Krzysztof Krawiec


Home

Research:

edit SideBar

We describe a novel method of evolutionary visual learning that uses generative approach for assessing learner’s ability to recognize image contents. Each learner, implemented as a genetic programming individual, processes visualprimitivesthatrepresentlocalsalientfeatures derived from a raw input raster image. In response to that input, the learnerproducespartialreproductionoftheinputimage,andisevaluated according to the quality of that reproduction. We present the method in detail and verify it experimentally on the real-world task of recognition of hand-drawn shapes.

@INPROCEEDINGS { jaskowski07learning,
    AUTHOR = { Wojciech Jaśkowski and Krzysztof Krawiec and Bartosz Wieloch },
    TITLE = { Learning and Recognition of Hand-Drawn Shapes Using Generative Genetic Programming },
    BOOKTITLE = { EvoWorkshops 2007 },
    YEAR = { 2007 },
    EDITOR = { M. Giacobini et al. },
    VOLUME = { 4448 },
    SERIES = { LNCS },
    PAGES = { 281-290 },
    ADDRESS = { Berlin Heidelberg },
    PUBLISHER = { Springer-Verlag },
    ABSTRACT = { We describe a novel method of evolutionary visual learning that uses generative approach for assessing learner’s ability to recognize image contents. Each learner, implemented as a genetic programming individual, processes visualprimitivesthatrepresentlocalsalientfeatures derived from a raw input raster image. In response to that input, the learnerproducespartialreproductionoftheinputimage,andisevaluated according to the quality of that reproduction. We present the method in detail and verify it experimentally on the real-world task of recognition of hand-drawn shapes. },
    OWNER = { krawiec },
    TIMESTAMP = { 2007.02.19 },
}


Powered by PmWiki