A 2-D HMM method for offline handwritten character recognition
Hidden Markov models
A System for the Automated Reading of Check Amounts - Some Key Ideas
DAS '98 Selected Papers from the Third IAPR Workshop on Document Analysis Systems: Theory and Practice
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Amount Translation and Error Localization in Check Processing Using Syntax-Directed Translation
ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 2 - Volume 2
Human reading based strategies for off-line Arabic word recognition
SACH'06 Proceedings of the 2006 conference on Arabic and Chinese handwriting recognition
| Hi-index | 0.00 |
Hidden Markov Models (HMMs) are fre-quently used in off-line cursive script recognition. In most cases the script is processed strictly from left to right, yielding a sequence of feature vectors fed into the HMM recognizer. In order to achieve good recognition results, more or less complex normalization has to be performed on the script beforehand to reduce the effects of writer variability. Taking the example of German literal amounts, especially ruler-line estimation and height normalization becomes a difficult task due to the often extremely long words. In many cases the assump-tion of straight ruler lines does not hold. Thus it would be advantageous to integrate normalization into the rec-ognition process. We present two approaches using regular one-dimensional HMMs in comparison to Pseudo two-dimensional HMMs (P2DHMM). Preprocessing is basically identical for both approaches. In the case of P2DHMMs, however, we use a much simpler ruler line estimation scheme. Under otherwise similar conditions, the P2DHMMs have proved to be slightly superior to the regular HMMs in first experiments. The performance could still be enhanced by combining the results from both recognizers.