TY - GEN
T1 - Ensemble classifier with dividing training scheme for Chinese scene character recognition
AU - Jiang, Long
AU - Goto, Hideaki
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/7/2
Y1 - 2017/7/2
N2 - Scene character recognition problem has attracted a great attention in computer vision field. As one of the most widely used characters, Chinese characters are more complicated than European characters, especially when it comes to those characters appeared in various scene texts. The recognition of Chinese scene characters is still far from a satisfactory level owing to the lack of adequate training data and efficient learning methods. In this paper, we propose a new strategy to divide training data and combine multiple classifiers to get a better performance of Chinese scene character recognition. Besides, facing the problem of data shortage, we propose a scene character synthesis method to gain enough training data. By applying the proposed training strategy, the average recognition accuracies of Random Forest (RF) and Support Vector Machine (SVM) have been improved by nearly 22% and 14%, respectively.
AB - Scene character recognition problem has attracted a great attention in computer vision field. As one of the most widely used characters, Chinese characters are more complicated than European characters, especially when it comes to those characters appeared in various scene texts. The recognition of Chinese scene characters is still far from a satisfactory level owing to the lack of adequate training data and efficient learning methods. In this paper, we propose a new strategy to divide training data and combine multiple classifiers to get a better performance of Chinese scene character recognition. Besides, facing the problem of data shortage, we propose a scene character synthesis method to gain enough training data. By applying the proposed training strategy, the average recognition accuracies of Random Forest (RF) and Support Vector Machine (SVM) have been improved by nearly 22% and 14%, respectively.
KW - Chinese scene character
KW - character recognition
KW - dividing training
KW - ensemble voting classifier
KW - synthetic data
UR - http://www.scopus.com/inward/record.url?scp=85050029641&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85050029641&partnerID=8YFLogxK
U2 - 10.1109/IVCNZ.2017.8402476
DO - 10.1109/IVCNZ.2017.8402476
M3 - Conference contribution
AN - SCOPUS:85050029641
T3 - International Conference Image and Vision Computing New Zealand
SP - 1
EP - 5
BT - 2017 International Conference on Image and Vision Computing New Zealand, IVCNZ 2017
PB - IEEE Computer Society
T2 - 2017 International Conference on Image and Vision Computing New Zealand, IVCNZ 2017
Y2 - 4 December 2017 through 6 December 2017
ER -