A multiscale retinex for bridging the gap between color images and the human observation of scenes

Abstract

Direct observation and recorded color images of the same scenes are often strikingly different because human visual perception computes the conscious representation with vivid color and detail in shadows, and with resistance to spectral shifts in the scene illuminant. A computation for color images that approaches fidelity to scene observation must combine dynamic range compression, color consistency-a computational analog for human vision color constancy-and color and lightness tonal rendition. In this paper, we extend a previously designed single-scale center/surround retinex to a multiscale version that achieves simultaneous dynamic range compression/color consistency/lightness rendition. This extension fails to produce good color rendition for a class of images that contain violations of the gray-world assumption implicit to the theoretical foundation of the retinex. Therefore, we define a method of color restoration that corrects for this deficiency at the cost of a modest dilution in color consistency. Extensive testing of the multiscale retinex with color restoration on several test scenes and over a hundred images did not reveal any pathological behaviour.

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

“…In this section, to evaluate the performance of the proposed low-light enhancement method, the resulting image is compared with those of histogram-based [2,3], transmission map-based [8], variational optimization-based [23], and Retinex-based methods [14,16]. The regularization parameters λ 1 , λ 2 , and λ 3 are determined to have the visually best enhancement result.…”

“…Since f k R is forced to be in the range [0,1], f k L is forced to be larger value than g at each iteration [19]. [2], d Kim's method [3], e Jiang's method [8], f Ravi's method [23], g Jobson's method [14], h Fu's method [16], and i the proposed method (λ 1 = 300, λ 2 = 0.1, λ 3 = 0.9, and ω = 10)…”

“…7 Comparative results using simulated low-light image with σ = 15: a input image, b simulated low-light image, c Chen's method [2], d Kim's method [3], e Jiang's method [8], f Ravi's method [23], g Jobson's method [14], h Fu's method [16], and i the proposed method (λ 1 = 300, λ 2 = 0.2, λ 3 = 0.9, and ω = 10) Fig. 8 Comparative results using simulated low-light image with σ = 20: a input image, b simulated low-light image, c Chen's method [2], d Kim's method [3], e Jiang's method [8], f Ravi's method [23], g Jobson's method [14], h Fu's method [16], and i the proposed method (λ 1 = 300, λ 2 = 0.2, λ 3 = 0.9, and ω = 10) The italicized number represents the highest value among the set of test methods…”

“…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.…”

Illumination Insensitive Face Representation for Face Recognition Based on Modified Weberface

“…Some illumination insensitive features were created by estimating L in the first place and then getting R based on the reflectance model. For example, Multiscale Retinex (MSR) [12] estimates L by smoothing the original face image and obtains the illumination invariant feature R by using the reflectance model. Self quotient image (SQI) [13] also uses a smoothed version as the estimation of L. The smoothing is realized by weighted Gaussian filters.…”