Improvement of matching and evaluation in handwritten numeral recognition using flexible standard patterns

The purpose of this study is to develop a flexible matching method for recognizing handwritten numerals based on the statistics of shapes and structures learned from learning samples. In the recognition method we reported before, there were problems in matching of the feature points and evaluation of matching. To solve them, we propose a new matching method supplementing contour orientations with convex/concave information and a new evaluation method considering the structure of strokes. With these improvements the recognition rate rose to 96.0% from the earlier figure 91.9%. We also made a recognition experiment on samples from the ETL-1 database and obtained the recognition rate 95.2%.

[1]  I. Yamashita,et al.  State of the art of handwritten numeral recognition in Japan-The results of the first IPTP character recognition competition , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).

[2]  Geoffrey E. Hinton,et al.  Using Generative Models for Handwritten Digit Recognition , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Eric Lecolinet,et al.  A Survey of Methods and Strategies in Character Segmentation , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Yves Lecourtier,et al.  A structural/statistical feature based vector for handwritten character recognition , 1998, Pattern Recognit. Lett..

[5]  Hirobumi Nishida,et al.  Automatic Construction of Structural Models Incorporating Discontinuous Transformations , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Proceedings Seventh International Conference on Document Analysis and Recognition , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[7]  Hong Yan,et al.  Structural primitive extraction and coding for handwritten numeral recognition , 1998, Pattern Recognit..

[8]  Anil K. Jain,et al.  Representation and Recognition of Handwritten Digits Using Deformable Templates , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Theodosios Pavlidis,et al.  A Shape Analysis Model with Applications to a Character Recognition System , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  K. Nakamura,et al.  Handwritten numeral recognition using flexible matching based on learning of stroke statistics , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[11]  Seiichi Uchida,et al.  A monotonic and continuous two-dimensional warping based on dynamic programming , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[12]  Masaki Nakagawa,et al.  A recognition based on a dynamic model , 1998, Pattern Recognit..

[13]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[14]  M. Nakagawa,et al.  The behavior of dynamic relaxation in an elastic stroke model for character recognition , 1997, Proceedings of the Fourth International Conference on Document Analysis and Recognition.

[15]  Seiichi Uchida,et al.  An Approximation Algorithm for Two-Dimensional Warping , 2000 .

[16]  RODNEY G. WEBSTER,et al.  AN INTERFACE-ORIENTED APPROACH TO CHARACTER RECOGNITION BASED ON A DYNAMIC MODEL , 2003 .