Active shape models—their training and application
Computer Vision and Image Understanding
A Survey of Methods and Strategies in Character Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Using Generative Models for Handwritten Digit Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic Construction of Structural Models Incorporating Discontinuous Transformations
IEEE Transactions on Pattern Analysis and Machine Intelligence
Representation and Recognition of Handwritten Digits Using Deformable Templates
IEEE Transactions on Pattern Analysis and Machine Intelligence
A structural/statistical feature based vector for handwritten character recognition
Pattern Recognition Letters
A Shape Analysis Model with Applications to a Character Recognition System
IEEE Transactions on Pattern Analysis and Machine Intelligence
The Behavior of Dynamic Relaxation in an Elastic Stroke Model for Character Recognition
ICDAR '97 Proceedings of the 4th International Conference on Document Analysis and Recognition
A Monotonic and Continuous Two-Dimensional Warping Based on Dynamic Programming
ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 1 - Volume 1
Handwritten Numeral Recognition Using Flexible Matching Based on Learning of Stroke Statistics
ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
Hi-index | 0.00 |
The purpose of this study is to develop a flexible matchingmethod for recognizing handwritten numerals based onthe statistics of shapes and structures learned from learningsamples. In the recognition method we reported before,there were problems in matching of the feature points andevaluation of matching. To solve them, we propose a newmatching method supplementing contour orientations withconvex/concave information and a new evaluation methodconsidering the structure of strokes.With these improvements the recognition rate rose to96.0% from the earlier figure 91.9%. We also made a recognitionexperiment on samples from the ETL-1 database andobtained the recognition rate 95.2%.