Colorizing a Masterpiece [Applications Corner]

  title={Colorizing a Masterpiece [Applications Corner]},
  author={Sotirios A. Tsaftaris and Kristin H. Lister and Inge Fiedler and Francesca Casadio and Aggelos K. Katsaggelos},
  journal={IEEE Signal Processing Magazine},
The purpose of this article is to discuss the process of colorizing a historical arti fact-a black and white archival photo of Bathers by a River, 1909-1917, by Henri Matisse (Art Institute of Chicago 1953.158), taken in November 1913, when the art ist was still working on the painting and showing it in a significantly differ ent state compared to the one seen today. Historical accounts describe a painting that was originally a more nat uralistic, pastoral image; but over the course of several… 

Figures from this paper

A novel visualization tool for art history and conservation: Automated colorization of black and white archival photographs of works of art

Abstract This paper describes the use of a customized algorithm for the colorization of historical black and white photographs documenting earlier states of paintings. This study specifically focuses

Estimation of scribble placement for painting colorization

  • Cristian RusuS. Tsaftaris
  • Computer Science
    2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA)
  • 2013
It is found that for the case of Picasso on average 10% of scribble coverage is enough and that flat areas can be presented by few scribbles, and the proposed method can be used verbatim to test any colorization algorithm.

Image hallucination at different times of day using locally affine model and kNN template matching from time-lapse images

This paper presents an image Hallucination technique based on the template (patch) matching from the database of time lapse images and learned locally affine model, and proposes two approaches for imposing consistency criteria across neighbouring patches in the form of regularization.



Matisse's methods revealed

embarked on a period of restless experimentation, eschewing the rich colours and sinuous lines of his earlier works for a more abstract, geometric approach to painting, dominated by blacks and greys.

Rejuvenating the color palette of Georges Seurat'sA Sunday on La Grande Jatte—1884: A simulation

Georges Seurat first employed his divisionist painting technique, commonly called pointillism, on A Sunday on La Grande Jatte—1884 beginning in October 1885. Painting with pigments representing

Image processing for the analysis and conservation of paintings: opportunities and challenges

This column sketches the main applications that could benefit from the introduction of ad hoc image processing tools, outlines the state-of-the-art, and discusses the main obstacles impeding a more fruitful cooperation between the image processing community and art historians, restorers, and artists in general.

Matisse: Radical Invention, 1913-1917

The works that Henri Matisse (1869-1954) executed between late 1913 and 1917 are among his most demanding, experimental, and enigmatic. Often sharply composed, heavily reworked, and dominated by the

Natural Image Colorization

An interactive system for users to easily colorize the natural images of complex scenes and employs a smoothness map to guide the incorporation of intensity-continuity and texture-similarity constraints in the design of the labeling algorithm.

Colorization using optimization

This paper presents a simple colorization method that requires neither precise image segmentation, nor accurate region tracking, and demonstrates that high quality colorizations of stills and movie clips may be obtained from a relatively modest amount of user input.

Fast image and video colorization using chrominance blending

Based on the concepts of luminance-weighted chrominance blending and fast intrinsic distance computations, high-quality colorization results for still images and video are obtained at a fraction of the complexity and computational cost of previously reported techniques.

Transferring color to greyscale images

This approach attempts to provide a method to help minimize the amount of human labor required for this task by transferring color between a source, color image and a destination, greyscale image by matching luminance and texture information between the images.

Unsupervised colorization of black-and-white cartoons

We present a novel color-by-example technique which combines image segmentation, patch-based sampling and probabilistic reasoning. This method is able to automate colorization when new color

Dynamic histogram warping of image pairs for constant image brightness

It is believed that an expansion/contraction matching of the intensity histograms represents the best method to both measure the degree of validity of the CIB assumption and correct for it.