Krzysztof Krawiec


Home

Research:

edit SideBar

We describe a novel method for acquisition of higher-level visual concepts using GP-based learners that process attributed visual primitives derived from raw raster images. The approach uses an original evaluation scheme: individuals-learners are rewarded for being able to restore the essential features (here: shape) of the visual stimulus. The approach is general and does not require any a priori knowledge about the particular application or target concept to be learned; the only prerequisite is universal knowledge related to interpretation of visual information, encoded in nodes of GP trees. The paper demonstrates the performance of the method on a specific visual task of acquiring the concept of a triangle from examples given in a form of raw raster images.

@INPROCEEDINGS { Krawiec06,
    AUTHOR = { Krzysztof Krawiec },
    TITLE = { Genetic Programming for Primitive-based Acquisition of Visual Concepts },
    BOOKTITLE = { Evolutionary Computation and Global Optimization 2006 Evolutionary Computation and Global Optimization 2006, Murzasichle, Poland, May 31 - June 2, 2006. Proceedings },
    YEAR = { 2006 },
    EDITOR = { Jaroslaw Arabas },
    VOLUME = { 156 },
    SERIES = { Prace Naukowe Politechniki Warszawskiej, Elektronika },
    PAGES = { 211 - 222 },
    ADDRESS = { Warszawa },
    PUBLISHER = { Oficyna Wydawnicza Politechniki Warszawskiej },
    ABSTRACT = { We describe a novel method for acquisition of higher-level visual concepts using GP-based learners that process attributed visual primitives derived from raw raster images. The approach uses an original evaluation scheme: individuals-learners are rewarded for being able to restore the essential features (here: shape) of the visual stimulus. The approach is general and does not require any a priori knowledge about the particular application or target concept to be learned; the only prerequisite is universal knowledge related to interpretation of visual information, encoded in nodes of GP trees. The paper demonstrates the performance of the method on a specific visual task of acquiring the concept of a triangle from examples given in a form of raw raster images. },
    OWNER = { krawiec },
    TIMESTAMP = { 2006.10.06 },
    URL = { http://www.cs.put.poznan.pl/kkrawiec/pubs/2006KAEiOG.pdf },
}


Powered by PmWiki