On the Dependence of Handwritten Word Recognizers on Lexicons
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Time-Length Constrained Level Building Algorithm for Large Vocabulary Handwritten Word Recognition
ICAPR '01 Proceedings of the Second International Conference on Advances in Pattern Recognition
Exploring similarity measures for biometric databases
AVBPA'05 Proceedings of the 5th international conference on Audio- and Video-Based Biometric Person Authentication
| Hi-index | 0.00 |
Two strategies can be considered in handwriting recognition: phrase or word approaches. In this paper we want to demonstrate the superiority of the phrase one, especially in city name recognition. The performances of an HMM-based off-line system using an analytic approach with explicit segmentation are evaluated on 2 databases: (i) city names in full and (ii) city names in single words. A difference between their performances is observed, principally caused by the dissimilarity of word lengths between the databases. After generating other data sets and lexicons, experiments were performed yielding results which lead us to conclude that word length in the data set as well as in lexicons, significantly influences recognition performance, and also that is preferable to perform city name recognition based on phrase approach than word recognition.