Learning features for object recognition

Authors:
Yingqiang Lin;Bir Bhanu
Affiliations:
Center for Research in Intelligent Systems, University of California, Riverside, CA;Center for Research in Intelligent Systems, University of California, Riverside, CA
Venue:
GECCO'03 Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartII
Year:
2003

Citing 5
Cited 2

Target detection in SAR imagery by genetic programming

Advances in Engineering Software
Evolution of Vehicle Detectors for Infrared Line Scan Imagery

EvoIASP '99/EuroEcTel '99 Proceedings of the First European Workshops on Evolutionary Image Analysis, Signal Processing and Telecommunications
Learning Composite Operators For Object Detection

GECCO '02 Proceedings of the Genetic and Evolutionary Computation Conference
Genetic Programming for Automatic Target Classification and Recognition

EP '98 Proceedings of the 7th International Conference on Evolutionary Programming VII
Genetic Programming for Feature Detection and Image Segmentation

Selected Papers from AISB Workshop on Evolutionary Computing

Optimized texture operators for the automated design of image analysis systems: Non-linear and oriented kernels vs. gray value co-occurrence matrices

International Journal of Hybrid Intelligent Systems - Hybridization of Intelligent Systems
Multiclass Object Recognition Based on Texture Linear Genetic Programming

Proceedings of the 2007 EvoWorkshops 2007 on EvoCoMnet, EvoFIN, EvoIASP,EvoINTERACTION, EvoMUSART, EvoSTOC and EvoTransLog: Applications of Evolutionary Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Features represent the characteristics of objects and selecting or synthesizing effective composite features are the key factors to the performance of object recognition. In this paper, we propose a co-evolutionary genetic programming (CGP) approach to learn composite features for object recognition. The motivation for using CGP is to overcome the limitations of human experts who consider only a small number of conventional combinations of primitive features during synthesis. On the other hand, CGP can try a very large number of unconventional combinations and these unconventional combinations may yield exceptionally good results in some cases. Our experimental results with real synthetic aperture radar (SAR) images show that CGP can learn good composite features. We show results to distinguish objects from clutter and to distinguish objects that belong to several classes.