Learning and Recognition of Hand-drawn Shapes using Generative Genetic Programming

by Wojciech Jaśkowski, Krzysztof Krawiec, Bartosz Wieloch
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 visual primitives that represent local salient features derived from a raw input raster image. In response to that input, the learner produces partial reproduction of the input image, and is evaluated 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.
Reference:
Learning and Recognition of Hand-drawn Shapes using Generative Genetic Programming (Wojciech Jaśkowski, Krzysztof Krawiec, Bartosz Wieloch), In Applications of Evolutionary Computing, EvoWorkshops 2007: EvoCOMNET, EvoFIN, EvoIASP, EvoInteraction, EvoMUSART, EvoSTOC, EvoTransLog (Mario Giacobini, ed.), Springer Verlag, volume 4448, 2007. (EvoWorkshops2007)
Bibtex Entry:
@InProceedings{Jaskowski2007learning,
  Title                    = {Learning and Recognition of Hand-drawn Shapes using Generative Genetic Programming},
  Author                   = {Wojciech Jaśkowski and Krzysztof Krawiec and Bartosz Wieloch},
  Booktitle                = {Applications of Evolutionary Computing, EvoWorkshops 2007: {EvoCOMNET}, {EvoFIN}, {EvoIASP}, {EvoInteraction}, {EvoMUSART}, {EvoSTOC}, {EvoTransLog}},
  Year                     = {2007},

  Address                  = {Valencia, Spain},
  Editor                   = {Mario Giacobini},
  Month                    = {apr},
  Note                     = {EvoWorkshops2007},
  Pages                    = {281--290},
  Publisher                = {Springer Verlag},
  Series                   = {LNCS},
  Volume                   = {4448},

  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 visual primitives that represent local salient features derived from a raw input raster image. In response to that input, the learner produces partial reproduction of the input image, and is evaluated 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.},
  Doi                      = {10.1007/978-3-540-71805-5_31},
  File                     = {Jaskowski07learning.pdf:\jaskowski07learning.pdf:PDF},
  Homepage-url             = {http://www.cs.put.poznan.pl/wjaskowski},
  Keywords                 = {evolutionary computation, genetic programming, pattern recognition, visual learning,},
  Url                      = {http://dx.doi.org/10.1007/978-3-540-71805-5_31}
}

This entry was posted by . Bookmark the permalink.