TY - GEN
T1 - An implementation of postal numerals segmentation and recognition system for Chinese business letters
AU - Lu, Yue
AU - Shi, Pengfei
AU - Wu, Jianzhong
AU - Rui, Jianming
N1 - Publisher Copyright:
© 1999 IEEE.
PY - 1999
Y1 - 1999
N2 - In this paper, a practical postal numeral segmentation and recognition system for Chinese business letters is presented. Line information for the address blocks is gained from the envelope image by projection, then the sub-image of the postal numerals is segmented. The numerals are recognized by three independent classifiers, and their results are combined to form final results. An improved voting principle based on a priori knowledge of each classifier is utilized to combine multiple classifiers in order to achieve perfect performance for high recognition rate and low error rate. The recognition ability of each classifier, acting with the voting principle, is obtained by statistics for a large set of samples. Different thresholds gained by training are employed for different classes, which can yield better results. A parallel structure hardware is designed to implement a real-time image processing system. The performance of the system is shown to be satisfactory, sufficient for the requirements of practical use.
AB - In this paper, a practical postal numeral segmentation and recognition system for Chinese business letters is presented. Line information for the address blocks is gained from the envelope image by projection, then the sub-image of the postal numerals is segmented. The numerals are recognized by three independent classifiers, and their results are combined to form final results. An improved voting principle based on a priori knowledge of each classifier is utilized to combine multiple classifiers in order to achieve perfect performance for high recognition rate and low error rate. The recognition ability of each classifier, acting with the voting principle, is obtained by statistics for a large set of samples. Different thresholds gained by training are employed for different classes, which can yield better results. A parallel structure hardware is designed to implement a real-time image processing system. The performance of the system is shown to be satisfactory, sufficient for the requirements of practical use.
KW - Chinese business letter
KW - Combination of multiple classifiers
KW - Numeral recognition
KW - Postal numeral
KW - Real-time system
KW - Segmentation
KW - Voting principle
UR - https://www.scopus.com/pages/publications/33751572122
U2 - 10.1109/ICDAR.1999.791890
DO - 10.1109/ICDAR.1999.791890
M3 - 会议稿件
AN - SCOPUS:33751572122
T3 - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
SP - 729
EP - 732
BT - Proceedings of the 5th International Conference on Document Analysis and Recognition, ICDAR 1999
PB - IEEE Computer Society
T2 - 5th International Conference on Document Analysis and Recognition, ICDAR 1999
Y2 - 20 September 1999 through 22 September 1999
ER -