Retinex Model Research Articles

Joint-Prior-Based Uneven Illumination Image Enhancement for Surface Defect Detection

Images in real surface defect detection scenes often suffer from uneven illumination. Retinex-based image enhancement methods can effectively eliminate the interference caused by uneven illumination and improve the visual quality of such images. However, these methods suffer from the loss of defect-discriminative information and a high computational burden. To address the above issues, we propose a joint-prior-based uneven illumination enhancement (JPUIE) method. Specifically, a semi-coupled retinex model is first constructed to accurately and effectively eliminate uneven illumination. Furthermore, a multiscale Gaussian-difference-based background prior is proposed to reweight the data consistency term, thereby avoiding the loss of defect information in the enhanced image. Last, by using the powerful nonlinear fitting ability of deep neural networks, a deep denoised prior is proposed to replace existing physics priors, effectively reducing the time consumption. Various experiments are carried out on public and private datasets, which are used to compare the defect images and enhanced results in a symmetric way. The experimental results demonstrate that our method is more conducive to downstream visual inspection tasks than other methods.

Non-Local Retinex Based Dehazing and Low Light Enhancement of Images

We know that a vast amount of research has recently been done on dehazing single images. More work is done on day-time images than night-time images. Also, enhancement of low light images is another area in which lots of research going on. In this paper, a simple yet effective unified variational model is proposed for dehazing of day and night images and low-light enhancement based on non-local global variational regularization. Given the relation between image dehazing and retinex, the haze removal process can minimize a variational retinex model. Estimating of ambient light and transmission maps is a key step in modern dehazing methods. Atmospheric light is not uniform and constant for hazy night images, as night scenes often contain multiple light sources. Often lit and non-illuminated regions have different colour characteristics and cause total variation colour distortion and halo artifacts. Our work directly implements a non-local retinal model based on the L2 norm that simulates the average activity of inhibitory and excitatory neuronal populations in the cortex to overcome this problem. This potential biological feasibility of the L2 norm of our work is divided into two parts using a filtered gradient approach, the reflection sparse prior and the reflection gradient fidelity before the observed image gradient. This unified framework of NLTV-Retinex and DCP efficiently performs low-light enhancement and dehazing of day and night images. We show results obtained using our method on daytime and night-time images and a low-light image dataset. We quantitatively and qualitatively compare our results with recently reported methods, which demonstrate the effectiveness of our method.

CODEN: combined optimization-based decomposition and learning-based enhancement network for Retinex-based brightness and contrast enhancement.

In this paper, we present a novel low-light image enhancement method by combining optimization-based decomposition and enhancement network for simultaneously enhancing brightness and contrast. The proposed method works in two steps including Retinex decomposition and illumination enhancement, and can be trained in an end-to-end manner. The first step separates the low-light image into illumination and reflectance components based on the Retinex model. Specifically, it performs model-based optimization followed by learning for edge-preserved illumination smoothing and detail-preserved reflectance denoising. In the second step, the illumination output from the first step, together with its gamma corrected and histogram equalized versions, serves as input to illumination enhancement network (IEN) including residual squeeze and excitation blocks (RSEBs). Extensive experiments prove that our method shows better performance compared with state-of-the-art low-light enhancement methods in the sense of both objective and subjective measures.

Automatic exposure correction algorithm for online silkworm pupae (Bombyx mori) sex classification

In the process of online sex identification and sorting of silkworm pupae by machine vision technology, the collected images of silkworm pupae gonad suffer underexposure or overexposure due to the biological characteristics of silkworm pupae and the mechanism movement. As a result, the partial texture characteristics of silkworm pupae gonad are not obvious and thus lead to a large error for the subsequent identification of male and female pupae. In view of the overexposed or underexposed problem existed in online image collecting of silkworm pupae gonad, an algorithm model is proposed in this paper. It can automatically determine whether the silkworm pupae gonad image has exposure problem according to the distribution law of gray values. Moreover, an extra correction model based on the combination of the Retinex (retina and cortex) model and the weighted least squares method is put forward to correcting the exposure of gonadal images. The experiment results demonstrate that the proposed algorithm not only can find the silkworm pupae gonad image with exposure problem completely and accurately, but also make the restored gonadal texture clearer. Furthermore, this algorithm has a good effect on the exposure correction of other objects. After the original data sets are processed by the algorithm, the correct sex identification rate in the classification network based on Resnet50 training reaches 90.52%. It is 7.08% higher than the original silkworm pupae gonad images, which can verify the effectiveness of the algorithm. And the recovery time of a single image is within 0.3 s, which can meet the needs of online automatic identification. The proposed algorithm is of great significance for the online male and female identification of silkworm pupae based on machine vision.

Evaluation of underwater image enhancement algorithms based on Retinex and its implementation on embedded systems

The improvement of underwater imaging has advanced significantly due to its contribution to marine engineering and underwater exploration. This fact has been reflected in recent years with the proposal of numerous algorithms that improve the quality of underwater images. A benchmarking of three algorithms based on the Retinex models implemented on five high-performance embedded systems is presented herein. These algorithms are the Single Scale Retinex Model (SSR), Multi-Scale Retinex Model (MSR), and the Multi-Scale Retinex Model with Color Restoration (MSRCR). These algorithms perform the histogram equalization to distribute pixels, reduce the predominant color, perform color and contrast correction, and achieve an automatic white balance to improve illumination. This paper employs five edge devices such as Beagle Board, Odroid-XU4, Raspberry Pi 4, Jetson Nano, and Jetson TX2 to enhance underwater images and benchmark their performance. Four quality metrics without a reference image such as UIQM, UCIQUE, BRISQUE and Entropy are used to evaluate the quality of the enhanced underwater images. The MSRCR algorithm achieves the best quality results when it is implemented on Jetson TX2 embedded system. It has a difference of 0.46 s in the processing time of 147 × 196 pixels images concerning a high-performance personal computer (PC). Implementing these algorithms on embedded systems offers an excellent cost-benefit ratio versus a traditional PC, considering image quality metrics, precision, accuracy, energy consumption, price, lightweight, size, portability, and reliability. These findings hold great promise for unmanned and self-propelled underwater vehicles with artificial vision for exploration.

Combining attention mechanism and Retinex model to enhance low-light images

Low-light image enhancement is challenging due to intractable problems such as color distortion and noise, which hide in the dark. Simply enhancing the brightness of dark areas will inevitably amplify hidden artifacts. We have observed more noise in the underexposed areas of images than in the normally exposed areas. Attention mechanism can be used to emphasize the vital information of the processed object and suppress some irrelevant information. Inspired by these observations, we propose a deep network that Combines Attention mechanism and Retinex (CA&R Net) model to enhance low-light images. Firstly, we develop an attention map to evaluate the degree of image underexposure and guide enhancement in a region-adaptive manner. This way, it can enhance underexposed areas and avoid over-enhancing normally exposed areas. Secondly, we use the reconstructed reflectance and low illumination to predict the illumination layers of the image jointly. This joint prediction utilizes the attention mechanism, making illumination adjustment achieve better results. The quantitative experimental results show that the CA&R Net can successfully handle noise, color distortion, and multiple types of degradation with the power of attention information. Moreover, both SSIM and PSNR are better than other advanced methods.

Joint enhancement and denoising in electronic speckle pattern interferometry fringe patterns with low contrast or uneven illumination via an oriented variational Retinex model.

Simultaneous speckle reduction and contrast enhancement for electronic speckle pattern interferometry (ESPI) fringe patterns is a challenging task. In this paper, we propose a joint enhancement and denoising method based on the oriented variational Retinex model for ESPI fringe patterns with low contrast or uneven illumination. In our model, we use the structure prior to constrain the illumination and introduce a fractional-order differential to constrain the reflectance for enhancement, then use the second-order partial derivative of the reflectance as the denoising term to reduce noise. The proposed model is solved using the sequential method to obtain piecewise smoothed illumination and noise-suppressed reflectance sequentially, which avoids remaining noise in the illumination and reflectance map. After obtaining the refined illuminance and reflectance, we substitute the gamma-corrected illuminance into the camera response function to further adjust the reflectance as the final enhancement result. We test our proposed method on two non-uniform illumination computer-simulated and two low-contrast experimentally obtained ESPI fringe patterns. Finally, we compare our method with three other joint enhancement and denoising variational Retinex methods.

Rethinking Low-Light Enhancement via Transformer-GAN

Images and videos shot in low light are often accompanied by severe image degradation, such as color noise, chromatic aberrations and loss of details. Most existing convolutional neural network (CNN)-based low-light enhancement methods focus on decomposing the image into illumination and reflection parts via the Retinex model, but these methods often fail to adequately consider controlling noise during enhancement and perform poorly in the face of complex lighting environments. In this letter, we propose a powerful Vision Transformer-based Generative Adversarial Network (Transformer-GAN) for enhancing low-light images. Transformer-GAN consists of two subnets as follows: (1) the feature extraction is achieved by an iterative multi-branch network in the feature extraction subnet, and (2) the enhancement is completed in the image reconstruction subnet. The innovative core works are multi-head multi-covariance self-attention (MHMCA) and Light feature-forward module structures (LFFM) in Transformer-GAN. Experiments demonstrate that our method outperforms state-of-the-art low-light enhancement methods on popular low-light datasets.

Blind Adaptive Structure-Preserving Imaging Enhancement for Low-Light Condition

In this letter, a novel and effective algorithm based on Retinex model is proposed for low-light image enhancement, named Blind Adaptive Structure-Preserving Image Enhancement (BASSY). The low-light image enhancement is still a challenging task because the decomposition of images into light components and reflection components is an ill-posed problem. BASSY adopts a content-adaptive guided filtering based on local variances to estimate the proper illumination map. The salient features of the proposed approach are: (1) For the illumination component, the overall structure in the low-light image is preserved and the texture details are smoothed. (2) The reflectance is estimated without logarithmic transformation to reduce the computational burden and to avoid over-smoothing the reflectance component. (3) The adaptive gamma correction for the illumination map is used to reconstruct the enhanced image. (4) BASSY can be implemented efficiently due to the low computation complexity Ο(N). Experimental results on six public datasets show that the enhanced images by the BASSY exhibit higher naturalness and better visual quality than six state-of-the-art methods.

Enhancement and denoising method for low-quality MRI, CT images via the sequence decomposition Retinex model, and haze removal algorithm

The visibility and analyzability of MRI and CT images have a great impact on the diagnosis of medical diseases. Therefore, for low-quality MRI and CT images, it is necessary to effectively improve the contrast while suppressing the noise. In this paper, we propose an enhancement and denoising strategy for low-quality medical images based on the sequence decomposition Retinex model and the inverse haze removal approach. To be specific, we first estimate the smoothed illumination and de-noised reflectance in a successive sequence. Then, we apply a color inversion from 0-255 to the estimated illumination, and introduce a haze removal approach based on the dark channel prior to adjust the inverted illumination. Finally, the enhanced image is generated by combining the adjusted illumination and the de-noised reflectance. As a result, improved visibility is obtained from the processed images and inefficient or excessive enhancement is avoided. To verify the reliability of the proposed method, we perform qualitative and quantitative evaluation on five MRI datasets and one CT dataset. Experimental results demonstrate that the proposed method strikes a splendid balance between enhancement and denoising, providing performance superior to that of several state-of-the-art methods.

Reflectance estimation for infrared and visible image fusion

The desirable result of infrared (IR) and visible (VIS) image fusion should have textural details from VIS images and salient targets from IR images. However, detail information in the dark regions of VIS image has low contrast and blurry edges, resulting in performance degradation in image fusion. To resolve the troubles of fuzzy details in dark regions of VIS image fusion, we have proposed a method of reflectance estimation for IR and VIS image fusion. In order to maintain and enhance details in these dark regions, dark region approximation (DRA) is pro-posed to optimize the Retinex model.With the improved Retinex model based on DRA, quasi-Newton method is adopted to estimate the reflectance of a VIS image. The final fusion out-come is obtained by fusing the DRA-based reflectance of VIS image with IR image. Our method could simultaneously retain the low visibility details in VIS images and the high con-trast targets in IR images. Experiment statistic shows that compared to some advanced ap-proaches, the proposed method has superiority on detail preservation and visual quality.

Single low-light image enhancer using Taylor expansion and fully dynamic convolution

Most preexisting deep learning-based enhancers are incapable of adjusting brightness of enhanced images, due to constant convolutional kernels. To address this issue, we propose an enhancer based on Taylor expansion and fully dynamic convolution, which can flexibly adjust the level of the brightness. In this study, the retinex model is first modified to serve as a framework for the proposed enhancer. Next, Taylor expansion and the attention mechanism are applied to construct a backbone network based on the modified retinex model. Subsequently, a strategy of fully dynamic convolution is proposed to flexibly adjust the degree of the brightness. Specifically, a weight-bias learning network is designed to dynamically generate weight matrices which are fed to the backbone network to perform the dynamic convolution. Furthermore, local mean and variance are used as a supplemental term for our loss function to improve the performance of the proposed enhancer, while a method of simulating realistic low-light images is used for synthesizing training data to suppress noise. Comprehensive experiments demonstrate satisfactory performance of the proposed enhancer in improving the clarity of low-light images and adjusting the degree of the brightness flexibly.

Performance Analysis of Retinex Based Algorithms for Enhancement of Low Light Images

The images captured under low and poor light conditions may suffer low contrast and blurring problems which will affect its interpretation and recognition. Hence it is important to enhance and restore such low contrast images. The enhancement of the captured images in the low light environment through various image enhancement algorithms is discussed in this work. The set of algorithms tested includes single scale retinex, multiscale retinex color preservation, multiscale retinex color restoration, contrast limited enhanced adaptive histogram equalization, dark channel prior, and gamma correction algorithms. This paper discusses the various variants of retinex models, which are considered powerful methods for image enhancement and restoration. The proposed work involves the study of various image enhancement algorithms and their comparison on the basis of a reference original low light image and human eye perception models. The performance of various retinex derivative algorithms is experimented with using the LIME dataset, and the histogram equalization is analyzed for metrics such as peak signal to noise ratio, structural similarity index, and discrete entropy.

Retinex-Based Fast Algorithm for Low-Light Image Enhancement.

We proposed the Retinex-based fast algorithm (RBFA) to achieve low-light image enhancement in this paper, which can restore information that is covered by low illuminance. The proposed algorithm consists of the following parts. Firstly, we convert the low-light image from the RGB (red, green, blue) color space to the HSV (hue, saturation, value) color space and use the linear function to stretch the original gray level dynamic range of the V component. Then, we estimate the illumination image via adaptive gamma correction and use the Retinex model to achieve the brightness enhancement. After that, we further stretch the gray level dynamic range to avoid low image contrast. Finally, we design another mapping function to achieve color saturation correction and convert the enhanced image from the HSV color space to the RGB color space after which we can obtain the clear image. The experimental results show that the enhanced images with the proposed method have better qualitative and quantitative evaluations and lower computational complexity than other state-of-the-art methods.

An Image Sharpness Enhancement Algorithm Based on Green Function

The traditional image sharpness enhancement algorithm faces several defects, namely, the lack of details, and the poor subjective effect. To solve these defects, this paper proposes an image sharpness enhancement algorithm based on the Green function. Specifically, the Retinex model was employed to ensure that the enhanced image has outstanding details, and the Poisson’s equation was solved to maintain the consistency between the enhanced image and the original image in the gradient domain. Then, adaptive brightness mapping was carried out to determine the boundary conditions suitable for display, and the boundary of the region was sampled to reduce the complexity of our algorithm. Experimental results show that our algorithm improved the contrast and sharpness of images from the levels of contrastive image enhancement algorithms.

Retinex model based stain normalization technique for whole slide image analysis.

Medical imaging provides the means for diagnosing many of the medical phenomena currently studied in clinical medicine and pathology. The variations of color and intensity in stained histological slides affect the quantitative analysis of the histopathological images. Moreover, stain normalization utilizing color for the classification of pixels into different stain components is challenging. The staining also suffers from variability, which complicates the automatization of tissue area segmentation with different staining and the analysis of whole slide images. We have developed a Retinex model based stain normalization technique in terms of area segmentation from stained tissue images to quantify the individual stain components of the histochemical stains for the ideal removal of variability. The performance was experimentally compared to reference methods and tested on organotypic carcinoma model based on myoma tissue and our method consistently has the smallest standard deviation, skewness value, and coefficient of variation in normalized median intensity measurements. Our method also achieved better quality performance in terms of Quaternion Structure Similarity Index Metric (QSSIM), Structural Similarity Index Metric (SSIM), and Pearson Correlation Coefficient (PCC) by improving robustness against variability and reproducibility. The proposed method could potentially be used in the development of novel research as well as diagnostic tools with the potential improvement of accuracy and consistency in computer aided diagnosis in biobank applications.

Low-Light Image Enhancement via Poisson Noise Aware Retinex Model

Limited by the number of available photons collected by a pixel and the stability of the imaging system, images captured under poor illumination conditions are often degraded by heavy shot noise and low contrast. In this letter, we propose a novel low-light image enhancement algorithm using the Poisson noise-aware Retinex model, in which the Poisson distribution is considered to formulate the fidelity term in the Retinex model for the first time. Furthermore, the space-variant weight maps for total variation regularization terms are calculated according to the piecewise smooth prior of illumination component and the Poisson noise distribution prior, which contributes to noise suppression in different noise intensity while preserving image details and structures. We get the optimal solution of the Poisson noise-aware Retinex model by an iterative optimization algorithm. Finally, the enhanced image is obtained by gamma correcting the estimated illumination map. Experimental results demonstrate that the proposed model performs better than state-of-the-art methods in low-light image enhancement and noise suppression.

RetinexGAN:Unsupervised Low-Light Enhancement With Two-Layer Convolutional Decomposition Networks

In the field of image enhancement, using deep learning methods to enhance low-light images is currently mainstream. However, the methods often have complex network structures of a large number of parameters, and their training often uses paired data-sets, which are difficult to obtain in actual practice. To solve these problems, this paper proposes a simple generative adversarial network and Retinex model, dubbed RetinexGAN, that is completely trained using unpaired data-sets. It contains a decomposition network and two discriminator networks. To reduce the parameters of the network, only two convolution layers are used in the decomposition network. We show more challenging testing data where some parts of the image are underexposed and others are normal light. Both quantitative and visual results show that RetinexGAN is largely superior to state-of-the-art methods.

Enhancing Low-Light Color Image via L 0 Regularization and Reweighted Group Sparsity

Classic Retinex model based low-light image enhancement methods ignored the interference of noise, which causes annoying artifacts. In this paper, we propose to estimate the illumination, reflectance and suppress the noise in a whole framework. Instead of using the L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> norm to constrain the piece-wise smoothness, we utilize the L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sub> norm to preserve the structure of the illumination map and remove the intensive noise. The clean reflectance is obtained via a novel group sparsity regularization to preserve the small scale details. Instead of using a zero-mean model for all sparse coefficients, we propose to adaptively estimate the mean of each coefficient according to the statistical characteristics of the image content. A re-weighting scheme is introduced to adjust how close the estimated patch is to the mean value. In addition, based on the observation that the noise levels in different color channels are different, the noise variance in each channel is estimated and updated during the model optimization process. Experimental results show that the proposed method outperforms the compared schemes in terms of both objective quality and visual quality.

Both speckle reduction and contrast enhancement for optical coherence tomography via sequential optimization in the logarithmic domain based on a refined Retinex model.

Optical coherence tomography (OCT) image enhancement is a challenging task because speckle reduction and contrast enhancement need to be addressed simultaneously and effectively. We present a refined Retinex model for guidance in improving the performance of enhancing OCT images accompanied by speckle noise; a physical explanation is provided. Based on this model, we establish two sequential optimization functions in the logarithmic domain for speckle reduction and contrast enhancement, respectively. More specifically, we obtain the despeckled image of an entire OCT image by solving the first optimization function. Incidentally, we can recover the speckle noise map through removing the despeckle component directly. Then, we estimate the illumination and reflectance by solving the second optimization function. Further, we apply the contrast-limited adaptive histogram equalization algorithm to adjust the illumination, and project it back to the reflectance for achieving contrast enhancement. Experimental results demonstrate the robustness and effectiveness of our proposed method. It performs well in both speckle reduction and contrast enhancement and is superior to the other two methods both in terms of qualitative analysis and quantitative assessment. Our method has the practical potential to improve the accuracy of manual screening and computer-aided diagnosis for retinal diseases.