A new algorithm for unsupervised global and local color correction

In this paper, we introduce a novel probabilistic version of retinex. It is based on a probabilistic formalization of the random spray retinex sampling and contributes to the investigation of the spatial properties of the model. Various versions available of the retinex algorithm are characterized by different procedures for exploring the image content (so as to obtain, for each pixel, a reference white value), then used to rescale the pixel lightness. Here we propose an alternative procedure, which computes the reference white value from the percentile values of the pixel population. We formalize two versions of the algorithm: one with global and one with local behavior, characterized by different computational costs.

show abstract

“…(6) gives the most natural results [36]. We have obtained similar results from the same test with local QBRIX; an example is presented in Fig.…”

Section: B Results Algorithm Locality and Choice Of Quantilesupporting

confidence: 62%

QBRIX: a quantile-based approach to retinex

2014

Self Cite

View full text Add to dashboard Cite

show abstract

“…In fact, identical levels of radiance at a point can originate completely different color sensations according to the values in the rest of the image. Clear examples of this behavior are visual illusions [18,19,34]. To reproduce this behavior, SCAs perform spatial comparisons among the pixels in the input image.…”

Section: Spatial Color Algorithms (Scas)mentioning

confidence: 99%

“…Starting from the Retinex theory, during the last years, a range of alternative image appearance models has been implemented, like e.g. ACE [34], RSR [26], STRESS [15].…”

Section: Spatial Color Algorithms (Scas)mentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised digital movie restoration with spatial models of color

Rizzi

Berolo

Bonanomi

et al. 2014

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

In this paper, we present an efficient approach to digital color restoration, based on the idea of recovering the appearance of color rather than the original color signal, since, in most of the cases, for old films the original reference is missing, and new films or digital coding can be subject to severe gamut transformations. This approach is based on the application of algorithms inspired by the capabilities of the Human Vision System of automatically adjust to the variation of color and lightness in the scene. The proposed method allows more unsupervised restoration. We present an overview of the approach, characteristics of this family of algorithms, and restoration examples.

show abstract

“…More recently, for color image enhancement [11], O. P. Verma et al [12] proposed to learn the parameters of membership function used for fuzzification and Rajni et al [13] proposed the color correction for underwater images. Since the systems based on fuzzy logic are resembled with human decision.…”

Section: Introductionmentioning

confidence: 99%

Efficient Color Cast Correction Based on Fuzzy Logic

Verma¹,

Sharma²

2017

JESTR

View full text Add to dashboard Cite

Color cast defect detection of an image is challenging and of great importance in the field of image quality evaluation. This paper presents a simple and less complex method to improve the visibility in color cast images. An objective measure called color cast could be independent of the illumination condition. There are different assumptions present in the literature to provide an estimate of the Red cast, Blue cast and Green cast present in the image. These assumptions sometimes failed to eliminate the effect of color cast under varying illumination condition. The proposed method performs well under these conditions which may involve two steps. Firstly it performs the color cast detection and thereafter, a power law transformation is introduced to achieve the true color distribution of the image. In our approach a new transformation method which corrects the color cast as well as improves the quality of image. The uncertainty in the color distribution due to the illumination is removed on the basis of fuzzy Gaussian membership functions and further, improves by using weighing distribution. The performance analysis of the proposed approach is carried out by using two objective measures the image distance metric criteria of CIELAB color space and the image quality assessment function. The effectiveness of the proposed approach is illustrated by minimizing the image distance between the reference image and corrected image. The computed higher value of the image quality assessment function obtained in the proposed algorithm application on images, also justifies that the proposed algorithm results the better quality of the image in comparison to existing methods.

show abstract

A new algorithm for unsupervised global and local color correction

Cited by 307 publications

References 14 publications

QBRIX: a quantile-based approach to retinex

QBRIX: a quantile-based approach to retinex

Unsupervised digital movie restoration with spatial models of color

Efficient Color Cast Correction Based on Fuzzy Logic

Contact Info

Product

Resources

About