A switched view of Retinex: Deep self-regularized low-light image enhancement

Jiang, Zhuqing; Li, Haotian; Liu, Liangjie; Men, Aidong; Wang, Haiying

doi:10.1016/j.neucom.2021.05.025

Cited by 48 publications

(21 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, Jiang Y. et al [11] proposed an unsupervised Gan (EnlightenGAN), which does not require paired low-/normal-light datasets during training and can restore image brightness well, but needs to carefully select a large number of unpaired low-/normal-light datasets. Jiang Z. et al [13] proposed a new self-regularization method based on Retinex. The training process only requires low-light images, which reduces the difficulty of collecting datasets.…”

Section: Deep Learning Methodsmentioning

confidence: 99%

“…Figure 2 shows the visual quality comparison between our method and several state-of-the-art methods. They are RetinexNet [6] and EnlightenGAN [11] trained with the original dataset, and ZeroDCE [12] and Retinex-SR [13] trained with the dataset used in this paper. To facilitate observation, some distinct details are enlarged.…”

Section: Visual Quality Comparisonmentioning

confidence: 99%

“…Although these methods have achieved promising results, it is difficult to obtain a dataset. To solve the problem of difficult acquisition of training datasets, self-supervised learning is introduced into some methods [12] [13]. These methods have the same enhancement effect as supervised learning methods, but for low-light images with uneven illumination distribution, there are enhancement deficiencies Excessive enhancement, or color distortion.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Retinex-SIE: self-supervised low-light image enhancement method based on Retinex and homomorphic filtering transformation

Yang¹,

Qian²,

Liu³

2023

Third International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022)

View full text Add to dashboard Cite

Low-light images suffer from low visibility, much noise, uneven illumination distribution, etc. Many existing methods have problems such as over enhancement or insufficient detail enhancement when dealing with low-light images with uneven illumination distribution. To remedy the above shortcomings, we proposes a Retinex-based self-supervised lowlight image enhancement model (Retinex-SIE), which is mainly composed of three parts: Retinex-based self-fsupervised image decomposition network (Retinex-DNet), nonlinear conditional illumination enhancement function (NCIEF), and image reconstruction (IR). First, a uniform illumination image of the same scene with the low-light image is generated by homomorphic filtering transformation, and the low-light image and the uniform illumination image are input into Retinex-DNet for decomposition to obtain reflectivity, noise and illumination. Then, NCIEF is used to enhance the illumination after decomposition. Finally, the final enhanced image is obtained by multiplying the decomposed reflectance and the enhanced illumination. Experiments on severa challenging low-light image datasets show that Retinex-SIE proposed in this paper can better handle low-light images with uneven illumination distribution, and avoid problems such as excessive enhancement or insufficient detail enhancement.

show abstract

Section: Deep Learning Methodsmentioning

confidence: 99%

Section: Visual Quality Comparisonmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Retinex-SIE: self-supervised low-light image enhancement method based on Retinex and homomorphic filtering transformation

Yang¹,

Qian²,

Liu³

2023

Third International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022)

View full text Add to dashboard Cite

show abstract

“…The retinex theory is a widely used image enhancement algorithm based on human visual perception, which is determined by the color of the image, not by light and other factors [19]. The calculation formula is as Eq.…”

Section: Ssr Algorithmmentioning

confidence: 99%

Edge Detection of COVID-19 CT Image Based on GF_SSR, Improved Multiscale Morphology, and Adaptive Threshold

Hou¹,

Jia²,

Li³

et al. 2022

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

Edge detection is an effective method for image segmentation and feature extraction. Therefore, extracting weak edges with the inhomogeneous gray of Corona Virus Disease 2019 (COVID-19) CT images is extremely important. Multiscale morphology has been widely used in the edge detection of medical images due to its excellent boundary detection accuracy. In this paper, we propose a weak edge detection method based on Gaussian filtering and singlescale Retinex (GF_SSR), and improved multiscale morphology and adaptive threshold binarization (IMSM_ATB). As all the CT images have noise, we propose to remove image noise by Gaussian filtering. The edge of CT images is enhanced using the SSR algorithm. In addition, based on the extracted edge of CT images using improved Multiscale morphology, a particle swarm optimization (PSO) algorithm is introduced to binarize the image by automatically getting the optimal threshold. To evaluate our method, we use images from three datasets, namely COVID-19, Kaggle-COVID-19, and COVID-Chestxray, respectively. The average values of results are worthy of reference, with the Shannon information entropy of 1.8539, the Precision of 0.9992, the Recall of 0.8224, the F-Score of 1.9158, running time of 11.3000. Finally, three types of lesion images in the COVID-19 dataset are selected to evaluate the visual effects of the proposed algorithm. Compared with the other four algorithms, the proposed algorithm effectively detects the weak edge of the lesion and provides help for image segmentation and feature extraction.

show abstract

“…The idea of decomposition was also used by other authors who have decomposed the picture not according to the Retinex theory but in some color spaces. Jiang et al [24], with their Retinex-2021, enhanced the value channel of the HSV color space and preserved color channels. This method has the potential to generate desirable results; however, chromatic aberrations existing in images captured under low-light conditions are not considered.…”

Section: Introductionmentioning

confidence: 99%

Iterative Retinex-Based Decomposition Framework for Low Light Visibility Restoration

et al. 2023

View full text Add to dashboard Cite

Images captured in low-light conditions often suffer from low brightness, low signal-to-noise ratio, low contrast, a narrow gray range, and color distortion, which can significantly impact human perception and limit the performance of various computer vision applications. Most existing low-light image restoration methods require assistance with a color cast, local over-exposure, glow, and artificial light sources. This paper proposes a new framework called RSD-Net, incorporating several innovative blocks, including a novel iterative Retinex network decomposition and enhancement algorithms, to improve the visibility and quality of images captured in low-light or nighttime conditions. We have extensively evaluated our proposed method on various benchmarking datasets and under different real-world scenarios, including challenging conditions such as glow, artificial light sources, low illumination, and noise. Moreover, we have evaluated our method on a face detection algorithm using extremely dark images and compared its performance with other state-of-the-art methods. The simulation results show that our proposed framework achieves a noticeable improvement compared to other low-quality image restoration techniques and enhances face detection accuracy in low-quality environments. The proposed framework has the potential to substantially impact human perception and enhance the performance of numerous computer vision applications.

show abstract

A switched view of Retinex: Deep self-regularized low-light image enhancement

Cited by 48 publications

References 40 publications

Retinex-SIE: self-supervised low-light image enhancement method based on Retinex and homomorphic filtering transformation

Retinex-SIE: self-supervised low-light image enhancement method based on Retinex and homomorphic filtering transformation

Edge Detection of COVID-19 CT Image Based on GF_SSR, Improved Multiscale Morphology, and Adaptive Threshold

Iterative Retinex-Based Decomposition Framework for Low Light Visibility Restoration

Contact Info

Product

Resources

About