Visual Learning by Evolutionary Feature Synthesis

In this paper, we present a novel method for learning complex concepts/hypotheses directly from raw training data. The task addressed here concerns data-driven synthesis of recognition procedures for real-world object recognition task. The method uses linear genetic programming to encode potential solutions expressed in terms of elementary operations, and handles the complexity of the learning task by applying cooperative coevolution to decompose the problem automatically. The training consists in coevolving feature extraction procedures, each being a sequence of elementary image processing and feature extraction operations. Extensive experimental results show that the approach attains competitive performance for 3-D object recognition in real synthetic aperture radar (SAR) imagery.

[1]  Michael Lee Bryant,et al.  Standard SAR ATR evaluation experiments using the MSTAR public release data set , 1998, Defense, Security, and Sensing.

[2]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques with Java implementations , 2002, SGMD.

[3]  R. Paul Wiegand,et al.  An empirical analysis of collaboration methods in cooperative coevolutionary algorithms , 2001 .

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

[5]  Kenneth A. De Jong,et al.  Cooperative Coevolution: An Architecture for Evolving Coadapted Subcomponents , 2000, Evolutionary Computation.

[6]  Krzysztof Krawiec,et al.  Pairwise Comparison of Hypotheses in Evolutionary Learning , 2001, ICML.

[7]  Krzysztof Krawiec,et al.  Coevolutionary Construction of Features for Transformation of Representation in Machine Learning , 2002 .

[8]  Wolfgang Banzhaf,et al.  Genetic Programming: An Introduction , 1997 .

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

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

[11]  Pankaj Mehra,et al.  Constructive Induction Framework , 1989, ML Workshop.

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

[13]  Bir Bhanu,et al.  Closed-loop object recognition using reinforcement learning , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[14]  David H. Wolpert,et al.  No free lunch theorems for optimization , 1997, IEEE Trans. Evol. Comput..

[15]  Peter Nordin,et al.  Genetic programming - An Introduction: On the Automatic Evolution of Computer Programs and Its Applications , 1998 .

[16]  Manuela M. Veloso,et al.  A Contolled Experiment: Evolution for Learning Difficult Image Classification , 1995, EPIA.

[17]  Bir Bhanu,et al.  Delayed reinforcement learning for adaptive image segmentation and feature extraction , 1998, IEEE Trans. Syst. Man Cybern. Part C.

[18]  R. Poli.  Genetic programming for image analysis , 1996 .