Multiobjective design of operators that detect points of interest in images

Published in Conferences Papers
  1. Leonardo Trujillo, Gustavo Olague, Francisco Fernández De Vega and Evelyne Lutton. Selecting Local Region Descriptors with a Genetic Algorithm for Real-world Place Recognition. In Proceedings of the 2008 Conference on Applications of Evolutionary Computing. 2008, 325–334. URL BibTeX

    	author = "Trujillo, Leonardo and Olague, Gustavo and De Vega, Francisco Fern\'{a}ndez and Lutton, Evelyne",
    	title = "Selecting Local Region Descriptors with a Genetic Algorithm for Real-world Place Recognition",
    	booktitle = "Proceedings of the 2008 Conference on Applications of Evolutionary Computing",
    	series = "Evo'08",
    	year = 2008,
    	isbn = "3-540-78760-7, 978-3-540-78760-0",
    	location = "Naples, Italy",
    	pages = "325--334",
    	numpages = 10,
    	url = "",
    	acmid = 1787980,
    	publisher = "Springer-Verlag",
    	address = "Berlin, Heidelberg"

In this paper, a multiobjective (MO) learning approach to image feature extraction is described, where Pareto-optimal interest point (IP) detectors are synthesized using genetic programming (GP). IPs are image pixels that are unique, robust to changes during image acquisition, and convey highly descriptive information. Detecting such features is ubiquitous to many vision applications, e.g. object recognition, image indexing, stereo vision, and content based image retrieval. In this work, candidate IP operators are automatically synthesized by the GP process using simple image operations and arithmetic functions. Three experimental optimization criteria are considered: 1) the repeatability rate; 2) the amount of global separability between IPs; and 3) the information content captured by the set of detected IPs. The MO-GP search considers Pareto dominance relations between candidate operators, a perspective that has not been contemplated in previous research devoted to this problem. The experimental results suggest that IP detection is an illposed problem for which a single globally optimum solution does not exist. We conclude that the evolved operators outperform and dominate, in the Pareto sense, all previously man-made designs.

Published in
Proceedings of the 10th annual conference on Genetic and evolutionary computation
Pages 1299-1306
Date of conference
12 - 16 July 2008