Generative Learning of Visual Concepts using Multiobjective Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.8120

@Article{Krawiec07PRL,

• author = "Krzysztof Krawiec",
• title = "Generative Learning of Visual Concepts using Multiobjective Genetic Programming",
• journal = "Pattern Recognition Letters",
• year = "2007",
• volume = "28",
• number = "16",
• pages = "2385--2400",
• month = "1 " # dec,
• email = "krawiec@cs.put.poznan.pl",
• keywords = "genetic algorithms, genetic programming, Visual learning, Generative pattern recognition, Evolutionary synthesis of pattern recognition systems",
• DOI = "doi:10.1016/j.patrec.2007.08.001",
• abstract = "This paper introduces a novel method of visual learning based on Genetic Programming, which evolves a population of individuals (image analysis programs) that process attributed visual primitives derived from raw raster images. The goal is to evolve an image analysis program that correctly recognises the training concept (shape). The approach uses generative evaluation scheme: individuals are rewarded for re-producing the shape of the object being recognised using graphical primitives and elementary background knowledge encoded in predefined operators. Evolutionary run is driven by a multiobjective fitness function to prevent premature convergence and enable effective exploration of the space of solutions. We present the method in detail and verify it experimentally on the task of learning two visual concepts from examples.",

}

Genetic Programming entries for Krzysztof Krawiec

Citations