Improving Offline Handwritten Text Recognition with Hybrid HMM/ANN Models

This paper proposes the use of hybrid Hidden Markov Model (HMM)/Artificial Neural Network (ANN) models for recognizing unconstrained offline handwritten texts. The structural part of the optical models has been modeled with Markov chains, and a Multilayer Perceptron is used to estimate the emission...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on pattern analysis and machine intelligence Ročník 33; číslo 4; s. 767 - 779
Hlavní autori:	España-Boquera, S, Castro-Bleda, M J, Gorbe-Moya, J, Zamora-Martinez, F
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Los Alamitos, CA IEEE 01.04.2011 IEEE Computer Society The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Algorithms Applied sciences Artificial intelligence Artificial neural networks Automatic Data Processing - methods Computer science; control theory; systems Connectionism. Neural networks Exact sciences and technology Handwriting Handwriting recognition Hidden Markov models HMM Humans hybrid HMM/ANN image normalization Image segmentation Learning theory Markov Chains Markov processes Mathematical models multilayer perceptron Multilayer perceptrons Neural networks offline handwriting Pattern Recognition, Automated - methods Pattern recognition. Digital image processing. Computational geometry Pixel Reading Recognition Reproducibility of Results Text recognition Texts On line Probabilistic approach Image processing image normalization neural networks HMM Text Markov model Pattern recognition Neural network Character recognition hybrid HMM/ANN Modeling Handwriting recognition Supervised learning Optical character recognition Database Hidden Markov model Multilayer perceptrons multilayer perceptron Hybrid model Feedforward Manuscript character offline handwriting
ISSN:	0162-8828, 1939-3539, 1939-3539
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Buďte prvý, kto okomentuje tento záznam!