Perez, Frank and Koch, Christof (1994) Toward color image segmentation in analog VLSI: Algorithm and hardware. International Journal of Computer Vision, 12 (1). pp. 17-42. ISSN 0920-5691. http://resolver.caltech.edu/CaltechAUTHORS:20130816-103219659
- Published Version
See Usage Policy.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20130816-103219659
Standard techniques for segmenting color images are based on finding normalized RGB discontinuities, color histogramming, or clustering techniques in RGB or CIE color spaces. The use of the psychophysical variable hue in HSI space has not been popular due to its numerical instability at low saturations. In this article, we propose the use of a simplified hue description suitable for implementation in analog VLSI. We demonstrate that if theintegrated white condition holds, hue is invariant to certain types of highlights, shading, and shadows. This is due to theadditive/shift invariance property, a property that other color variables lack. The more restrictive uniformly varying lighting model associated with themultiplicative/scale invariance property shared by both hue and normalized RGB allows invariance to transparencies, and to simple models of shading and shadows. Using binary hue discontinuities in conjunction with first-order type of surface interpolation, we demonstrate these invariant properties and compare them against the performance of RGB, normalized RGB, and CIE color spaces. We argue that working in HSI space offers an effective method for segmenting scenes in the presence of confounding cues due to shading, transparency, highlights, and shadows. Based on this work, we designed and fabricated for the first time an analog CMOS VLSI circuit with on-board phototransistor input that computes normalized color and hue.
|Additional Information:||Cover Date: 1994-02-01. Received September 26, 1991; Revised April 22 and November 11, 1992; April 20, 1993. The authors would like to thank John Harris and Andy Moore for illuminating discussions, and Steven Shafer of Carnegie Mellon University's Calibrated Imaging Laboratory (which is sponsored by NSF, DARPA, and NASA) for the original data that was used to generate the images in figure 8. This research was supported by the James S. McDonnell Foundation, the National Science Foundation, the Office of Naval Research, and by Rockwell International Science Center.|
|Group:||Koch Laboratory, KLAB|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||KLAB Import|
|Deposited On:||16 May 2008 00:51|
|Last Modified:||16 Sep 2013 16:39|
Repository Staff Only: item control page