TY - GEN
T1 - Synthetic Scene Character Generator and Multi-Scale Voting Classifier for Japanese Scene Character Recognition
AU - Horie, Fuma
AU - Goto, Hideaki
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/6/28
Y1 - 2018/6/28
N2 - Scene character recognition is challenging owing to various noise and distortions. In addition, Japanese character recognition requires a large number of training data since thousands of character classes exist in the language. Some researches proposed training data augmentation techniques using synthetic scene character data (SSD)to compensate for the shortage of training data. We proposed multi-scale scheme using multiple dataset consisting of SSD in our previous work to improve recognition accuracy. For further improvement of the scheme, we then proposed Random Filter as SSD generator. This paper enhances the effectiveness of the multi-scale scheme and Random Filter by using larger dataset, JPSC1400, which we have developed by collecting Japanese real scene characters. Experimental results show that the accuracy has been improved from 61.5% to 65.5 % by newly introduced an affine transformation to the SSD generation.
AB - Scene character recognition is challenging owing to various noise and distortions. In addition, Japanese character recognition requires a large number of training data since thousands of character classes exist in the language. Some researches proposed training data augmentation techniques using synthetic scene character data (SSD)to compensate for the shortage of training data. We proposed multi-scale scheme using multiple dataset consisting of SSD in our previous work to improve recognition accuracy. For further improvement of the scheme, we then proposed Random Filter as SSD generator. This paper enhances the effectiveness of the multi-scale scheme and Random Filter by using larger dataset, JPSC1400, which we have developed by collecting Japanese real scene characters. Experimental results show that the accuracy has been improved from 61.5% to 65.5 % by newly introduced an affine transformation to the SSD generation.
KW - Japanese scene character recognition
KW - character recognition
KW - ensemble voting classifier
KW - scene character dataset
KW - synthetic scene character data
UR - http://www.scopus.com/inward/record.url?scp=85062799325&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85062799325&partnerID=8YFLogxK
U2 - 10.1109/IVCNZ.2018.8634801
DO - 10.1109/IVCNZ.2018.8634801
M3 - Conference contribution
AN - SCOPUS:85062799325
T3 - International Conference Image and Vision Computing New Zealand
BT - 2018 International Conference on Image and Vision Computing New Zealand, IVCNZ 2018
PB - IEEE Computer Society
T2 - 2018 International Conference on Image and Vision Computing New Zealand, IVCNZ 2018
Y2 - 19 November 2018 through 21 November 2018
ER -