An estimate of an upper bound for the entropy of English
Computational Linguistics
Large Vocabulary Recognition of On-Line Handwritten Cursive Words
IEEE Transactions on Pattern Analysis and Machine Intelligence
A technique for computer detection and correction of spelling errors
Communications of the ACM
The Role of Holistic Paradigms in Handwritten Word Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Perceptual Model of Handwriting Drawing Application to the Handwriting Segmentation Problem
ICDAR '97 Proceedings of the 4th International Conference on Document Analysis and Recognition
Integration of an On-Line Handwriting Recognition System in a Smart Phone Device
ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3
Design of a linguistic postprocessor using variable memory length Markov models
ICDAR '95 Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 1) - Volume 1
Design and integration of a handwritten character recognition system into mobile phones
UbiMob '04 Proceedings of the 1st French-speaking conference on Mobility and ubiquity computing
Recognition and Verification of Unconstrained Handwritten Words
IEEE Transactions on Pattern Analysis and Machine Intelligence
Statistical Language Models for On-line Handwritten Sentence Recognition
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Lexicon reduction using dots for off-line Farsi/Arabic handwritten word recognition
Pattern Recognition Letters
Effect of delayed strokes on the recognition of online Farsi handwriting
Pattern Recognition Letters
| Hi-index | 0.00 |
This paper presents a lexical post-processing optimizationfor handwritten word recognition. The aim of thiswork is to explore the combination of different lexical post-processingapproaches in order to optimize the recognitionrate, the recognition time and memory requirements. Thepresent method focuses on the following tasks: a lexiconorganization with word filtering, based on holistic word featuresto deal with large vocabulary (creation of static sublexiconcompressed in a trie structure); a dedicated stringmatching algorithm for on-line handwriting (to compensatethe recognition and the segmentation errors); and a specificexploration strategy of the results provided by the analyticalword recognition process.Experimental results are reported using several lexiconsizes (about 1,000; 7,000 and 25,000 entries) to evaluate differentoptimization strategies according to the recognitionrate, computational cost and memory requirements.