Color Constancy Algorithm for Mixed-Illuminant Scene Images

Hussain, Akmol; Sheikh-Akbari, Akbar

doi:10.1109/access.2018.2808502

Cited by 17 publications

(21 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a pre-processing step, extensive experiments were performed using the benchmark image dataset to empirically determine the threshold values. The results showed that a threshold value of 0.01 for the T R , T G and T B components can efficiently eliminate segments with uniform areas [55]. Hence, the proposed technique will exclude this segment’s coefficients from contributing into the colour correction of the whole image.…”

Section: Experimental Results and Evaluationmentioning

confidence: 99%

Colour Constancy for Image of Non-Uniformly Lit Scenes

Hussain

Sheikh-Akbari

Mporas

2019

Sensors

Self Cite

View full text Add to dashboard Cite

Digital camera sensors are designed to record all incident light from a captured scene, but they are unable to distinguish between the colour of the light source and the true colour of objects. The resulting captured image exhibits a colour cast toward the colour of light source. This paper presents a colour constancy algorithm for images of scenes lit by non-uniform light sources. The proposed algorithm uses a histogram-based algorithm to determine the number of colour regions. It then applies the K-means++ algorithm on the input image, dividing the image into its segments. The proposed algorithm computes the Normalized Average Absolute Difference (NAAD) for each segment and uses it as a measure to determine if the segment has sufficient colour variations. The initial colour constancy adjustment factors for each segment with sufficient colour variation is calculated. The Colour Constancy Adjustment Weighting Factors (CCAWF) for each pixel of the image are determined by fusing the CCAWFs of the segments, weighted by their normalized Euclidian distance of the pixel from the center of the segments. Results show that the proposed method outperforms the statistical techniques and its images exhibit significantly higher subjective quality to those of the learning-based methods. In addition, the execution time of the proposed algorithm is comparable to statistical-based techniques and is much lower than those of the state-of-the-art learning-based methods.

show abstract

Section: Experimental Results and Evaluationmentioning

confidence: 99%

Colour Constancy for Image of Non-Uniformly Lit Scenes

Hussain

Sheikh-Akbari

Mporas

2019

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…The proposed algorithm has been evaluated using the multiple illuminant and multiple object (MIMO) dataset [6,27] to perform a comparison between the classification results provided by the dataset and the obtained results using the proposed methodology. The MIMO dataset comprises: (a) 58 laboratory images with a spatial resolution of 452 × 260 representing indoor scenarios under controlled lighting conditions; these images are illuminated by two lighting sources, which ensure that these images have nonhomogeneous lighting conditions regardless of the position of the illuminant, and (b) 20 real‐world images with spatial resolution of 452 × 302 that were taken under uncontrolled lighting conditions; these are exposed to lighting sources such as indoor light, skylight, color projector lighting, and shadows.…”

Section: Experimental Validationmentioning

confidence: 99%

“…In scientific literature, these algorithms are based on the color constancy (CC) phenomenon [3‐5]. The CC algorithms change the hue lighting of the image to reveal the actual colors of the objects by maintaining a constant distribution of the light spectrum across the digital image so that the image appears as if it has been taken under a canonical source illuminant [6]. In other words, these algorithms can simulate the colors' behavior in the captured scene as if it were illuminated with a known illuminant regardless of the color of the illumination source.…”

Section: Introductionmentioning

confidence: 99%

Lighting source classification applied in color images to contrast enhancement

Dehesa‐González

Rosales

Gallegos‐Funes

et al. 2020

Color Research & Application

View full text Add to dashboard Cite

A novel methodology is proposed to identify the distribution of the intensity of the illuminant across a real‐world image; with this information, the image can be classified as a homogeneous or nonhomogeneous lighting source. A criterion is proposed for deciding whether the illumination in the tested image is homogeneous or nonhomogeneous. This criterion is based on well‐established methods that are dedicated to improving color characteristics and are commonly used to determine the color of the lighting source during a captured scene. The classification of homogeneous or nonhomogeneous illumination in real‐world images is implemented in the BSD500 database, and the results are compared with a manual classification of images—proposed under subjective criteria—by the authors; in this way, one can analyze how the lighting source affects the image. This procedure provides a classification methodology for real‐world image databases found in the scientific literature.

show abstract

“…C OLOR constancy is a fundamental task in the fields of computer vision, computational photography and image processing [1], [2]. Its ultimate objective is to recover the intrinsic surface color by removing the effect of illuminant chromaticity [3]- [6]. In this regard, it is crucial to separate illuminant chromaticity from a digital image where surface and illuminant colors are mixed.…”

Section: Introductionmentioning

confidence: 99%

Deep Spatio-Temporal Illuminant Estimation Under Time-Varying AC Lights

Yoo

Lee

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Artificial lights, which are powered by alternating current (AC), are ubiquitous nowadays. The intensity of these lights fluctuates dynamically depending on the AC power. In contrast to previous color constancy methods that exploited the spatial color information, we propose a novel deep learning-based color constancy method that exploits the temporal variations exhibited by AC-powered lights. Using a highspeed camera, we capture the intensity variations of AC lights. Then, we use these variations as an important cue for illuminant learning. We propose a network composed of spatial and temporal branches to train the model with both spatial and temporal features. The spatial branch learns the conventional spatial features from a single image, whereas the temporal branch learns the temporal features of AC-induced light intensity variations in a high-speed video. The proposed method calculates the temporal correlation between the highspeed frames to extract the effective temporal features. The calculations are done at a low computational cost and the output is fed into the temporal branch to help the model concentrate on illuminant-attentive regions. By learning both spatial and temporal features, the proposed method performs remarkably under a complex illuminant environment in a real world scenario in which color constancy is difficult to investigate. The experimental results demonstrate that the proposed method produces lower angular error than the previous state-of-the-art by 30%, and works exceptionally well under various illuminants, including complex ambient light environments.INDEX TERMS Temporal color constancy, temporal correlation, AC light, high-speed video.

show abstract

Color Constancy Algorithm for Mixed-Illuminant Scene Images

Cited by 17 publications

References 48 publications

Colour Constancy for Image of Non-Uniformly Lit Scenes

Colour Constancy for Image of Non-Uniformly Lit Scenes

Lighting source classification applied in color images to contrast enhancement

Deep Spatio-Temporal Illuminant Estimation Under Time-Varying AC Lights

Contact Info

Product

Resources

About