TY - GEN
T1 - Novel character segmentation method for overlapped Chinese handwriting recognition based on LSTM neural networks
AU - Su, Tonghua
AU - Jia, Shukai
AU - Wang, Qiufeng
AU - Sun, Li
AU - Wang, Ruigang
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/1/1
Y1 - 2016/1/1
N2 - Overlapped handwriting recognition is widely used to input text in smart devices since it allows to write continuous characters on an size-restricted screens. How to segment the stroke sequences into characters is a crucial step before recognition. It is currently formulated as a two-class classification problem merely evaluating on the relationships between a pair of adjacent strokes. To facilitate the long contextual dependency, the paper novelly presents the problem as a sequential classification problem. Firstly each adjacent stroke pair is expressed as a feature vector. Secondly a LSTM model is learned to encode the long contextual history information from massive data. Finally the model is propagated forward to predict the labels once new samples are fed. Experiments are conducted on a public online Chinese handwriting database. The results show that the proposed method outperforms the traditional ones with about 10 percent improvement in terms of both specificity and precision.
AB - Overlapped handwriting recognition is widely used to input text in smart devices since it allows to write continuous characters on an size-restricted screens. How to segment the stroke sequences into characters is a crucial step before recognition. It is currently formulated as a two-class classification problem merely evaluating on the relationships between a pair of adjacent strokes. To facilitate the long contextual dependency, the paper novelly presents the problem as a sequential classification problem. Firstly each adjacent stroke pair is expressed as a feature vector. Secondly a LSTM model is learned to encode the long contextual history information from massive data. Finally the model is propagated forward to predict the labels once new samples are fed. Experiments are conducted on a public online Chinese handwriting database. The results show that the proposed method outperforms the traditional ones with about 10 percent improvement in terms of both specificity and precision.
KW - Character segmentation
KW - LSTM network
KW - Overlapped handwriting
KW - Sequential classification
UR - http://www.scopus.com/inward/record.url?scp=85019151950&partnerID=8YFLogxK
U2 - 10.1109/ICPR.2016.7899790
DO - 10.1109/ICPR.2016.7899790
M3 - Conference Proceeding
AN - SCOPUS:85019151950
T3 - Proceedings - International Conference on Pattern Recognition
SP - 1141
EP - 1146
BT - 2016 23rd International Conference on Pattern Recognition, ICPR 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 23rd International Conference on Pattern Recognition, ICPR 2016
Y2 - 4 December 2016 through 8 December 2016
ER -