Synthesis of interest point detectors through genetic programming

Published in Conferences Papers
  1. Leonardo Trujillo and Gustavo Olague. Using Evolution to Learn How to Perform Interest Point Detection. In Proceedings of the 18th International Conference on Pattern Recognition - Volume 01. 2006, 211–214. URL, DOI BibTeX

    @inproceedings{Trujillo:2006:UEL:1170747.1171958,
    	author = "Trujillo, Leonardo and Olague, Gustavo",
    	title = "Using Evolution to Learn How to Perform Interest Point Detection",
    	booktitle = "Proceedings of the 18th International Conference on Pattern Recognition - Volume 01",
    	series = "ICPR '06",
    	year = 2006,
    	isbn = "0-7695-2521-0",
    	pages = "211--214",
    	numpages = 4,
    	url = "http://dx.doi.org/10.1109/ICPR.2006.1153",
    	doi = "10.1109/ICPR.2006.1153",
    	acmid = 1171958,
    	publisher = "IEEE Computer Society",
    	address = "Washington, DC, USA"
    }
    
Abstract

This contribution presents a novel approach for the automatic generation of a low-level feature extractor that is useful in higher-level computer vision tasks. Specifically, our work centers on the well-known computer vision problem of interest point detection. We pose interest point detection as an optimization problem, and are able to apply Genetic Programming to generate operators that exhibit human-competitive performace when compared with state-of-the-art designs. This work uses the repeatability rate that is applied as a benchmark metric in computer vision literature as part of the GP fitness function, together with a measure of the entropy related with the point distribution across the image. This two measures promote geometric stability and global separability under several types of image transformations. This paper introduces a Genetic Programming implementation that was able to discover a modified version of the DET operator [3], that shows a surprisingly high-level of performace. In this work emphasis was given to the balance between genetic programming and domain knowledge expertise to obtain results that are equal or better than human created solutions.

Published in
Proceeding GECCO '06 Proceedings of the 8th annual conference on Genetic and evolutionary computation
http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=10468
(Awarded the bronze medal at the 2006 Human-Competetive Awards)
Date of conference
08 - 12 July 2006
Pages
887-894
ISBN
1-59593-186-4
Feedback