PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Machine Learning Methods for Automatic Image Colorization
Guillaume Charpiat, Ilja Bezrukov, Matthias Hofmann, Yasemin Altun and Bernhard Scholkopf
In: Computational Photography: Methods and Applications (2009) CRC Press Online .

Abstract

We aim to color greyscale images automatically, without any manual intervention. The color proposition could then be interactively corrected by user-provided color landmarks if necessary. Automatic colorization is nontrivial since there is usually no one-to-one correspondence between color and local texture. The contribution of our framework is that we deal directly with multimodality and estimate, for each pixel of the image to be colored, the probability distribution of all possible colors, instead of choosing the most probable color at the local level. We also predict the expected variation of color at each pixel, thus defining a non-uniform spatial coherency criterion. We then use graph cuts to maximize the probability of the whole colored image at the global level. We work in the L-a-b color space in order to approximate the human perception of distances between colors, and we use machine learning tools to extract as much information as possible from a dataset of colored examples. The resulting algorithm is fast, designed to be more robust to texture noise, and is above all able to deal with ambiguity, in contrary to previous approaches.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Book Section
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:6114
Deposited By:Yasemin Altun
Deposited On:08 March 2010