou

Ren

et al. 2020

IEEE Trans. on Image Process.

202

114

View full text Add to dashboard Cite

show abstract

“…Instead, the degraded images are processed by traditional image processing methods in order to remove noise and enhance the color, sharpness, or contrast. Image enhancement can be achieved by techniques such as the Histogram Equalization (Agaian and Roopaei, 2013), Unsharp Masking (Deng, 2011), or the Probability-based (Fu et al, 2015) method. One of the approaches in image enhancement techniques is to remove uneven illumination and preform color balancing.…”

Section: Dehazingmentioning

confidence: 99%

Impact of Dehazing on Underwater Marker Detection for Augmented Reality

et al. 2018

View full text Add to dashboard Cite

Underwater augmented reality is a very challenging task and amongst several issues, one of the most crucial aspects involves real-time tracking. Particles present in water combined with the uneven absorption of light decrease the visibility in the underwater environment. Dehazing methods are used in many areas to improve the quality of digital image data that is degraded by the influence of the environment. This paper describes the visibility conditions affecting underwater scenes and shows existing dehazing techniques that successfully improve the quality of underwater images. Four underwater dehazing methods are selected for evaluation of their capability of improving the success of square marker detection in underwater videos. Two reviewed methods represent approaches of image restoration: Multi-Scale Fusion, and Bright Channel Prior. Another two methods evaluated, the Automatic Color Enhancement and the Screened Poisson Equation, are methods of image enhancement. The evaluation uses diverse test data set to evaluate different environmental conditions. Results of the evaluation show an increased number of successful marker detections in videos pre-processed by dehazing algorithms and evaluate the performance of each compared method. The Screened Poisson method performs slightly better to other methods across various tested environments, while Bright Channel Prior and Automatic Color Enhancement shows similarly positive results.

show abstract

“…The noisy image decomposed into sub bands by using six levelsof DT-CWT. The possible coefficients with phase information are +75º, +45º, +15º,-15º,-45º and -75º [14][15][16][17].For the first level, specially designed real filters with real coefficients were used.For the remaining levels, these phase coefficients were used. For this purpose, the sample process repeated 5 times for Real and Imaginary parts individually.…”

Section: Dual-tree Complex Wavelet Transform (Dt-cwt)mentioning

confidence: 99%

A Systematic Approach for Image Enhancement on Landsat 8 Imagery

2017

IJAERD

View full text Add to dashboard Cite

A Probabilistic Method for Image Enhancement With Simultaneous Illumination and Reflectance Estimation

Cited by 360 publications

References 38 publications

STAR: A Structure and Texture Aware Retinex Model

STAR: A Structure and Texture Aware Retinex Model

Impact of Dehazing on Underwater Marker Detection for Augmented Reality

A Systematic Approach for Image Enhancement on Landsat 8 Imagery

Contact Info

Product

Resources

About