Color Cast Research Articles

An underwater image enhancement method based on multi-scale layer decomposition and fusion

High-quality underwater images can intuitively reflect the most realistic underwater conditions, guiding for underwater environmental monitoring and resource exploration strongly. But when factors like light absorption affect underwater optical imaging, it has been found that poor visibility and blurred texture details occur in acquired images, posing challenges for the identification and detection of underwater targets. To obtain natural images, an enhancement algorithm is proposed based on multi-scale layer decomposition and fusion. The algorithm employs different strategies to recover image attenuation information from both local and global perspectives, generating two complementary preprocessed fusion inputs. For fusion input 1, operations are conducted in the RGB color space. Initially, the mean proportion of each color channel is used to identify the attenuated color channel. Then, a local compensation strategy is adaptively applied to restore the pixel intensity of the attenuated color channel. Finally, a statistical color correction method is used to eliminate color cast in the image. Fusion input 2 involves two processing stages. In the Lab color space, the algorithm uses the grayscale information to reduce the deviation in the mean values of channels a and b globally. The local mean information of the component L enhances detail textures. In the RGB color space, linear stretching is applied to correct color deviations. To fuse the structural features of two complementary preprocessed inputs and avoid interference between signals from different layers, the color channels of fused input image are first decomposed into muti-scale structural layers based on structural priors. Then, the image enhancement is achieved through layer-by-layer fusion of the corresponding color channels of the two inputs. By testing and analyzing with the, it was found that the proposed method can improve the clarity of attenuated images in various underwater scenarios of UIEBD and RUIE datasets effectively, enhancing image detail and texture richness, increases contrast, and achieving natural and comfortable visual quality. Compared with the quantitative metrics of 14 other algorithms, the proposed algorithm shows an average score improvement of 10.14, 90.48, and 2.06, respectively, in metrics AG (average gradient), EI (edge intensity), and NIQE (natural image quality evaluator). In the RUIE dataset, it shows an average score improvement of 10.21, 94.76, and 1.86, respectively.

Perceptual illumination-structure patch decomposition for enhancing complex lighted underwater images

Due to the influence of natural and artificial lighting, complicated illuminated underwater images suffer from uneven exposure, accompanied by color cast, low contrast, and blurred details. Existing methods often struggle to brighten dark areas and suppress overexposed areas. To this end, a perceptual illumination-structure patch decomposition (PISPD) model is proposed to enhance complex lighted underwater images. The PISPD method is firstly based on two complementary inputs, including a contrast-enhanced image and a detail-sharpened image. To combine the complementary information of two inputs and balance brightness, the PISPD model decomposes the inputs into four elements: perceptual illumination map, contrast, structure, and average intensity. The perceptual illumination map is used to balance brightness, while the contrast, structure, and average intensity are used to integrate the features of the inputs. Moreover, a weighted edge-preserving factor is introduced in the decomposition-fusion process of contrast, structure, and mean intensity to avoid artifacts. This study also provides a benchmark dataset, namely, CLUID, containing 990 complex lighted underwater images. Experiments with qualitative and quantitative analyses show that our PISPD outperforms eight state-of-the-art approaches.

Subject review: White balance techniques of digital image

Due to un control environment during creating of the digital image make the resulting image have un real color cast, for that a white balance algorithm has been found to correct the unreal color cast create by non-canonical Lighting sources, In order to achieve satisfactory color of the digital image, a white balance required to adjust the image color either automatically or manually. for that researchers found an automatic and manual white balance algorithms, and even the Automatic white balance algorithm depending on analysis either low level features or high Level features, explaining An examples for Automatic white balance algorithm ( Gray World Algorithm and The white patch Algorithm ) and clarify each Algorithm suits different kind of Image.

Underwater image enhancement via color correction and multi-feature image fusion

Abstract The light attenuation underwater causes the actual underwater images to suffer from color cast, low contrast, and weak illumination. To address these issues, an effective fusion-based method is proposed, which realizes color correction, brightness adjustment, contrast, and detail enhancement of underwater images. Concretely, we first design an adaptive color correction method via dominant color channel judgment and lower color channel compensation. Then, we detect the brightness of each input image and propose a gamma correction function based on the gradient of the cumulative histogram to adjust the brightness of the low-light images. Subsequently, global histogram stretching and adaptive fractional differentiation techniques are employed to process the brightness-adjusted image, and then the global contrast-enhanced version and detail-enhanced version are generated respectively. To integrate the advantages of both versions, a channel fusion method based on the Lab color space is used to fuse the luminance and color of the two versions separately. The experimental results demonstrate the effectiveness of the proposed method in improving the color and illumination of underwater images, as well as enhancing the clarity of images. Moreover, the testing results on multiple datasets validate the excellent stability of this method.

Hierarchical prior-guided quality assessment method for underwater images

Many underwater image enhancement (UIE) algorithms have been proposed to improve the quality of the underwater image. However, the lack of effective objective image quality assessment (IQA) methods has hindered the further development of UIE algorithms. Unlike traditional distorted images, underwater images usually contain natural distortions such as color cast and fog effects induced by light absorption and scattering. In addition, due to the complexity of underwater scenes, the enhanced results generated using existing UIE algorithms may have artificial distortions such as under-enhancement, over-enhancement, and detail loss. Thus, it is difficult for traditional IQA methods to comprehensively capture quality-related features in complicated underwater conditions. Based on this, this paper proposes a new hierarchical prior-guided quality assessment method for underwater images with the aid of deep learning technology, which first decomposes the underwater image into the base layer and detail layer. Then, the two layers are taken as input of feature extraction network for extracting the luminance information and texture information of the image, respectively. Meanwhile, two pseudo-reference images are used to guide model training so as to obtain luminance and texture features more accurately and efficiently. Finally, the two types of features are fused to obtain the quality score of the underwater image. Extensive experiments have been conducted on two publicly available underwater image datasets, and the experimental results show that the proposed method outperforms other underwater image quality assessment methods.

An integrated enhancement method to improve image visibility and remove color cast for sand-dust image

AbstractSand-dust color images suffer from poor image visibility and serious color cast that significantly affect the performance of outdoor computer vision systems. Therefore, this paper proposes an integrated enhancement method for the sand-dust image. The proposed method improves the image visibility and removes the sand-dust color cast. It integrates two main processes in two different color models. The adaptive gray world-blue channel (AGW-B) is utilized in the Red-Green-Blue (RGB) color model to remove the sand-dust color cast. Then, the contrast limited adaptive histogram equalization with normalized intensity and saturation correction (CLAHE-NISC) is conducted in a Hue-Saturation-Intensity (HSI) color model to enhance the image visibility. Sand-dust images with weak, medium, and extreme sand-dust color casts were utilized in the subjective and objective evaluations. Results show that the proposed method produced better and clearer enhanced images than the other four current sand-dust image enhancement methods.

DICAM: Deep Inception and Channel-wise Attention Modules for underwater image enhancement

In underwater environments, imaging devices suffer from water turbidity, attenuation of lights, scattering, and particles, leading to low quality, poor contrast, and biased color images. This has led to great challenges for underwater condition monitoring and inspection using conventional vision techniques. In recent years, underwater image enhancement has attracted increasing attention due to its critical role in improving the performance of current computer vision tasks in underwater object detection and segmentation. As existing methods, built mainly from natural scenes, have performance limitations in improving the color richness and distributions we propose a novel deep learning-based approach namely Deep Inception and Channel-wise Attention Modules (DICAM) to enhance the quality, contrast, and color cast of the hazy underwater images. The proposed DICAM model enhances the quality of underwater images, considering both the proportional degradations and non-uniform color cast. Extensive experiments on two publicly available underwater image enhancement datasets have verified the superiority of our proposed model compared with several state-of-the-art conventional and deep learning-based methods in terms of full-reference and reference-free image quality assessment metrics. The source code of our DICAM model is available at https://github.com/hfarhaditolie/DICAM.

Fusion of multiscale gradient domain enhancement and gamma correction for underwater image/video enhancement and restoration

Underwater images and video often suffer from poor visibility and color cast because light gets scattered and absorbed in water. To solve this problem, a novel method based on the fusion of multiscale gradient-domain enhancement and gamma correction is proposed for underwater images and video enhancement. Firstly, a white balance is used for color correction to the input underwater image and video. secondly, the color corrected underwater RGB images are converted to YCbCr color space. The Y-component of the image is decomposed into the base layer and detail layers using a Weighted Least Squares (WLS) filter. The base layer is enhanced by using gamma correction and detail layers are enhanced using the S-shape function in the gradient domain. The enhanced base layer and detail layers are fused. Finally, the fused image combined with Cb and Cr-component of YCbCr color space to obtained enhanced image. The proposed method has been implemented on the Underwater Image Enhancement Benchmark (UIEB) dataset, Underwater-45 (U45) dataset, and Dataset Real-world Underwater Video of Artifacts (DRUVA) based on the Peak Signal-to-Noise Ratio (PSNR), Structure Similarity Index Measure (SSIM), Measure of Enhancement (EME), Discrete Entropy (DE), Underwater Image Quality Measure (UIQM), and Underwater Color Image Quality Evaluation (UCIQE). To verify the efficacy of the proposed method, a qualitative and quantitative comparison has been conducted on the UIEB, U45, and DRUVA datasets. The result demonstrates that the proposed method outperforms the state-of-the-art method, in terms of PSNR, SSIM, EME, UIQM, and UCIQE parameters. Furthermore, the efficiency of proposed method tested on fog image and low illumination images.

UnitModule: A lightweight joint image enhancement module for underwater object detection

Underwater object detection faces the problem of underwater image degradation, which affects the performance of the detector. Underwater object detection methods based on noise reduction and image enhancement usually do not provide images preferred by the detector or require additional datasets. In this paper, we propose a plug-and-play Underwater joint image enhancement Module (UnitModule) that provides the input image preferred by the detector. We design an unsupervised learning loss for the joint training of UnitModule with the detector without additional datasets to improve the interaction between UnitModule and the detector. Furthermore, a color cast predictor with the assisting color cast loss and a data augmentation called Underwater Color Random Transfer (UCRT) are designed to improve the performance of UnitModule on underwater images with different color casts. Extensive experiments are conducted on DUO for different object detection models, where UnitModule achieves the highest performance improvement of 2.6 AP for YOLOv5-S and gains the improvement of 3.3 AP on the brand-new test set (URPCtest). And UnitModule significantly improves the performance of all object detection models we test, especially for models with a small number of parameters. In addition, UnitModule with a small number of parameters of 31K has little effect on the inference speed of the original object detection model. Our quantitative and visual analysis also demonstrates the effectiveness of UnitModule in enhancing the input image and improving the perception ability of the detector for object features. The code is available at https://github.com/LEFTeyex/UnitModule.

Novel-Fl Operators Based Visibility Processing Techniques of Denoising Algorithm Using Exdark Dataset Simulation

Abstract: An inclement dusty weather can significantly reduce the visual quality of captured images and this consequently leads to hamper the observation of meaningful image details. Capturing images in such weather often leads to undesirable artifacts such as poor contrast, deficient colors or color cast. Hence, various methods have been proposed to process such unwanted event and recover vivid results with acceptable colors. These methods vary from simple to complex due to the variation of the used processing concepts. In this article, an innovative technique that utilizes tuned fuzzy intensification operators is introduced to expeditiously process poor quality images captured in an inclement dusty weather. Intensive experiments were carried out to check the processing ability of the proposed technique, wherein the obtained results exhibited its competence in filtering various degraded images. Specifically, it performed well in providing acceptable colors and unveiling fine details for the processed images. This study expanded upon earlier methods of low-light picture enhancement that relied on DCP. After the light reflection direction was initialised, it was refocused using the red channel estimate. Separating the region with strong lighting characteristics from the background darkness zone is another usage of DCP. The next step was to create and assess new anthropogenic light quality by estimating and refining transmission maps. An image free of black areas is also produced by recovering the picture light radiance using the updated transmission map data. The last step in achieving high-quality output images is using the denoising algorithm. Results from the ExDark dataset simulations shown that the proposed strategy achieved better subjective and objective performance than state-of-the-art methods.

Underwater Image Enhancement Network Based on Dual Layers Regression

Due to the absorption and scattering of light in water, captured underwater images often suffer from some degradation, such as color cast, blur, and low contrast. These types of degradation usually affect and degrade the performance of computer vision methods and tasks under water. In order to solve these problems, in this paper, we propose a multi-stage and gradually optimized underwater image enhancement deep network, named DLRNet, based on dual layers regression. Our network emphasizes important information by aggregating different depth features in the channel attention module, and the dual-layer regression module is designed with regression to obtain the ambient light and scene light transmission for an underwater image. Then, with the underwater imaging model, the enhanced underwater image for a degraded image can be obtained with normal color, higher clarity, and contrast. The experiments on some different datasets with qualitative analysis and quantitative evaluations validate our network, and show that it outperforms some state-of-the-art approaches.

Efficient Framework for Real-Time Color Cast Correction and Dehazing Using Online Algorithms to Approximate Image Statistics

Efficient Framework for Real-Time Color Cast Correction and Dehazing Using Online Algorithms to Approximate Image Statistics

IDACC: Image Dehazing Avoiding Color Cast Using a Novel Atmospheric Scattering Model

IDACC: Image Dehazing Avoiding Color Cast Using a Novel Atmospheric Scattering Model

Primary Colour Detection in An Image

Primary Colour Detection in an Image, Traditional methods of color cast detection do not discriminate between images with true cast and those with dominant colors. This may result in an inaccuracy of the color cast measurement. In order to overcome the limitation of traditional methods, an approach based on image semantic is present. It can improve the accuracy and reliability of the detecting results by the means of recognizing and removing the dominant color objects · and analyzing the color distribution of the whole image. Class specific color detection is already implemented in some systems, but image classification usually relies on global image features only. The method of recognizing the dominant color objects is based on block-features and region-features by using K-Means Clustering in this project. It shows a significant improvement over previously achieved classification for a variety of critical image classes. The comparison of the results of the approach proposed to that of people shows that it is reliable and effective. This project proposes the use of Machine Learning Techniques and Deep Learning Algorithms.

A Cascaded Multimodule Image Enhancement Framework for Underwater Visual Perception.

Underwater images usually exhibit severe color cast, hazy appearance, and/or dark regions because of the complex lighting absorption and scattering in water. How to increase the quality of these degraded underwater images has emerged as a key issue for various underwater application tasks. Recent efforts have been made to deal with single type degradation, however, it is still challenging to deal with multiple degradations that usually coexist in an underwater image with a general network. The degradations in underwater images can be divided into medium-agnostic (hazy or low-light which also encountered in in-air images) and medium-specific (color distortion caused by the specific light attenuation property in water) ones. According to this observation, this article proposes a cascaded multimodule underwater image enhancement (UIE) framework to address the coexisted multiple degradations. In the proposed framework, an in-air image enhancement module and a novel proposed adaptive color channel compensation network (AC 3 Net) are cascaded, in which the former focuses primarily on solving medium-agnostic degradations and the latter is for handling the medium-specific degradation. This framework has good flexibility by cascading different types of in-air image enhancement networks with AC 3 Net to achieve various UIE. The effectiveness of the proposed framework has been extensively validated on various degraded underwater images as well as different underwater visual perception tasks.

CURE-Net: A Cascaded Deep Network for Underwater Image Enhancement

Underwater imaging is usually degraded by low contrast or color cast due to light absorption and scattering. This fact limits the accuracy of object recognition in underwater and marine environments. In this article, to address this issue, we propose a CURE-Net that progressively improves degraded underwater images in a coarse-to-fine way. To be specific, our CURE-Net consists of three cascaded subnetworks. The first two subnetworks use attention and gate fusion to learn multiscale contextual information, whereas the third subnetwork preserves fine spatial details. A detail enhancement block and a supervised recovery block are deployed between subnetworks to further improve the recovery of colors and details. Our proposed CURE-Net is extensively evaluated on popular data sets and achieves state-of-the-art performance. Compared with its peers, our method is also more friendly to object recognition—underwater objects are more easily recognized after being processed by our method.

Underwater image contrast enhancement through an intensity-randomised approach incorporating a swarm intelligence technique with unsupervised dual-step fusion

ABSTRACT Analysing objects in an underwater medium is difficult due to light problems in such an environment. Low contrast and visibility in water medium result in restricted information extraction. Some previous methods inadequately reduce underwater colour cast and improve the image contrast minimally. This work proposes intensity-randomised underwater image contrast enhancement (IRUCE), an improved enhancement method that integrates an unsupervised dual-step fusion technique to reduce blue-green colour cast, improve contrast, and enhance image brightness, especially in turbid and deep underwater media. IRUCE enhances the inferior colour channels and moderates the dominant colour channel to reduce the colour cast before the intensity-randomised approach is implemented. The intensity-randomised approach is designed to effectively distribute image intensity across all intensity levels. Next, a swarm intelligence algorithm is fused to perform median equalisation on all colour channels. The median intensity values of inferior colour channels are shifted towards the dominant colour channel. The unsharp masking technique is employed in the last step to increase image sharpness. The effectiveness of this approach is validated through quantitative and qualitative evaluations, and the results are compared with those of other state-of-the-art methods. Outcomes indicate that the proposed method improves underwater image quality significantly and outperforms other contemporary techniques.

Efficient Contrast Adjustment and Fusion Method for Underexposed Images in Industrial Cyber-Physical Systems

Owing to imaging equipment's environment and limitations, the images obtained in industrial cyber-physical systems (ICPSs) are degraded and available in various visual appearances. The process of highlighting the hidden contents in night-time contrast-distorted images is complex. Earlier approaches have solved this problem from a different perspective and achieved remarkable results that are generally unsatisfactory for images with diverse illumination distortions in ICPSs. Hence, an effective visibility enhancement model is proposed to eliminate inconsistent color casts while highlighting more hidden content for improved inspection, safety in large spaces, and monitoring of large systems. Our proposed model has four steps: 1) removal of the unnatural color cast via a white balance technique, 2) use of probability density and softplus functions to process the images with the actual color cast, 3) using an optimization algorithm to estimate the illumination and adjusting it using a nonlinear function, and 4) blending by multiscale fusion to obtain the most effective visual result. Evaluation of ten benchmark datasets using 14 quality metrics for 22 conventional and modern algorithms shows that our approach is robust, flexible, and applicable to numerous vision-based applications, such as ICPSs, autonomous vehicles, smart cameras, smart mobility, and transportation, especially in low-light environments.

Underwater image recovery based on water type estimation and adaptive color correction

In underwater environments, light propagation is affected by scattering and absorption, leading to color distortion and quality degradation of underwater images. In addition, the presence of a color cast in the image and variations in the attenuation coefficients across various water bodies bring great challenges for underwater image restoration. In this paper, an underwater image restoration method based on water body type estimation and adaptive color correction is proposed. Initially, the underwater images are categorized into color casts and non-color casts according to their hue, and a water body type estimation method based on image color and blurriness is introduced for improving the accuracy of transmission map estimation. Following this, we performed adaptive color correction on the image using a nonlinear transformation, which effectively eliminates color cast. Then the background light position is corrected using the degree of color cast of the image to restore the hue and brightness of the image more naturally. Ultimately, the acquired background light and transmission map are utilized to generate clear underwater images using the image formation model (IFM). Experiments on the widely used UIEB benchmark and SUID datasets show that our method effectively solves the problems of image color distortion and quality degradation, generating satisfactory visual effects.

DGD-cGAN: A dual generator for image dewatering and restoration

Underwater images are usually covered with a blue–greenish colour cast, making them distorted, blurry or low in contrast. This phenomenon occurs due to the light attenuation given by the scattering and absorption in the water column. In this paper we present an image dewatering approach motivated upon the observation that the image formation model can be used to drive the learning process by constraining the loss function and making used of paired data. To this end, we employ a conditional generative adversarial network (cGAN) with two generators. Our Dual Generator Dewatering cGAN (DGD-cGAN) removes the haze and colour cast induced by the water column and restores the true colours of underwater scenes whereby the effects of various attenuation and scattering phenomena that occur in underwater images are tackled by the two generators. The first generator takes as input the underwater image and predicts the dewatered scene, while the second generator learns the underwater image formation process by implementing a custom loss function based upon the transmission and the veiling light components of the image formation model. Extensive experiments show that DGD-cGAN consistently delivers a margin of improvement as compared with state-of-the-art methods on several widely available datasets.