TY - GEN
T1 - Automatic generation of personal Chinese handwriting by capturing the characteristics of personal handwriting
AU - Xu, Songhua
AU - Jin, Tao
AU - Jiang, Hao
AU - Lau, Francis C.M.
PY - 2009
Y1 - 2009
N2 - Personal handwritings can add colors to human communication. Handwriting, however, takes more time and is less favored than typing in the digital age. In this paper we propose an intelligent algorithm which can generate imitations of Chinese handwriting by a person requiring only a very small set of training characters written by the person. Our method first decomposes the sample Chinese handwriting characters into a hierarchy of reusable components, called character components. During handwriting generation, the algorithm tries and compares different possible ways to compose the target character. The likeliness of a given personal handwriting generation result is evaluated according to the captured characteristics of the person's handwriting. We then find among all the candidate generation results an optimal one which can maximize a likeliness estimation. Experiment results show that our algorithm works reasonably well in the majority of the cases and sometimes remarkably well, which was verified through comparison with the groundtruth data and by a small scale user survey.
AB - Personal handwritings can add colors to human communication. Handwriting, however, takes more time and is less favored than typing in the digital age. In this paper we propose an intelligent algorithm which can generate imitations of Chinese handwriting by a person requiring only a very small set of training characters written by the person. Our method first decomposes the sample Chinese handwriting characters into a hierarchy of reusable components, called character components. During handwriting generation, the algorithm tries and compares different possible ways to compose the target character. The likeliness of a given personal handwriting generation result is evaluated according to the captured characteristics of the person's handwriting. We then find among all the candidate generation results an optimal one which can maximize a likeliness estimation. Experiment results show that our algorithm works reasonably well in the majority of the cases and sometimes remarkably well, which was verified through comparison with the groundtruth data and by a small scale user survey.
UR - http://www.scopus.com/inward/record.url?scp=74949110933&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=74949110933&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:74949110933
SN - 9781577354239
T3 - Proceedings of the 21st Innovative Applications of Artificial Intelligence Conference, IAAI-09
SP - 191
EP - 196
BT - Proceedings of the 21st Innovative Applications of Artificial Intelligence Conference, IAAI-09
T2 - 21st Innovative Applications of Artificial Intelligence Conference, IAAI-09
Y2 - 14 July 2009 through 16 July 2009
ER -