Termite Retinex: a new implementation based on a colony of intelligent agents

Simone, Gabriele; Audino, Giuseppe; Farup, Ivar; Albregtsen, Fritz; Rizzi, Alessandro

doi:10.1117/1.jei.23.1.013006

Cited by 49 publications

(19 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The computational complexity of the TR sampling approach is O(Nl|I |). Based on some experimental results, the work in [11] suggests to set up l as the 70% of the length of the diagonal of Supp(I ). This makes the complexity of TR much smaller than O(N|I | 2 ).…”

Section: B Image Aware Image Sampling: Tr and Etrmentioning

confidence: 99%

“…After the image exploration, TR computes the color sensation by the ratio-product-reset mechanism of MI-Retinex [3], as described in [7] and reported in [11].…”

Section: B Image Aware Image Sampling: Tr and Etrmentioning

confidence: 99%

“…The work we present here originates from two recent path-based implementations of Milano Retinex [3], [10], a class of Retinex algorithms mainly developed for color image enhancement: Termite Retinex (TR) [11] and Energy-driven Termite Retinex (ETR) [12]. The main novelty of these methods is their image aware spatial color sampling, i.e.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

GRASS: A Gradient-Based Random Sampling Scheme for Milano Retinex

Lecca

Rizzi

Serapioni

2017

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Retinex is an early and famous theory attempting to estimate the human color sensation derived from an observed scene. When applied to a digital image, the original implementation of retinex estimates the color sensation by modifying the pixels channel intensities with respect to a local reference white, selected from a set of random paths. The spatial search of the local reference white influences the final estimation. The recent algorithm energy-driven termite retinex (ETR), as well as its predecessor termite retinex, has introduced a new path-based image aware sampling scheme, where the paths depend on local visual properties of the input image. Precisely, the ETR paths transit over pixels with high gradient magnitude that have been proved to be important for the formation of color sensation. Such a sampling method enables the visit of image portions effectively relevant to the estimation of the color sensation, while it reduces the analysis of pixels with less essential and/or redundant data, i.e., the flat image regions. While the ETR sampling scheme is very efficacious in detecting image pixels salient for the color sensation, its computational complexity can be a limit. In this paper, we present a novel Gradient-based RAndom Sampling Scheme that inherits from ETR the image aware sampling principles, but has a lower computational complexity, while similar performance. Moreover, the new sampling scheme can be interpreted both as a path-based scanning and a 2D sampling.

show abstract

Section: B Image Aware Image Sampling: Tr and Etrmentioning

confidence: 99%

“…After the image exploration, TR computes the color sensation by the ratio-product-reset mechanism of MI-Retinex [3], as described in [7] and reported in [11].…”

Section: B Image Aware Image Sampling: Tr and Etrmentioning

confidence: 99%

See 1 more Smart Citation

GRASS: A Gradient-Based Random Sampling Scheme for Milano Retinex

Lecca

Rizzi

Serapioni

2017

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Many SCAs exist, derived from Retinex theory by Land and McCann 15 and Land 16 . Among the many SCA algorithms we recall in particular RSR by Provenzi et al 17 , STRESS by Kolås et al 18 , ACE by Rizzi et al 19 , RACE by Provenzi et al 20 , Termite Retinex by Simone et al 21 and QBRIX by Gianini et al 22 .…”

Section: Spatial Color Algorithms and Clahementioning

confidence: 99%

A novel approach to visual rendering of astro-photographs

2016

View full text Add to dashboard Cite

When we perform a visual analysis of a cosmic object photograph the contrast plays a fundamental role. A linear distribution of the observable values is not necessarily the best possible for the Human Visual System (HVS). In fact HVS has a non-linear response, and exploits contrast locally with different stretching for different lightness areas. As a consequence, according to the observation task, local contrast can be adjusted to make easier the detection of relevant information. The proposed approach is based on Spatial Color Algorithms (SCA) that mimic the HVS behavior. These algorithms compute each pixel value by a spatial comparison with all (or a subset of) the other pixels of the image. The comparison can be implemented as a weighted difference or as a ratio-product over given sampling in the neighbor region. A final mapping allows exploiting all the available dynamic range. In the case of color images SCA process separately the three chromatic channels producing an effect of color normalization, without introducing channel cross correlation. We will present very promising results on amateur photographs of deep sky objects. The results are presented for a qualitative and subjective visual evaluation and for a quantitative evaluation through image quality measures, in particular to quantify the effect of algorithms on the noise. Moreover our results help to better characterize contrast measures.

show abstract

“…The straightforward random path-based computation presented by Land and McCann [10] has been modified to consider various models such as random sprays [13], Brownian motion [11,14], or swarn termites movement [15]. Retinex has been also mathematically defined using minimizations based on the Laplacian of the image [6] or variational-based energy minimizations [7].…”

Section: Introductionmentioning

confidence: 99%

Image processing applications through a variational perceptually-based color correction related to Retinex

Vázquez-Corral¹,

Zamir²,

Galdrán³

et al. 2016

View full text Add to dashboard Cite

The retinex theory of color vision has been a light of inspiration for color researchers since its inception 50 years ago. It has been adapted to work for different goals such as shadow removal, high dynamic range imaging, or computational color constancy. Back in 2007 a variational perceptually-based color correction model related to Retinex was presented by Bertalmío and colleagues. In this paper we first comment on this model and later we review different image processing applications that have been obtained by performing small modifications to it, namely color gamut mapping and image dehazing.

show abstract

Termite Retinex: a new implementation based on a colony of intelligent agents

Cited by 49 publications

References 41 publications

GRASS: A Gradient-Based Random Sampling Scheme for Milano Retinex

GRASS: A Gradient-Based Random Sampling Scheme for Milano Retinex

A novel approach to visual rendering of astro-photographs

Image processing applications through a variational perceptually-based color correction related to Retinex

Contact Info

Product

Resources

About