Header logo is ei

Machine Learning Methods for Automatic Image Colorization


Book Chapter


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.

Author(s): Charpiat, G. and Bezrukov, I. and Hofmann, M. and Altun, Y. and Schölkopf, B.
Book Title: Computational Photography: Methods and Applications
Pages: 395-418
Year: 2010
Day: 0

Series: Digital Imaging and Computer Vision
Editors: Lukac, R.
Publisher: CRC Press

Department(s): Empirical Inference
Bibtex Type: Book Chapter (inbook)

Address: Boca Raton, FL, USA
ISBN: 978-1-4398-1749-0
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF


  title = {Machine Learning Methods for Automatic Image Colorization},
  author = {Charpiat, G. and Bezrukov, I. and Hofmann, M. and Altun, Y. and Sch{\"o}lkopf, B.},
  booktitle = {Computational Photography: Methods and Applications},
  pages = {395-418},
  series = {Digital Imaging and Computer Vision},
  editors = {Lukac, R.},
  publisher = {CRC Press},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  address = {Boca Raton, FL, USA},
  year = {2010}