Visual Learning by Evolutionary and Coevolutionary Feature Synthesis

Authors:
K. Krawiec;B. Bhanu
Affiliations:
Poznati Univ. of Technol., Poznan;-
Venue:
IEEE Transactions on Evolutionary Computation
Year:
2007

Citing 0
Cited 13

A Real-Time Evolutionary Object Recognition System

EuroGP '09 Proceedings of the 12th European Conference on Genetic Programming
Construction of image feature extractors based on multi-objective genetic programming with redundancy regulations

SMC'09 Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics
Interaction of culture-based learning and cooperative co-evolution and its application to automatic behavior-based system design

IEEE Transactions on Evolutionary Computation
New crossover operators in linear genetic programming for multiclass object classification

Proceedings of the 12th annual conference on Genetic and evolutionary computation
Evolving object detectors with a GPU accelerated vision system

ICES'10 Proceedings of the 9th international conference on Evolvable systems: from biology to hardware
Redundancies in linear GP, canonical transformation, and its exploitation: a demonstration on image feature synthesis

Genetic Programming and Evolvable Machines
Multi-criteria decision making approach based on immune co-evolutionary algorithm with application to garment matching problem

Expert Systems with Applications: An International Journal
Parallel linear genetic programming

EuroGP'11 Proceedings of the 14th European conference on Genetic programming
Towards automated learning of object detectors

EvoApplicatons'10 Proceedings of the 2010 international conference on Applications of Evolutionary Computation - Volume Part I
Parallel linear genetic programming for multi-class classification

Genetic Programming and Evolvable Machines
Modeling global temperature changes with genetic programming

Computers & Mathematics with Applications
Pattern-guided genetic programming

Proceedings of the 15th annual conference on Genetic and evolutionary computation
A feature construction method for general object recognition

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

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. 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 at the genotype level. The training coevolves feature extraction procedures, each being a sequence of elementary image processing and computer vision operations applied to input images. Extensive experimental results show that the approach attains competitive performance for three-dimensional object recognition in real synthetic aperture radar imagery.