Generation of Handwritten Characters with Bayesian network based On-line Handwriting Recognizers

In this paper, we propose a new character generation method from on-line handwriting recognizers based on Bayesian networks. On-line handwriting recognizers are trained with handwriting samples from many writers. Then, character shapes are generated from given texts by searching the most probable input point sequences. Since Bayesian network based classifiers have large number of parameters for modeling components and their relationships, they generate more natural character shapes than various kinds of hidden Markov models.

• Type: Conference
• Year: 2003
• Where: ICDAR
• Authors: Hyun-Il Choi, Sung-Jung Cho, Jin Hyung Kim
• Keywords: Bayesian Network, Character Shapes, Document Analysis, ICDAR 2003, On-line Handwriting Recognizers