Title :
Unconstrained offline handwriting recognition using connectionist character N-grams
Author :
Zamora-Martínez, F. ; Castro-Bleda, M.J. ; España-Boquera, S. ; Gorbe-Moya, J.
Author_Institution :
Dept. de Cienc. Fisicas, Mat. y de la Comput., Univ. CEU-Cardenal Herrera, Valencia, Spain
Abstract :
This work presents an unconstrained offline hand-written line recognition system based on hybrid HMM (Hidden Markov Model)/ANN (Artificial Neural Network) models. The particularity of the system lies in the use of an ensemble of connectionist/statistical character n-gram language models. These language models are trained with a text corpus at character level; therefore, no explicit lexicon is used during recognition. The recognizer is thus able to output words which do not belong to that corpus. The proposed system favorably behaves compared to using a standard character n-gram on the IAM database lines corpus and achieves error rates comparable to state-of-the-art lexicon-driven alternatives.
Keywords :
Markov processes; database management systems; handwritten character recognition; neural nets; ANN; HMM; IAM database; artificial neural network; character level; connectionist character n-grams; hidden Markov model; lexicon-driven alternatives; unconstrained offline handwriting recognition; Artificial neural networks; Computational modeling; Databases; Feature extraction; Hidden Markov models; Mathematical model; Training;
Conference_Titel :
Neural Networks (IJCNN), The 2010 International Joint Conference on
Conference_Location :
Barcelona
Print_ISBN :
978-1-4244-6916-1
DOI :
10.1109/IJCNN.2010.5596327