TY - GEN
T1 - Weakly Supervised Learning for Over-Segmentation Based Handwritten Chinese Text Recognition
AU - Wang, Zhen Xing
AU - Wang, Qiu Feng
AU - Yin, Fei
AU - Liu, Cheng Lin
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/9
Y1 - 2020/9
N2 - In this paper, we proposed a weakly supervised learning method for string-level training of character classifier in over-segmentation based handwritten Chinese text recognition (HCTR). The over-segmentation based framework can easily integrate multiple context models and provide accurate character boundary and recognition confidence, but has not been implemented with string-level training for HCTR. We propose to optimize the character classifier by minimizing the marginal log-likelihood on a string-level annotated handwriting dataset, where the forward-backward algorithm is utilized in a segmentation-and-recognition lattice. Experimental results on the CASIA-HWDB and ICDAR-2013 competition datasets show that the proposed method improves the recognition performance significantly, which demonstrates its effectiveness.
AB - In this paper, we proposed a weakly supervised learning method for string-level training of character classifier in over-segmentation based handwritten Chinese text recognition (HCTR). The over-segmentation based framework can easily integrate multiple context models and provide accurate character boundary and recognition confidence, but has not been implemented with string-level training for HCTR. We propose to optimize the character classifier by minimizing the marginal log-likelihood on a string-level annotated handwriting dataset, where the forward-backward algorithm is utilized in a segmentation-and-recognition lattice. Experimental results on the CASIA-HWDB and ICDAR-2013 competition datasets show that the proposed method improves the recognition performance significantly, which demonstrates its effectiveness.
KW - character classifier
KW - handwritten Chinese text recognition
KW - oversegmentation
KW - string-level training
KW - weakly supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85097764754&partnerID=8YFLogxK
U2 - 10.1109/ICFHR2020.2020.00038
DO - 10.1109/ICFHR2020.2020.00038
M3 - Conference Proceeding
AN - SCOPUS:85097764754
T3 - Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR
SP - 157
EP - 162
BT - Proceedings - 2020 17th International Conference on Frontiers in Handwriting Recognition, ICFHR 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 17th International Conference on Frontiers in Handwriting Recognition, ICFHR 2020
Y2 - 7 September 2020 through 10 September 2020
ER -