Properties and performance of a center/surround retinex

Abstract

The last version of Land's (1986) retinex model for human vision's lightness and color constancy has been implemented and tested in image processing experiments. Previous research has established the mathematical foundations of Land's retinex but has not subjected his lightness theory to extensive image processing experiments. We have sought to define a practical implementation of the retinex without particular concern for its validity as a model for human lightness and color perception. We describe the trade-off between rendition and dynamic range compression that is governed by the surround space constant. Further, unlike previous results, we find that the placement of the logarithmic function is important and produces best results when placed after the surround formation. Also unlike previous results, we find the best rendition for a "canonical" gain/offset applied after the retinex operation. Various functional forms for the retinex surround are evaluated, and a Gaussian form is found to perform better than the inverse square suggested by Land. Images that violate the gray world assumptions (implicit to this retinex) are investigated to provide insight into cases where this retinex fails to produce a good rendition.

Low-light image restoration using bright channel prior-based variational Retinex model

“…where * represents the convolution operator, G is the Gaussian low-pass filter, and logf R is the reflectance image [12]. This method assumes that the slowly changing illumination component can be estimated by the Gaussian low-pass filtered version of the input image.…”

“…Provenzi et al mathematically analyzed the Retinex algorithm and demonstrated the performance according to various parameters such as threshold and the number of path of light paths to a pixel [11]. The Retinex methods enhance the input image by eliminating the illumination component using the low-pass filtering and logarithmic transformation [12][13][14]. However, the resulting image shows the halo effect near the edges.…”

Contrast Enhancement of Color Images Using Improved Retinex Method

“…The illumination is estimated. Retinex is based on the center/surround algorithm [14].The given centre pixel value is compared with the surrounding average pixel values to get the new pixel value. The input value of the center surround functions is obtained by its centre input value and its neighborhood.…”

QBRIX: a quantile-based approach to retinex

“…An overview is out of the scope of this paper; however, these implementations can be divided into two major groups and differ in the ways they achieve locality. The first group, among which we can mention RSR, [1,9,11,[19][20][21] uses a sampling approach: the neighborhood of each pixel is explored either using paths or extracting random pixels; the second group [23,[29][30][31][32] computes values over the image with convolution masks or weighting distances. An extensive review on retinex, including recent PDE and variational implementations, can be found in [33].…”

“…Among the many image sampling methods used, we recall predefined [19][20][21], constrained [22], or Brownian random paths (isotropic memoryless random walks) [11], fixed masks [23], random points [24], multilevel image decomposition [20,21,25]. Moreover, several variational formulations of the model also have been developed so far [6,10,12,26,27].…”