Retinex in Matlab

By Brian V. Funt, F. Ciurea, J. McCann. International Conference on Communications in Computing, 2000

331 citations recorded by the source corpus.

Many different descriptions of retinex methods of lightness computation exist. This paper provides concise MATLAB implementations of two of the spatial techniques of making pixel comparisons. The code is presented along with test results on several images and a discussion of the results . The paper also discusses the calibration of input images and the post-retinex processing required to display the output images.

Subfields: Atomic and Molecular Physics, and Optics, Biomedical Engineering, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/8eda45fa89dd9ed484dae9e51a1689f1cd5925ae

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

In Biomedical Engineering

In Electrical and Electronic Engineering

Citations in the corpus

High dynamic range image rendering with a retinex-based adaptive filter (2006, methodology): “Other the methods that are based on the same smooth illuminant assumption [5], [6], [12], [16] suffer from the same drawback.”
A Generalized Unsharp Masking Algorithm (2011, methodology): “The illuminance is estimated by using a low-pass filter or multiresolution [10] or formulating the estimating problem as a constrained optimization problem [11].”
A Weighted Variational Model for Simultaneous Reflectance and Illumination Estimation (2016, methodology): “These methods require intensive parameter tuning and have high computational complexity, which was later addressed using recursive matrix calculation [5] [21].”
A Probabilistic Method for Image Enhancement With Simultaneous Illumination and Reflectance Estimation (2015, methodology): “In [20], [21], the path computation is replaced by a recursive matrix calculation to make the algorithm more efficient.”
STAR: A Structure and Texture Aware Retinex Model (2019, methodology): “Classical Retinex Methods include path-based methods [12]–[15], Partial Differential Equation (PDE)-based methods [16], [17], center/surround methods [18], [19].”
A Variational Framework for Retinex (2002, background): “(Frankle and McCann, 1983; Funt et al., 2000; McCann, 1999), are an iterative multi-resolution type of non-linear filter.”