TY - GEN
T1 - Improving accuracy of printed character recognition using hexagonal zoning of directional histogram feature
AU - Ohyama, Wataru
AU - Yamamoto, Akihito
AU - Wakabayashi, Tetsushi
AU - Kimura, Fumitaka
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014/12/4
Y1 - 2014/12/4
N2 - Accurate character recognition is still very important for camera based printed document analysis. Due to its inherent conceptual and technical simplicity, conventional recognition strategies relied on features extracted using square block zoning of a character image. In this paper, we propose an isotropic feature extraction method using regular hexagonal zoning and confirm its effectiveness by printed character recognition experiments. A 2% improvement in accuracy was achieved in experiments using gradient features. And the effectiveness of hexagonal zoning for recognition of high stroke count characters and low-resolution characters is confirmed by the experiments.
AB - Accurate character recognition is still very important for camera based printed document analysis. Due to its inherent conceptual and technical simplicity, conventional recognition strategies relied on features extracted using square block zoning of a character image. In this paper, we propose an isotropic feature extraction method using regular hexagonal zoning and confirm its effectiveness by printed character recognition experiments. A 2% improvement in accuracy was achieved in experiments using gradient features. And the effectiveness of hexagonal zoning for recognition of high stroke count characters and low-resolution characters is confirmed by the experiments.
UR - http://www.scopus.com/inward/record.url?scp=84919897451&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84919897451&partnerID=8YFLogxK
U2 - 10.1109/ICPR.2014.466
DO - 10.1109/ICPR.2014.466
M3 - Conference contribution
AN - SCOPUS:84919897451
T3 - Proceedings - International Conference on Pattern Recognition
SP - 2697
EP - 2702
BT - Proceedings - International Conference on Pattern Recognition
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 22nd International Conference on Pattern Recognition, ICPR 2014
Y2 - 24 August 2014 through 28 August 2014
ER -