TY - GEN
T1 - Recent approaches in handwriting recognition with markovian modelling and recurrent neural networks
AU - Likforman-Sulem, Laurence
PY - 2014/3/28
Y1 - 2014/3/28
N2 - Handwriting recognition is challenging because of the inherent variability of character shapes. Popular approaches for handwriting recognition are markovian and neuronal. Both approaches can take as input, sequences of frames obtained by sliding a window along a word or a text-line. We present markovian (Dynamic Bayesian Networks, Hidden Markov Models) and recurrent neural network-based approaches (RNNs) dedicated to character, word and text-line recognition. These approaches are applied to the recognition of both Latin and Arabic scripts.
AB - Handwriting recognition is challenging because of the inherent variability of character shapes. Popular approaches for handwriting recognition are markovian and neuronal. Both approaches can take as input, sequences of frames obtained by sliding a window along a word or a text-line. We present markovian (Dynamic Bayesian Networks, Hidden Markov Models) and recurrent neural network-based approaches (RNNs) dedicated to character, word and text-line recognition. These approaches are applied to the recognition of both Latin and Arabic scripts.
KW - BLSTMs
KW - Hidden Markov Models
KW - Recurrent neural networks
KW - Text-line recognition
KW - Word recognition
U2 - 10.1007/978-3-319-04129-2_26
DO - 10.1007/978-3-319-04129-2_26
M3 - Conference contribution
AN - SCOPUS:84897884993
SN - 9783319041285
T3 - Smart Innovation, Systems and Technologies
SP - 261
EP - 267
BT - Recent Advances of Neural Network Models and Applications - Proceedings of the 23rd Workshop of the Italian Neural Networks Society (SIREN)
T2 - 23rd Workshop of the Italian Neural Networks Society, WIRN 2013
Y2 - 23 May 2013 through 24 May 2013
ER -