Reflectance ratios: An extension of Land's retinex theory

Neighboring points on a smoothly curved surface have similar surface orientations and illumination conditions. Therefore, their brightness values can be used to compute the ratio of their reflectance coefficients. We develop an algorithm that estimates a reflectance ratio for each region in an image with respect to its background. The region reflectance ratio represents a physical property that is invariant to illumination and imaging parameters and is an extension of Land's “Lightness” defined in his Retinex theory. The ratio invariant is used to automatically build representations of objects and recognize objects from a single brightness image of a scene.

[1]  E. Land Recent advances in retinex theory , 1986, Vision Research.

[2]  J.B. Burns,et al.  View Variation of Point-Set and Line-Segment Features , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Shree K. Nayar,et al.  Computing reflectance ratios from an image , 1993, Pattern Recognit..

[4]  J. Koenderink,et al.  Photometric Invariants Related to Solid Shape , 1980 .

[5]  Shree K. Nayar,et al.  Reflectance ratio: A photometric invariant for object recognition , 1993, 1993 (4th) International Conference on Computer Vision.

[6]  E H Land,et al.  Recent advances in retinex theory and some implications for cortical computations: color vision and the natural image. , 1983, Proceedings of the National Academy of Sciences of the United States of America.

[7]  Charles R. Dyer,et al.  Model-based recognition in robot vision , 1986, CSUR.

[8]  Ramesh C. Jain,et al.  Three-dimensional object recognition , 1985, CSUR.

[9]  Rakesh Mohan,et al.  Multidimensional indexing for recognizing visual shapes , 1991, CVPR 1991.