Reflectance ratio: A photometric invariant for object recognition
- 30 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 280-285
- https://doi.org/10.1109/iccv.1993.378205
Abstract
Neighboring points on a smoothly curved surface have similar surface orientations and illumination conditions. Hence, their brightness values can be used to compute the ratio of their reflectance coefficients. Based on this observation, an efficient algorithm is developed that estimates a reflectance ratio for each region in an image with respect to its background. The region reflectance ratio represents a physical property of a region that is invariant to the illumination conditions. The ratio invariant is used to recognize objects from a single brightness image of a scene. Experimental results demonstrate the power of using reflectance and geometric properties of objects simultaneously Author(s) Nayar, S.K. Dept. of Comput. Sci., Columbia Univ., New York, NY, USA Bolle, R.M.Keywords
This publication has 6 references indexed in Scilit:
- Surface reflection: physical and geometrical perspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991
- Recognizing solid objects by alignment with an imageInternational Journal of Computer Vision, 1990
- Model-based recognition in robot visionACM Computing Surveys, 1986
- Determining lightness from an imageComputer Graphics and Image Processing, 1974
- Lightness and Retinex TheoryJournal of the Optical Society of America, 1971
- The RetinexPublished by Wiley ,1965