Learning High-Level Visual Concepts Using Attributed Primitives and Genetic Programming

In this paper, we present a novel approach to genetic learning of high-level visual concepts that works with sets of attributed visual primitives rather than with raster images. The paper presents the approach in detail and verifies it in an experiment concerning locating objects in real-world 3D scenes.

[1]  Katsushi Ikeuchi,et al.  Symbolic visual learning , 1997 .

[2]  Rodney A. Brooks,et al.  Artificial Life IV: Proceedings of the Fourth International Workshop on the Synthesis and Simlulation of Living Systmes , 1994 .

[3]  Astro Teller,et al.  PADO: a new learning architecture for object recognition , 1997 .

[4]  Bruce A. Draper,et al.  Learning Blackboard-Based Scheduling Algorithms for Computer Vision , 1992, Int. J. Pattern Recognit. Artif. Intell..

[5]  Louis A. Tamburino,et al.  Evolving pattern recognition systems , 2002, IEEE Trans. Evol. Comput..

[6]  John R. Koza,et al.  Genetic Programming III: Darwinian Invention & Problem Solving , 1999 .

[7]  Ramakant Nevatia,et al.  Improved Rooftop Detection in Aerial Images with Machine Learning , 2003, Machine Learning.

[8]  Trevor Darrell,et al.  Evolving Visual Routines , 1994, Artificial Life.

[9]  Dennis Gabor,et al.  Theory of communication , 1946 .

[10]  D. B. Davis,et al.  Sun Microsystems Inc. , 1993 .

[11]  P. Nordin.  Genetic Programming III - Darwinian Invention and Problem Solving , 1999 .

[12]  R. Sarker,et al.  Fast Texture Segmentation using Genetic Programming , 2003 .

[13]  William D. Smart,et al.  Learning Visual Feature Detectors for Obstacle Avoidance using Genetic Programming , 2003, 2003 Conference on Computer Vision and Pattern Recognition Workshop.

[14]  Krzysztof Krawiec,et al.  Visual learning by coevolutionary feature synthesis , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).