Contrast enhancement based on discriminative co-occurrence statistics

This study introduces an innovative unsupervised low-light image enhancement method, termed GDLLE. The key innovation lies in decoupling the luminance and content representations of an image, thereby establishing a bidirectional mapping between low-light and normal-light images, which significantly enhances the visual quality of low-light images. In contrast to traditional supervised learning approaches that rely on paired datasets, the GDLLE method does not require paired low-light and normal-light image pairs. Instead, it enhances low-light images by extracting luminance masks and content information from unpaired images. Furthermore, the study incorporates an adaptive normalization strategy and a multi-scale enhancement framework to optimize both the global structure and local details of the image. To further improve the enhancement performance, a self-supervised mechanism based on cyclic consistency is introduced, which leverages cyclic consistency loss and self-feature preservation loss to ensure the quality of the generated images. Experimental results demonstrate that the GDLLE method outperforms existing approaches on several benchmark datasets, compared with the baseline models, GDLLE has achieved an improvement of 0.46 dB in the PSNR metric, validating its effectiveness and superiority in the unsupervised low-light image enhancement task. This research offers a novel solution in the field of low-light image enhancement, with promising potential for superior image quality improvement in practical applications.

Low-light images suffer from severe noise, low brightness, low contrast, etc. In previous researches, many image enhancement methods have been proposed, but few methods can deal with these problems simultaneously. In this paper, to solve these problems simultaneously, we propose a low-light image enhancement method that can be combined with supervised learning and previous HSV (Hue, Saturation, Value) or Retinex model-based image enhancement methods. First, we analyse the relationship between the HSV color space and the Retinex theory, and show that the V channel (V channel in HSV color space, equals the maximum channel in RGB color space) of the enhanced image can well represent the contrast and brightness enhancement process. Then, a data-driven conditional re-enhancement network (denoted as CRENet) is proposed. The network takes low-light images as input and the enhanced V channel (V channel of the enhanced image) as a condition during testing, and then it can re-enhance the contrast and brightness of the low-light image and at the same time reduce noise and color distortion. In addition, it takes 23 ms to process a color image with the resolution 400*600 on a 1080Ti GPU. Finally, some comparative experiments are implemented to prove the effectiveness of the method. The results show that the method proposed in this paper can significantly improve the quality of the enhanced image, and by combining it with other image contrast enhancement methods, the final enhancement result can even be better than the reference image in contrast and brightness when the contrast and brightness of the reference are not good.

Low-light color images are limited in their application in fields such as security monitoring and autonomous driving due to issues such as dim brightness and blurry details. To improve the problem of dim brightness and uneven local lighting in low-light color images, and to enhance image quality to meet practical application needs, this study adopts multi-frame grouping denoising and adaptive gamma correction to unify the brightness range, combined with blind source separation denoising and Pearson growth curve adjustment of brightness. To address uneven light in a single frame, dual-scale adaptive gamma correction are adopted. Comparative experiments are conducted with multiple sets of low-light and light uneven images to validate the performance of the research method. The findings denoted that the average brightness of the enhanced image increased from the original 5.03-25.31 to 57.14-80.02, the information entropy increased from 3.26 to 6.07 to 7.05-8.19, and the image processing time was only 2.47-2.55s. In images with uneven lighting, the average gradient increased from 12.74 to 16.47 to 25.32-27.12, and the visual information fidelity reached 0.89-0.93. Full size processing could be completed in 85.06 ms. The research method effectively solves the problems of brightness fluctuations and local overexposure in low-light images, providing a reference path for low-light image applications in related fields.

Enhancing low-light images via dehazing principles: Essence and method

Low light images suffer from a low dynamic range and severe noise due to low signal-to-noise ratio (SNR). In this paper, we propose joint contrast enhancement and noise reduction of low light images via just-noticeable-difference (JND) transform. We adopt the JND transform to achieve both contrast enhancement and noise reduction based on human visual perception. First, we generate a JND map based on an the human visual system (HVS) response model from foreground and background luminance, called JND transform. Second, for base image, we perform perceptual contrast enhancement based on luminance adaptation to effectively allocate a dynamic range to each gray level while preventing under enhancement (tone distortion) and over-enhancement. Third, we refine the JND map using Weber's law, luminance adaptation and visual masking. Weber's law enhances the JND map based on the luminance variation after contrast enhancement. Luminance adaptation suppresses noise for smooth regions, while visual masking enforces detail enhancement for textural regions. Fourth, we perform inverse JND transform to generate the enhanced luma channel from the JND map and base image. Finally, we conduct chroma denoising by transferring texture information of the enhanced luma channel to the chroma channels with guided filtering. Experimental results show that the proposed method achieves both contrast enhancement and noise reduction for low light images as well as outperforms state-of-the-art methods in terms of quantitative measurements.

Low-light object detection involves identifying and locating objects in images captured under poor lighting conditions. It plays a significant role in surveillance and security, night pedestrian recognition, and autonomous driving, showcasing broad application prospects. Most existing object detection algorithms and datasets are designed for normal lighting conditions, leading to a significant drop in detection performance when applied to low-light environments. To address this issue, we propose a Low-Light Detection with Low-Light Enhancement (LDWLE) framework. LDWLE is an encoder-decoder architecture where the encoder transforms the raw input data into a compact, abstract representation (encoding), and the decoder gradually generates the target output format from the representation produced by the encoder. Specifically, during training, low-light images are input into the encoder, which produces feature representations that are decoded by two separate decoders: an object detection decoder and a low-light image enhancement decoder. Both decoders share the same encoder and are trained jointly. Throughout the training process, the two decoders optimize each other, guiding the low-light image enhancement towards improvements that benefit object detection. If the input image is normally lit, it first passes through a low-light image conversion module to be transformed into a low-light image before being fed into the encoder. If the input image is already a low-light image, it is directly input into the encoder. During the testing phase, the model can be evaluated in the same way as a standard object detection algorithm. Compared to existing object detection algorithms, LDWLE can train a low-light robust object detection model using standard, normally lit object detection datasets. Additionally, LDWLE is a versatile training framework that can be implemented on most one-stage object detection algorithms. These algorithms typically consist of three components: the backbone, neck, and head. In this framework, the backbone functions as the encoder, while the neck and head form the object detection decoder. Extensive experiments on the COCO, VOC, and ExDark datasets have demonstrated the effectiveness of LDWLE in low-light object detection. In quantitative measurements, it achieves an AP of 25.5 and 38.4 on the synthetic datasets COCO-d and VOC-d, respectively, and achieves the best AP of 30.5 on the real-world dataset ExDark. In qualitative measurements, LDWLE can accurately detect most objects on both public real-world low-light datasets and self-collected ones, demonstrating strong adaptability to varying lighting conditions and multi-scale objects.

The goal of low-light image enhancement (LLIE) is to enhance perception to restore normal-light images. The primary emphasis of earlier LLIE methods was on enhancing the illumination while paying less attention to the color distortions and noise in the dark. In comparison to the ground truth, the restored images frequently exhibit inconsistent color and residual noise. To this end, this paper introduces a Wasserstein contrastive regularization method (WCR) for LLIE. The WCR regularizes the color histogram (CH) representation of the restored image to keep its color consistency while removing noise. Specifically, the WCR contains two novel designs including a differentiable CH module (DCHM) and a WCR loss. The DCHM serves as a modular component that can be easily integrated into the network to enable end-to-end learning of the image CH. Afterwards, to ensure color consistency, we utilize the Wasserstein distance (WD) to quantify the resemblance of the learnable CHs between the restored image and the normal-light image. Then, the regularized WD is used to construct the WCR loss, which is a triplet loss and takes the normal-light images as positive samples, the low-light images as negative samples, and the restored images as anchor samples. The WCR loss pulls the anchor samples closer to the positive samples and simultaneously pushes them away from the negative samples so as to help the anchors remove the noise in the dark. Notably, the proposed WCR method was only used for training, and was shown to achieve high performance and high speed inference using lightweight networks. Therefore, it is valuable for real-time applications such as night automatic driving and night reversing image enhancement. Extensive evaluations on benchmark datasets such as LOL, FiveK, and UIEB showed that the proposed WCR method achieves superior performance, outperforming existing state-of-the-art methods.

Image contrast enhancement methods play a key role in many image processing and vision applications. For surveillance applications, real-time contrast improvement over the whole image is required when videos are taken in poor lighting conditions. It is also necessary to highlight details in shadowed regions without introducing artifacts. In this paper, several state-of-the-art contrast enhancement methods are compared. Image quality is evaluated by means of objective metrics such as intensity contrast and brightness error, and by subjective assessment. Execution time is also measured. Experimental results show that a technique based on histogram modification presents a better trade-off considering both aspects.

Images captured in low-light conditions usually suffer from very low contrast and underexpose, which cannot be directly utilized in the subsequent computer vision tasks, such as object recognition, detection, identification and tracking. Existing methods include HE based method, Retinex theory based method and deep learning method which may generate undesirable enhanced results including amplified noise, biased colors and extreme boundary. To address this problem, we utilize prior knowledge of Retinex theory and GAN based on data statistic to propose a progressive GAN-based Transfer network to realize the low-light enhancement. In this paper, the image is decomposed by JieP method based on the Retinex model to obtain the reflection and light components, and learn the relationship between the reflection component of the low-light image and normal light image via a reflection decomposition on network (RefDecN), and then generate the reflection component of the low-light image. Then, another illumination transfering network (IllumTransN) is utilized to transfer the light of normal light image to the reflection component to realize low-light enhancement. Experimental results of low-light image enhancement on RAISE, LOL and MEF datasets demonstrate our ProGAN can outperform state-of-the-art methods in terms of objective and subjective quality.KeywordsLow-light enhancementReflection componentIllumination componentRetinex modelGenerative adversarial network

Purpose:Breast cancer can be cured if diagnosed early, with digital mammography which is one of the most effective imaging modalities for early detection. However mammogram images often come with low contrast, high background noises and artifacts, making diagnosis difficult. The purpose of this research is to preprocess mammogram images to improve results with a computer aided diagnosis system. The focus is on three preprocessing methods: a breast border segmentation method; a contrast enhancement method; and a pectoral muscle removal method.Methods:The proposed breast border extraction method employs a threshold based segmentation technique along with a combination of morphological operations. The contrast enhancement method presented here is divided into two phages. In phase I, a bi-level histogram modification technique is applied to enhance the image globally and in phase II a non-linear filter based on local mean and local standard deviation for each pixel is applied to the histogram modified image. The pectoral muscle removal method discussed here is implemented by applying a region growing algorithm.Results:The proposed techniques are tested with the Mini MIAS dataset. The breast border extraction method is applied to 322 images and achieved 98.7% segmentation accuracy. The contrast enhancement method is evaluated based on quantitative measures like measure of enhancement, absolute mean brightness error, combined enhancement measure and discrete entropy. The proposed contrast enhancement method when applied to 14 images with different types of masses, the quantitative measures showed an optimum level of contrast enhancement compared to other enhancement methods with preservation of local detail. Removal of the pectoral muscle from MLO mammogram images reduced the search region while identifying abnormalities like masses and calcification.Conclusions:The preprocessing steps proposed here show promising results in terms of both qualitative and quantitative analysis.

Low-light images incur several complicated degradation factors such as poor brightness, low contrast, color degradation, and noise. Most previous deep learning-based approaches, however, only learn the mapping relationship of single channel between the input low-light images and the expected normal-light images, which is insufficient enough to deal with low-light images captured under uncertain imaging environment. Moreover, too deeper network architecture is not conducive to recover low-light images due to extremely low values in pixels. To surmount aforementioned issues, in this paper we propose a novel multi-branch and progressive network (MBPNet) for low-light image enhancement. To be more specific, the proposed MBPNet is comprised of four different branches which build the mapping relationship at different scales. The followed fusion is performed on the outputs obtained from four different branches for the final enhanced image. Furthermore, to better handle the difficulty of delivering structural information of low-light images with low values in pixels, a progressive enhancement strategy is applied in the proposed method, where four convolutional long short-term memory networks (LSTM) are embedded in four branches and an recurrent network architecture is developed to iteratively perform the enhancement process. In addition, a joint loss function consisting of the pixel loss, the multi-scale perceptual loss, the adversarial loss, the gradient loss, and the color loss is framed to optimize the model parameters. To evaluate the effectiveness of proposed MBPNet, three popularly used benchmark databases are used for both quantitative and qualitative assessments. The experimental results confirm that the proposed MBPNet obviously outperforms other state-of-the-art approaches in terms of quantitative and qualitative results. The code will be available at https://github.com/kbzhang0505/MBPNet.

This paper describes a new method for contrast enhancement in images of low-light or unevenly illuminated scenes based on statistical modelling of wavelet coefficients of the image. A non-linear enhancement function has been designed based on the local dispersion of the wavelet coefficients modelled as a bivariate Cauchy distribution. Within the same statistical framework, a simultaneous noise reduction in the image is performed by means of a shrinkage function, thus preventing noise amplification. The proposed enhancement method has been shown to perform very well with insufficiently illuminated and noisy images, outperforming other conventional methods, in terms of contrast enhancement and noise reduction in the output image.

A robust contrast enhancement algorithm for noisy low-light images, called the denoising-enhancement-completion (DEC), is proposed in this work. We observe that noise components in low-light images degrade the performance of the contrast enhancement. Therefore, we first reduce noise components in an input image. Then, we compute the reliability weight for each pixel, by measuring the difference between the input image and the denoised image, and categorize each pixel into one of two classes: noise-free or noisy. We perform the selective histogram equalization to enhance the contrast of the noise-free pixels only. Finally, we restore missing values of the noisy pixels using the enhanced noise-free pixel values, by employing a low-rank matrix completion scheme. Experimental results show that the proposed DEC algorithm removes noise and enhances the contrast of low-light images more effectively than conventional algorithms.

To evaluate temporal changes in signal intensity (SI) and degree of contrast enhancement (CE) of bone marrow in lumbosacral vertebrae inside and outside the radiation therapy (RT) field. Twenty-three patients with advanced uterine cervical cancer who were treated with RT were prospectively evaluated. Each patient underwent four dynamic magnetic resonance (MR) studies: before RT, 2 and 4 weeks after initiation of RT, and 4 weeks after completion of RT. SI and CE were calculated in all four studies of each patient. Bone marrow inside the RT field showed steady and marked increase in precontrast SI and early and transient increase in CE at 2 weeks after initiation of RT followed by progressive and marked decrease in CE at 4 weeks after initiation of RT and 4 weeks after completion of RT. Bone marrow outside the RT field showed slight increase in precontrast SI and steady and moderate decrease in CE to a lesser degree without early increase as seen in bone marrow inside the RT field. RT causes an increase in precontrast SI predominantly in bone marrow inside the RT field. However, a decrease in CE is seen in bone marrow not only inside but also outside the RT field.

In this paper, a new denoising and contrast enhancement method for DTI is proposed. Noise removal is given priority in existing denoising methods. In order to increase the visibility of structural details, contrast enhancement methods has to be used. In proposed method, a non-linear adaptive Gaussian denoising filter removes noises from the DTI. To increase the visibility of filtered micro structural details, a contrast enhancement method is also used. The proposed method is compared with the existing scalar Partial Differential Equation (PDE) and non local means (NLM) denoising methods. Quantitative measures are used for validating the efficiency of the proposed contrast enhancement method. The experiment results shows that the proposed method outperforms the scalar PDE method and NLM method.