Genetic engineering of handwriting representations
Tóm tắt
This paper presents experiments with genetically engineered feature sets for recognition of online handwritten characters. These representations stem from a nondescript decomposition of the character frame into a set of rectangular regions, possibly overlapping each represented by a vector of 7 fuzzy variables. Efficient new feature sets are automatically discovered using genetic programming techniques. Recognition experiments conducted on isolated digits of the Unipen database yield improvements of more than 3% over a previously, manually designed representation where region positions and sizes were fixed.
Từ khóa
#Genetic engineering #Genetic programming #Handwriting recognition #Fuzzy sets #Spatial databases #Topology #Humans #Data mining #Clocks #ConferencesTài liệu tham khảo
10.1109/ICPR.1994.576870
gagne, 2002, Open beagle: A new c++ evolutionary computation framework, Late Breaking Papers Genetic Evol Computat Conf
10.1002/047134608X.W5508
banzhaf, 1998, Genetic Programming An Introduction On the Automatic Evolution of Computer Programs and its Applications
koza, 0, Genetic Programming III Darwinian Invention and Problem Solving
koza, 1992, Genetic Programming On the Programming of Computers by Means of Natural Selection
holland, 1975, Adaptation in Natural and Artificial Systems
hebert, 1998, A new fuzzy geometric representation for on-line isolated character recognition, Proc of the 14th International Conference on Pattern Recognition, 33
10.1109/ICDAR.2001.953836
10.1162/evco.1995.3.2.199
teredesai, 2001, Active handwritten character recognition using genetic programming, Proceedings of the European Conference on Genetic Programming (EuroGP), 10.1007/3-540-45355-5_30