Paper
27 March 1989 Learning Lightness Algorithms
Anya C. Hurlbert, Tomaso A. Poggio
Author Affiliations +
Proceedings Volume 1002, Intelligent Robots and Computer Vision VII; (1989) https://doi.org/10.1117/12.960280
Event: 1988 Cambridge Symposium on Advances in Intelligent Robotics Systems, 1988, Boston, MA, United States
Abstract
Lightness algorithms, which recover surface reflectance from the image irradiance signal in individual color channels, provide one solution to the computational problem of color constancy. We compare three methods for constructing (or "learning") lightness algorithms from examples in a Mondrian world: optimal linear estimation, backpropagation (BP) on a two-layer network, and optimal polynomial estimation. In each example, the input data (image irradiance) is paired with the desired output (surface reflectance). Optimal linear estimation produces a lightness operator that is approximately equivalent to a center-surround, or bandpass, filter and which resembles a new lightness algorithm recently proposed by Land. This technique is based on the assumption that the operator that transforms input into output is linear, which is true for a certain class of early vision algorithms that may therefore be synthesized in a similar way from examples. Although the backpropagation net performs slightly better on new input data than the estimated linear operator, the optimal polynomial operator of order two performs marginally better than both.
© (1989) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Anya C. Hurlbert and Tomaso A. Poggio "Learning Lightness Algorithms", Proc. SPIE 1002, Intelligent Robots and Computer Vision VII, (27 March 1989); https://doi.org/10.1117/12.960280
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Reflectivity

Computer vision technology

Evolutionary algorithms

Machine vision

Robot vision

Robots

Linear filtering

RELATED CONTENT

Geometric Reasoning In Task Planning
Proceedings of SPIE (December 11 1985)
Measuring shapes by size functions
Proceedings of SPIE (February 01 1992)
A Heuristic Route Planner For Autonomous Robots
Proceedings of SPIE (January 17 1985)
Shape And Correspondence
Proceedings of SPIE (March 27 1987)
Intelligent material handling: use of vision
Proceedings of SPIE (February 01 1991)
Default Knowledge With Partial Matching
Proceedings of SPIE (March 01 1990)
Optimal 3D object surface identification
Proceedings of SPIE (August 06 1993)

Back to Top