Text Recognition in Videos Using a Recurrent Connectionist Approach.

Khaoula Elagouni Christophe Garcia Franck Mamalet Pascale Sébillot

Published in: ICANN (2) (2012)

Keyphrases

text recognition
viterbi algorithm
optical character recognition
video sequences
video frames
hidden markov models
recurrent neural networks
dynamic scenes
feed forward
text regions
markov model
neural network
human activities
edge information
key frames
dynamic programming
image processing