A new multi‐stage classification scheme for recognition of postal road/street names

Abstract A new multi‐stage classification scheme is proposed to recognize road/street names from handwritten Chinese postal addresses. The first stage, namely pre‐classification, is carried out by a reliable fuzzy rule‐based approach to classify an input road/street name into a corresponding cluster. The second stage, namely fine classification, is used to recognize the road/street name within a cluster by a hidden Markov model‐based approach. Based on the demand for lower error rates and higher processing speed, some fast and effective approaches within the scheme are adopted to make the scheme feasible. Moreover, several experiments show that the scheme can be used to produce very encouraging results.

[1]  Jhing-Fa Wang,et al.  Recognition of handwritten Chinese postal address using neural networks , 1998, ISCAS '98. Proceedings of the 1998 IEEE International Symposium on Circuits and Systems (Cat. No.98CH36187).

[2]  Paul D. Gader,et al.  Handwritten Word Recognition Using Segmentation-Free Hidden Markov Modeling and Segmentation-Based Dynamic Programming Techniques , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Dorothea Blostein,et al.  Handbook of Character Recognition and Document Image Analysis , 1997 .

[4]  Ching Y. Suen,et al.  HMM word recognition engine , 1997, Proceedings of the Fourth International Conference on Document Analysis and Recognition.

[5]  Julius T. Tou,et al.  Pattern Recognition Principles , 1974 .

[6]  Richard M. Schwartz,et al.  A Script-Independent Methodology For Optical Character Recognition , 1998, Pattern Recognit..

[7]  Chuen-Chien Lee,et al.  Fuzzy logic in control systems: fuzzy logic controller. II , 1990, IEEE Trans. Syst. Man Cybern..

[8]  Valluru Rao,et al.  C++ neural networks and fuzzy logic , 1993 .

[9]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[10]  Yoshiki Mizukami.  A handwritten Chinese character recognition system using hierarchical displacement extraction based on directional features , 1998, Pattern Recognit. Lett..

[11]  Hong Yan,et al.  Fuzzy Rule-based Systems , 1996 .

[12]  Lianwen Jin,et al.  Off-line Chinese handwriting recognition using multi-stage neural network architecture , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[13]  C C Lee,et al.  FUZZY LOGIC IN CONTROL SYSTEM FUZZY LOGIC CONTROLLER-PART II , 1990 .

[14]  Hsin-Chia Fu,et al.  Recognition of handwritten Chinese characters by multi-stage neural network classifiers , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[15]  Tetsushi Wakabayashi,et al.  Improvement of handwritten Japanese character recognition using weighted direction code histogram , 1997, Pattern Recognit..

[16]  Horst Bunke,et al.  Off-line cursive handwriting recognition using hidden markov models , 1995, Pattern Recognit..

[17]  Sankar K. Pal,et al.  Fuzzy models for pattern recognition : methods that search for structures in data , 1992 .