Using Evolution to Learn How to Perform Interest Point Detection

Created by W.Langdon from gp-bibliography.bib Revision:1.3973

@InProceedings{Trujillo:2006:ICPR,
  author =       "L. Trujillo and G. Olague",
  title =        "Using Evolution to Learn How to Perform Interest Point
                 Detection",
  booktitle =    "ICPR 2006 18th International Conference on Pattern
                 Recognition",
  year =         "2006",
  editor =       "X. Y Tang et al.",
  volume =       "1",
  pages =        "211--214",
  month =        "20-24 " # aug,
  publisher =    "IEEE",
  keywords =     "genetic algorithms, genetic programming",
  URL =          "http://www.genetic-programming.org/hc2006/Olague-Paper-2-ICPR-2006.pdf",
  DOI =          "doi:10.1109/ICPR.2006.1153",
  abstract =     "The performance of high-level computer vision
                 applications is tightly coupled with the low-level
                 vision operations that are commonly required. Thus, it
                 is advantageous to have low-level feature extractors
                 that are optimal with respect to a desired performance
                 criteria. This paper presents a novel approach that
                 uses Genetic Programming as a learning framework that
                 generates a specific type of low-level feature
                 extractor: Interest Point Detector. The learning
                 process is posed as an optimization problem. The
                 optimization criterion is designed to promote the
                 emergence of the detectors' geometric stability under
                 different types of image transformations and global
                 separability between detected points. This concept is
                 represented by the operators repeatability rate [11].
                 Results prove that our approach is effective at
                 automatically generating low-level feature extractors.
                 This paper presents two different evolved operators:
                 IPGP1 and IPGP2. Their performance is comparable with
                 the Harris [5] operator given their excellent
                 repeatability rate. Furthermore, the learning process
                 was able to rediscover the DET corner detector proposed
                 by Beaudet.",
}

Genetic Programming entries for Leonardo Trujillo Gustavo Olague

Citations