TY - GEN
T1 - Highly-accurate fast candidate reduction method for Japanese/Chinese character recognition
AU - Odate, Ryosuke
AU - Goto, Hideaki
PY - 2016/8/3
Y1 - 2016/8/3
N2 - A high-speed pattern matching algorithm is required for developing real-time character recognition applications especially for mobile devices with limited computational performances. Multilingual scene text recognition has recently become more important for mobile and wearable devices. Since Japanese and Chinese have thousands of characters, not only the accuracy but also the speed of classifiers are crucial. We formalized the candidate reduction technique for the Nearest Neighbor (NN) search with high-dimensional feature vectors, and proposed a tree-based clustering method to realize a fast handwritten character recognition. It works fine with ETL9B dataset consisting of Japanese handwritten characters and HCL2000 Chinese handwritten character dataset. In this paper, we propose an improved candidate reduction method based on our former one. The experimental results show that our method is 60.48% faster and more accurate than the former method.
AB - A high-speed pattern matching algorithm is required for developing real-time character recognition applications especially for mobile devices with limited computational performances. Multilingual scene text recognition has recently become more important for mobile and wearable devices. Since Japanese and Chinese have thousands of characters, not only the accuracy but also the speed of classifiers are crucial. We formalized the candidate reduction technique for the Nearest Neighbor (NN) search with high-dimensional feature vectors, and proposed a tree-based clustering method to realize a fast handwritten character recognition. It works fine with ETL9B dataset consisting of Japanese handwritten characters and HCL2000 Chinese handwritten character dataset. In this paper, we propose an improved candidate reduction method based on our former one. The experimental results show that our method is 60.48% faster and more accurate than the former method.
KW - Approximate Nearest Neighbor (ANN) search
KW - Fast Nearest Neighbor search
KW - Linear Discriminant Analysis (LDA)
KW - Multilingual OCR
KW - Real-time character recognition
UR - http://www.scopus.com/inward/record.url?scp=85006756986&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85006756986&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2016.7532887
DO - 10.1109/ICIP.2016.7532887
M3 - Conference contribution
AN - SCOPUS:85006756986
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 2886
EP - 2890
BT - 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings
PB - IEEE Computer Society
T2 - 23rd IEEE International Conference on Image Processing, ICIP 2016
Y2 - 25 September 2016 through 28 September 2016
ER -