GamutNet: Restoring Wide-Gamut Colors for Camera-Captured Images

2021 ◽  
Vol 2021 (29) ◽  
pp. 7-12
Author(s):  
Hoang Le ◽  
Taehong Jeong ◽  
Abdelrahman Abdelhamed ◽  
Hyun Joon Shin ◽  
Michael S. Brown
Keyword(s):  
Learning Strategy ◽  
Color Space ◽  
Image Editing ◽  
Challenging Problem ◽  
Color Spaces ◽  
Unique Approach ◽  
Color Restoration ◽  
Visual Artifacts ◽  
Image Pairs ◽  
Restoration Problem

Most cameras still encode images in the small-gamut sRGB color space. The reliance on sRGB is disappointing as modern display hardware and image-editing software are capable of using wider-gamut color spaces. Converting a small-gamut image to a wider-gamut is a challenging problem. Many devices and software use colorimetric strategies that map colors from the small gamut to their equivalent colors in the wider gamut. This colorimetric approach avoids visual changes in the image but leaves much of the target wide-gamut space unused. Noncolorimetric approaches stretch or expand the small-gamut colors to enhance image colors while risking color distortions. We take a unique approach to gamut expansion by treating it as a restoration problem. A key insight used in our approach is that cameras internally encode images in a wide-gamut color space (i.e., ProPhoto) before compressing and clipping the colors to sRGB's smaller gamut. Based on this insight, we use a softwarebased camera ISP to generate a dataset of 5,000 image pairs of images encoded in both sRGB and ProPhoto. This dataset enables us to train a neural network to perform wide-gamut color restoration. Our deep-learning strategy achieves significant improvements over existing solutions and produces color-rich images with few to no visual artifacts.

Color Space Transformation using Neural Networks

2019 ◽  
Vol 2019 (1) ◽  
pp. 153-158
Author(s):  
Lindsay MacDonald
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Color Space ◽  
Reflectance Spectra ◽  
Network Architectures ◽  
Color Spaces ◽  
Natural Materials ◽  
Space Transformation ◽  
Color Space Transformation

We investigated how well a multilayer neural network could implement the mapping between two trichromatic color spaces, specifically from camera R,G,B to tristimulus X,Y,Z. For training the network, a set of 800,000 synthetic reflectance spectra was generated. For testing the network, a set of 8,714 real reflectance spectra was collated from instrumental measurements on textiles, paints and natural materials. Various network architectures were tested, with both linear and sigmoidal activations. Results show that over 85% of all test samples had color errors of less than 1.0 ΔE2000 units, much more accurate than could be achieved by regression.

scholarly journals The Application of Machine Learning for Cultivar Discrimination of Sweet Cherry Endocarp

Agriculture ◽  
2020 ◽  
Vol 11 (1) ◽  
pp. 6
Author(s):  
Ewa Ropelewska
Keyword(s):  
Sweet Cherry ◽  
Color Space ◽  
Geometric Parameters ◽  
Geometric Features ◽  
Color Spaces ◽  
Discriminative Models ◽  
Sweet Cherries ◽  
Rgb Color Space ◽  
Cultivar Discrimination ◽  
Color Channels

The aim of this study was to evaluate the usefulness of the texture and geometric parameters of endocarp (pit) for distinguishing different cultivars of sweet cherries using image analysis. The textures from images converted to color channels and the geometric parameters of the endocarp (pits) of sweet cherry ‘Kordia’, ‘Lapins’, and ‘Büttner’s Red’ were calculated. For the set combining the selected textures from all color channels, the accuracy reached 100% when comparing ‘Kordia’ vs. ‘Lapins’ and ‘Kordia’ vs. ‘Büttner’s Red’ for all classifiers. The pits of ‘Kordia’ and ‘Lapins’, as well as ‘Kordia’ and ‘Büttner’s Red’ were also 100% correctly discriminated for discriminative models built separately for RGB, Lab and XYZ color spaces, G, L and Y color channels and for models combining selected textural and geometric features. For discrimination ‘Lapins’ and ‘Büttner’s Red’ pits, slightly lower accuracies were determined—up to 93% for models built based on textures selected from all color channels, 91% for the RGB color space, 92% for the Lab and XYZ color spaces, 84% for the G and L color channels, 83% for the Y channel, 94% for geometric features, and 96% for combined textural and geometric features.

scholarly journals A Watershed-Segmentation-Based Improved Algorithm for Extracting Cultivated Land Boundaries

2021 ◽  
Vol 13 (5) ◽  
pp. 939
Author(s):  
Yongan Xue ◽  
Jinling Zhao ◽  
Mingmei Zhang
Keyword(s):  
Color Space ◽  
Cultivated Land ◽  
Color Spaces ◽  
Region Merging ◽  
Watershed Segmentation ◽  
Coverage Area ◽  
Time Efficiency ◽  
Image Contrast Enhancement ◽  
Segmentation Accuracy ◽  
Rgb Color Space

To accurately extract cultivated land boundaries based on high-resolution remote sensing imagery, an improved watershed segmentation algorithm was proposed herein based on a combination of pre- and post-improvement procedures. Image contrast enhancement was used as the pre-improvement, while the color distance of the Commission Internationale de l´Eclairage (CIE) color space, including the Lab and Luv, was used as the regional similarity measure for region merging as the post-improvement. Furthermore, the area relative error criterion (δA), the pixel quantity error criterion (δP), and the consistency criterion (Khat) were used for evaluating the image segmentation accuracy. The region merging in Red–Green–Blue (RGB) color space was selected to compare the proposed algorithm by extracting cultivated land boundaries. The validation experiments were performed using a subset of Chinese Gaofen-2 (GF-2) remote sensing image with a coverage area of 0.12 km2. The results showed the following: (1) The contrast-enhanced image exhibited an obvious gain in terms of improving the image segmentation effect and time efficiency using the improved algorithm. The time efficiency increased by 10.31%, 60.00%, and 40.28%, respectively, in the RGB, Lab, and Luv color spaces. (2) The optimal segmentation and merging scale parameters in the RGB, Lab, and Luv color spaces were C for minimum areas of 2000, 1900, and 2000, and D for a color difference of 1000, 40, and 40. (3) The algorithm improved the time efficiency of cultivated land boundary extraction in the Lab and Luv color spaces by 35.16% and 29.58%, respectively, compared to the RGB color space. The extraction accuracy was compared to the RGB color space using the δA, δP, and Khat, that were improved by 76.92%, 62.01%, and 16.83%, respectively, in the Lab color space, while they were 55.79%, 49.67%, and 13.42% in the Luv color space. (4) Through the visual comparison, time efficiency, and segmentation accuracy, the comprehensive extraction effect using the proposed algorithm was obviously better than that of RGB color-based space algorithm. The established accuracy evaluation indicators were also proven to be consistent with the visual evaluation. (5) The proposed method has a satisfying transferability by a wider test area with a coverage area of 1 km2. In addition, the proposed method, based on the image contrast enhancement, was to perform the region merging in the CIE color space according to the simulated immersion watershed segmentation results. It is a useful attempt for the watershed segmentation algorithm to extract cultivated land boundaries, which provides a reference for enhancing the watershed algorithm.

scholarly journals Robust Chromatic Adaptation Based Color Correction Technology for Underwater Images

2020 ◽  
Vol 10 (18) ◽  
pp. 6392
Author(s):  
Xieliu Yang ◽  
Chenyu Yin ◽  
Ziyu Zhang ◽  
Yupeng Li ◽  
Wenfeng Liang ◽  
...  
Keyword(s):  
Color Space ◽  
Color Correction ◽  
Test Methods ◽  
Chromatic Adaptation ◽  
Water Type ◽  
Underwater Image ◽  
Other Information ◽  
Color Restoration ◽  
Color Cast ◽  
Imaging Conditions

Recovering correct or at least realistic colors of underwater scenes is a challenging issue for image processing due to the unknown imaging conditions including the optical water type, scene location, illumination, and camera settings. With the assumption that the illumination of the scene is uniform, a chromatic adaptation-based color correction technology is proposed in this paper to remove the color cast using a single underwater image without any other information. First, the underwater RGB image is first linearized to make its pixel values proportional to the light intensities arrived at the pixels. Second, the illumination is estimated in a uniform chromatic space based on the white-patch hypothesis. Third, the chromatic adaptation transform is implemented in the device-independent XYZ color space. Qualitative and quantitative evaluations both show that the proposed method outperforms the other test methods in terms of color restoration, especially for the images with severe color cast. The proposed method is simple yet effective and robust, which is helpful in obtaining the in-air images of underwater scenes.

Using ACES Look Modification Transforms (LMTs) in VFX Environments – Part 2: Gamut Mapping

2021 ◽  
Vol 2021 (3) ◽  
pp. 108-1-108-14
Author(s):  
Eberhard Hasche ◽  
Oliver Karaschewski ◽  
Reiner Creutzburg
Keyword(s):  
Dynamic Range ◽  
List Item ◽  
Color Space ◽  
High Dynamic Range ◽  
Target Color ◽  
List Type ◽  
Color Spaces ◽  
Gamut Mapping ◽  
Scale Down ◽  
Image Production

In modern moving image production pipelines, it is unavoidable to move the footage through different color spaces. Unfortunately, these color spaces exhibit color gamuts of various sizes. The most common problem is converting the cameras’ widegamut color spaces to the smaller gamuts of the display devices (cinema projector, broadcast monitor, computer display). So it is necessary to scale down the scene-referred footage to the gamut of the display using tone mapping functions [34].In a cinema production pipeline, ACES is widely used as the predominant color system. The all-color compassing ACES AP0 primaries are defined inside the system in a general way. However, when implementing visual effects and performing a color grade, the more usable ACES AP1 primaries are in use. When recording highly saturated bright colors, color values are often outside the target color space. This results in negative color values, which are hard to address inside a color pipeline. "Users of ACES are experiencing problems with clipping of colors and the resulting artifacts (loss of texture, intensification of color fringes). This clipping occurs at two stages in the pipeline: <list list-type="simple"> <list-item>- Conversion from camera raw RGB or from the manufacturer’s encoding space into ACES AP0</list-item> <list-item>- Conversion from ACES AP0 into the working color space ACES AP1" [1]</list-item> </list>The ACES community established a Gamut Mapping Virtual Working Group (VWG) to address these problems. The group’s scope is to propose a suitable gamut mapping/compression algorithm. This algorithm should perform well with wide-gamut, high dynamic range, scene-referred content. Furthermore, it should also be robust and invertible. This paper tests the behavior of the published GamutCompressor when applied to in- and out-ofgamut imagery and provides suggestions for application implementation. The tests are executed in The Foundry’s Nuke [2].

Evolutionary Path Making and Natural Drift

2017 ◽  
Author(s):  
Francisco J. Varela ◽  
Evan Thompson ◽  
Eleanor Rosch
Keyword(s):  
Color Space ◽  
Vantage Point ◽  
Alternative View ◽  
Color Spaces ◽  
Structural Coupling ◽  
Evolutionary Path ◽  
The World ◽  
Natural Drift

This chapter demonstrates how unique histories of structural coupling can be understood from the vantage point of evolution. To this end, it provides a critique of the adaptationist view of evolution as a process of progressive fitness, and articulates an alternative view of evolution as natural drift. These unique histories of coupling, which enact incommensurable kinds of “color space,” should not be explained as optimal adaptations to different regularities in the world. Instead, they should be explained as the result of different histories of natural drift. Moreover, since organism and environment cannot be separated but are in fact codetermined in evolution as natural drift, the environmental regularities that one associates with these various color spaces must ultimately be specified in tandem with the perceptually guided activity of the animal.

Estimation of Fractal Dimension in Different Color Model

2018 ◽  
Vol 8 (1) ◽  
pp. 75-93
Author(s):  
Sumitra Kisan ◽  
Sarojananda Mishra ◽  
Ajay Chawda ◽  
Sanjay Nayak
Keyword(s):  
Fractal Dimension ◽  
Color Space ◽  
Vital Role ◽  
Color Images ◽  
Color Spaces ◽  
Fractal Surfaces ◽  
Test Operation ◽  
Novel Method ◽  
Rgb Color Space ◽  
Different Color

This article describes how the term fractal dimension (FD) plays a vital role in fractal geometry. It is a degree that distinguishes the complexity and the irregularity of fractals, denoting the amount of space filled up. There are many procedures to evaluate the dimension for fractal surfaces, like box count, differential box count, and the improved differential box count method. These methods are basically used for grey scale images. The authors' objective in this article is to estimate the fractal dimension of color images using different color models. The authors have proposed a novel method for the estimation in CMY and HSV color spaces. In order to achieve the result, they performed test operation by taking number of color images in RGB color space. The authors have presented their experimental results and discussed the issues that characterize the approach. At the end, the authors have concluded the article with the analysis of calculated FDs for images with different color space.

A Robustness Watermarking Algorithm for Digital Color Image Print-Scan Process

2013 ◽  
Vol 333-335 ◽  
pp. 992-997
Author(s):  
Yun Lu Ge ◽  
Hui Han ◽  
Xiao Dong Sun ◽  
Sheng Pin Wang ◽  
Sheng Yun Ji
Keyword(s):  
Color Image ◽  
Random Noise ◽  
Color Space ◽  
Low Frequency ◽  
New Method ◽  
Color Spaces ◽  
Image Watermark ◽  
Color Space Conversion ◽  
Frequency Components ◽  
Orthogonal Transform

Most of watermarking algorithms are for digital grey image, which are not robust against the attacks of print-scan process, and the embedded information capacity is small. To solve these problem, a new method based on DWT transform and Walsh orthogonal transform for the print-scan process of digital color image was proposed. The method chosed the color spaces conversion from RGB to CIEL*a*b* for digital color image. The low frequency components of the DWT transform image was embed the watermark. The results show that the correlation of watermark is improved using Walsh orthogonal transform, the watermark extraction rate is high and image watermark is distinct and readable after print-scan process. And this method is robust against the various attacks of the print-scan process, such as color space conversion, image halftone, D/A conversion, A/D conversion, scaling, rotation, cropping, skew, and random noise signals.

scholarly journals Color Image Segmentation Based on Different Color Space Models Using Automatic GrabCut

2014 ◽  
Vol 2014 ◽  
pp. 1-10 ◽  
Author(s):  
Dina Khattab ◽  
Hala Mousher Ebied ◽  
Ashraf Saad Hussein ◽  
Mohamed Fahmy Tolba
Keyword(s):  
Image Segmentation ◽  
Comparative Study ◽  
Color Image ◽  
Color Space ◽  
User Interaction ◽  
Color Image Segmentation ◽  
Space Representation ◽  
Color Spaces ◽  
Different Color ◽  
The Comparative Study

This paper presents a comparative study using different color spaces to evaluate the performance of color image segmentation using the automatic GrabCut technique. GrabCut is considered as one of the semiautomatic image segmentation techniques, since it requires user interaction for the initialization of the segmentation process. The automation of the GrabCut technique is proposed as a modification of the original semiautomatic one in order to eliminate the user interaction. The automatic GrabCut utilizes the unsupervised Orchard and Bouman clustering technique for the initialization phase. Comparisons with the original GrabCut show the efficiency of the proposed automatic technique in terms of segmentation, quality, and accuracy. As no explicit color space is recommended for every segmentation problem, automatic GrabCut is applied withRGB,HSV,CMY,XYZ, andYUVcolor spaces. The comparative study and experimental results using different color images show thatRGBcolor space is the best color space representation for the set of the images used.

Human Body Parts Detection Using YCbCr Color Space

2013 ◽  
Vol 393 ◽  
pp. 556-560
Author(s):  
Nurul Fatiha Johan ◽  
Yasir Mohd Mustafah ◽  
Nahrul Khair Alang Md Rashid
Keyword(s):  
Human Body ◽  
Skin Color ◽  
Color Space ◽  
Detection Algorithm ◽  
Color Segmentation ◽  
Color Model ◽  
Body Parts ◽  
Color Spaces ◽  
Morphological Operation ◽  
Ycbcr Color Space

Skin color is proved to be very useful technique for human body parts detection. The detection of human body parts using skin color has gained so much attention by many researchers in various applications especially in person tracking, search and rescue. In this paper, we propose a method for detecting human body parts using YCbCr color spaces in color images. The image captured in RGB format will be transformed into YCbCr color space. This color model will be converted to binary image by using color thresholding which contains the candidate human body parts like face and hands. The detection algorithm uses skin color segmentation and morphological operation.

Sign in / Sign up

Export Citation Format

Share Document