ICADL '02 Proceedings of the 5th International Conference on Asian Digital Libraries: Digital Libraries: People, Knowledge, and Technology
Recognition of Cursive Roman Handwriting - Past, Present and Future
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Off-line Character Recognition using On-line Character Writing Information
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Information Processing and Management: an International Journal - Special issue: An Asian digital libraries perspective
Maximization of Mutual Information for Offline Thai Handwriting Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Design, implementation, and evaluation of a methodology for automatic stemmer generation
Journal of the American Society for Information Science and Technology
Off-line cursive script recognition: current advances, comparisons and remaining problems
Artificial Intelligence Review
| Hi-index | 0.00 |
The purpose of our research is to improve the recognition rate of off-line character recognition systems using the HMM (Hidden Markov Model) without increasing a number of HMM parameters too much. Some 2-dimensional HMM character recognition systems have been proposed to increase representational power. However, since 2-D HMM has much more complex structure and thus requires much more parameters than 1-dimensional HMM, it becomes very hard to gather sufficient samples in order to guarantee the successful generalization. To overcome the problem, we propose a method for character recognition using 1-D HMMs in multiple directions with 2-dimensional feature extraction. To further improve the performance, bagging algorithm is also exploited. The voting by the bagging algorithm, which is reported effective in some neural-network and decision tree classifier systems, has never been used in HMM character recognition systems yet. In our experiment, the recognition rate is increased by about 1% with the multiple directional HMM character recognition system compared to the 1-D HMM character recognition system. The recognition rate is further increased by about 1% with the HMM character recognition system using bagging algorithm.