Detecting Scale-Invariant Regions Using Evolved Image Operators

Book Chapters

  1. Leonardo Trujillo and Gustavo Olague. Detecting Scale-Invariant Regions Using Evolved Image Operators. In Stefano Cagnoni (ed.). Evolutionary Image Analysis and Signal Processing. Studies in Computational Intelligence series, volume 213, Springer Berlin Heidelberg, 2009, pages 21-40. URL, DOI BibTeX

    	year = 2009,
    	isbn = "978-3-642-01635-6",
    	booktitle = "Evolutionary Image Analysis and Signal Processing",
    	volume = 213,
    	series = "Studies in Computational Intelligence",
    	editor = "Cagnoni, Stefano",
    	doi = "10.1007/978-3-642-01636-3_2",
    	title = "Detecting Scale-Invariant Regions Using Evolved Image Operators",
    	url = "",
    	publisher = "Springer Berlin Heidelberg",
    	author = "Trujillo, Leonardo and Olague, Gustavo",
    	pages = "21-40"


This chapter describes scale-invariant region detectors that are based on image operators synthesized through Genetic Programming (GP). Interesting or salient regions on an image are of considerable usefulness within a broad range of vision problems, including, but not limited to, stereo vision, object detection and recognition, image registration and content-based image retrieval. A GP-based framework is described where candidate image operators are synthesized by employing a fitness measure that promotes the detection of stable and dispersed image features, both of which are highly desirable properties. After a significant number of experimental runs, a plateau of maxima was identified within the search space that contained operators that are similar, in structure and/or functionality, to basic LoG or DoG filters. Two such operators with the simplest structure were selected and embedded within a linear scale space, thereby making scale-invariant feature detection a straightforward task. The proposed scale-invariant detectors exhibit a high performance on standard tests when compared with state-of-the-art techniques. The experimental results exhibit the ability of GP to construct highly reusable code for a well known and hard task when an appropriate optimization problem is framed.

Published in
Evolutionary Image Analysis and Signal Processing
Studies in Computational Intelligence
Pages 21-40
Chapter 2
Volume 213
Last modified on%PM, %12 %767 %2013 %17:%Oct
(0 votes)
Read 4342 times