A learning algorithm for structured character pattern representation used in online recognition of handwritten Japanese characters
Tóm tắt
This paper describes a prototype learning algorithm for structured character pattern representation with common sub-patterns shared among multiple character templates for online recognition of handwritten Japanese characters. Although prototype learning algorithms have been proved useful for an unstructured set of features, they have not been presented for structured or hierarchical pattern representation. In this paper, we present cost-free parallel translation without rotation of sub-patterns that negates their location distributions and normalization that reflects feature distributions in raw patterns to the sub-pattern prototypes, and then show that a prototype learning algorithm can be applied to the structured character pattern representation with significant effect.
Từ khóa
#Character recognition #Pattern recognition #Dictionaries #Handwriting recognition #Prototypes #Programmable logic arrays #Shape #Robustness #Statistical learning #Statistical distributionsTài liệu tham khảo
10.1109/78.175747
10.1109/72.80344
10.1109/ICDAR.1997.619874
10.1109/IJCNN.1990.137622
10.1007/3-540-61577-6_19
nakagawa, 1996, Robust and highly customizable recognition of on-line handwritten Japanese characters, Proc 13th ICPR, 3, 269
10.1016/S0031-3203(00)00018-2
sato, 1998, A formulation of learning vector quantization using a new misclassification measure, Proc 14th ICPR Brisbane, 322
nakagawa, 1994, A Linear-time elastic matching for stroke number free recognition of on-line handwritten characters, Proc 4th IWFHR
akiyama, 2000, A Method of Generating High Quality Online Character Recognition Dictionary Based on Training Samples, 31