Decolorize:
Fast, Contrast Enhancing,
Color to Grayscale Conversion
Web: www.Eyemaginary.com
Email: Mark@Eyemaginary.com
|
|
|
| Color Image | Standard Grayscale | Enhanced Grayscale |
Citation:
Decolorize: Fast, Contrast Enhancing, Color to Grayscale Conversion
Mark Grundland and Neil A. Dodgson
Pattern Recognition, vol. 40, no. 11, pp. 2891-2896, (2007). ISSN 0031-3203.
Presented also as a poster at the International Symposium on Non-Photorealistic Animation and Rendering (Annecy, France, 5-7 June, 2006).Extended version published as Computer Laboratory Technical Report UCAM-CL-TR-649, (University of Cambridge, United Kingdom, October 2005). ISSN 1476-2986.
Abstract:
We present a new contrast enhancing color to grayscale conversion algorithm which works in real-time. It incorporates novel techniques for image sampling and dimensionality reduction, sampling color differences by Gaussian pairing and analyzing color differences by predominant component analysis. In addition to its speed and simplicity, the algorithm has the advantages of continuous mapping, global consistency, and grayscale preservation, as well as predictable luminance, saturation, and hue ordering properties.
Online:
Paper + Illustrations + Bibliography
Technical Report + Poster + Abstract
Evaluation:
Perceptual Evaluation of Color-to-Grayscale Image Conversions
M. Cadik
Computer Graphics Forum, vol. 27, no. 7, pp. 1745-1754, (2008).In 2008, Cadik performed a comprehensive review of color to grayscale conversion algorithms based on nearly 20,000 responses from over 100 viewers evaluating the performance of 7 state-of-the-art techniques on a standard set of 24 images. In this independent evaluation, our decolorize technique obtained the highest preference score and the second highest accuracy score. Of all the techniques considered, our decolorize technique earned the top overall score, though only slightly ahead of the apparent grayscale technique of Smith, Landes, Thollo, and Myszkowski. Note that our decolorize technique was tested with the degree of image enhancement set to 0.5, which tends to somewhat exaggerate contrast; for practical use in color to grayscale conversion, the recommended setting is 0.3.
Applications:
A Bidirectional Light Field - Hologram Transform
R. Ziegler, S. Bucheli, L. Ahrenberg, M. Magnor, and M. Gross
Computer Graphics Forum, vol.26, no.3, pp. 435-46, (2007).A Hierarchical Object Recognition System Based on Multi-Scale Principal Curvature Regions
Z. Wei, D. Hongli, T. G. Dietterich, and E. N. Mortensen
Proceedings of the International Conference on Pattern Recognition, vol. 1, pp. 778-782, IEEE, (2006).
Commercial Uses:
Fotomietstudio24
Nuernberg, Germany, (2008).
Examples:
| Color Image | Standard Grayscale | Enhanced Grayscale |
 |
 |
 |
| Color Image | Standard Grayscale | Enhanced Grayscale |
Website traffic statistics
were reset in February 2014.
Copyright © 2015 Mark Grundland. All
rights reserved.