A statistical learning approach to color demosaicing

by   J. H. Oaknin, et al.

A statistical learning/inference framework for color demosaicing is presented. We start with simplistic assumptions about color constancy, and recast color demosaicing as a blind linear inverse problem: color parameterizes the unknown kernel, while brightness takes on the role of a latent variable. An expectation-maximization algorithm naturally suggests itself for the estimation of them both. Then, as we gradually broaden the family of hypothesis where color is learned, we let our demosaicing behave adaptively, in a manner that reflects our prior knowledge about the statistics of color images. We show that we can incorporate realistic, learned priors without essentially changing the complexity of the simple expectation-maximization algorithm we started with.


page 19

page 20


An Expectation-Maximization Algorithm for the Fractal Inverse Problem

We present an Expectation-Maximization algorithm for the fractal inverse...

Blind Decoding-Metric Estimation for Probabilistic Shaping via Expectation Maximization

An unsupervised learning approach based on expectation maximization is p...

Adaptive Interface for Accommodating Colour-Blind Users by Using Ishihara Test

Imperative visual data frequently vanishes when color applications are s...

Nonlinearities and Adaptation of Color Vision from Sequential Principal Curves Analysis

Mechanisms of human color vision are characterized by two phenomenologic...

Federated Expectation Maximization with heterogeneity mitigation and variance reduction

The Expectation Maximization (EM) algorithm is the default algorithm for...

Optimizing Spectral Learning for Parsing

We describe a search algorithm for optimizing the number of latent state...

Continuous Color Transfer

Color transfer, which plays a key role in image editing, has attracted n...

Please sign up or login with your details

Forgot password? Click here to reset