Abstract
A key problem in model-based object recognition is selection, namely, the problem of determining which regions in an image are likely to come from a single object. In this paper we present an approach that uses color as a cue to perform selection either based solely on image-data (data-driven), or based on the knowledge of the color description of the model (model-driven). It presents a method of color specification by color categories which are used to design a fast segmentation algorithm to extract perceptual color regions. Data driven selection is then achieved by selecting salient color regions while model-driven selection is achieved by locating instances of the model in the image using the color region description of the model. The approach presented here tolerates some of the problems of occlusion, pose and illumination changes that make a model instance in an image appear different from its original description.
This paper describes research done at the AI Lab., M.I.T. Support for the lab's research is provided in part by Office of Naval Research and in part by the Advanced Research Projects Agency of the Dept. of Defense. The author is supported by an IBM Fellowship.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
D.T. Clemens and D.W. Jacobs, “Space and time bounds on indexing 3D models from 2D images,” IEEE Trans. Pattern Anal. and Machine Intelligence, vol. 13, Oct. 1991.
T. F. Syeda-Mahmood, “Data and model-driven selection using color regions,” AI-Memo 1270, Artificial Intelligence Lab., M.I.T., 1992.
W.E.L. Grimson., Object Recognition by Computer: The Role of Geometric Constraints, MIT Press: Cambridge, 1990.
D.G. Lowe, Perceptual Organization and Visual Recognition, Kluwer Academic: Boston, 1985.
G.J. Klinker, S.A. Shafer, and T. Kanade, “A physical approach to color image understanding,” Intl. Jl. Computer Vision, vol.4, no.1., pp.7–38, Jan. 1990.
E. Land, “Recent advances in retinex theory,” inCentral and Peripheral Mechanisms of color Vision, T. Ottoson and S. Zeki Ed., pp. 5–17, London:McMillan, 1985.
L. T. Maloney and B. Wandel, “Color constancy: A method for recovering surface spectral reflectance,” Jl. Optical Society of America, vol.3, 1986, pp.29–33.
E. Sternheim and R. Boynton, “Uniqueness of perceived hues investigated with a continuous judgemental technique,” Jl. of Experimental Psychology, vol.72, pp.770–776, 1966.
M.J. Swain and D. Ballard, “Indexing via color histograms,” Third Int. Conf. Computer Vision, 1990.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Syeda-Mahmood, T.F. (1992). Data and model-driven selection using color regions. In: Sandini, G. (eds) Computer Vision — ECCV'92. ECCV 1992. Lecture Notes in Computer Science, vol 588. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-55426-2_14
Download citation
DOI: https://doi.org/10.1007/3-540-55426-2_14
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-55426-4
Online ISBN: 978-3-540-47069-4
eBook Packages: Springer Book Archive