UCT CS Research Document Archive

Genetic Parameter Tuning for Reliable Segmentation of Colored Visual Tags

Mbogho, Audrey J.W. and Lori L. Scarlatos (2007) Genetic Parameter Tuning for Reliable Segmentation of Colored Visual Tags. In Thierens et al., Dirk et al., Eds. Proceedings Genetic and Evolutionary Computation Conference II, pages 1525, London, England.

Full text available as:
PDF - Requires Adobe Acrobat Reader or other PDF viewer.

Abstract

This paper reports on a case study on segmentation of colored visual tags for object identification. Lighting variations result in uncertainty in color thresholds leading to unreliable overall system behavior. We describe an experiment with a genetic algorithm (GA) approach for generating reliable thresholds for color identification. We compare it with a maximum distance (MD) approach, and demonstrate that the genetic approach is far more accurate and reliable.

EPrint Type:Conference Paper
Keywords:visual tags
genetic algorithms
image segmentation
parameter tuning
Subjects:I Computing Methodologies: I.4 IMAGE PROCESSING AND COMPUTER VISION
ID Code:437
Deposited By:Mbogho, Audrey J. W.
Deposited On:29 November 2007
Alternative Locations:http://people.cs.uct.ac.za/~ambogho/papers/gecco2007.pdf