A Hybrid Large Vocabulary Handwritten Word Recognition System Using Neural Networks with Hidden Markov Models

Authors:
Alessandro L. Koerich;Yann Leydier;Robert Sabourin;Ching Y. Suen
Affiliations:
-;-;-;-
Venue:
IWFHR '02 Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition (IWFHR'02)
Year:
2002

Citing 0
Cited 9

Recognition of Cursive Roman Handwriting - Past, Present and Future

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Parsing N-Best Lists of Handwritten Sentences

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Recognition and Verification of Unconstrained Handwritten Words

IEEE Transactions on Pattern Analysis and Machine Intelligence
Offline Grammar-Based Recognition of Handwritten Sentences

IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic fuzzy rule base generation for on-line handwritten alphanumeric character recognition

International Journal of Knowledge-based and Intelligent Engineering Systems - Selected papers from the KES2004 conference
Text search for medieval manuscript images

Pattern Recognition
Architecture of Multiple Algorithm Integration for Real-Time Image Understanding Application

AICI '09 Proceedings of the International Conference on Artificial Intelligence and Computational Intelligence
Offline handwritten Amharic word recognition

Pattern Recognition Letters
New segmentation algorithm for individual offline handwritten character segmentation

FSKD'05 Proceedings of the Second international conference on Fuzzy Systems and Knowledge Discovery - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present a hybrid recognition system that integrates hidden Markov models (HMM) with neural networks (NN) in a probabilistic framework. The input data is processed first by a lexicon-driven word recognizer based on HMMs to generate a list of the candidate N-best-scoring word hypotheses as well as the segmentation of such word hypotheses into characters. An NN classifier is used to generate a score for each segmented character and inthe end, the scores from the HMM and the NN classifiers are combined to optimize performance. Experimental results show that for an 80,000-word vocabulary, the hybrid HMM/NN system improves by about 10% the word recognition rate over the HMM system alone.