A hybrid large vocabulary handwritten word recognition system using neural networks with hidden Markov models
Tóm tắt
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 in the 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.
Từ khóa
#Vocabulary #Handwriting recognition #Neural networks #Hidden Markov models #Pattern recognition #Character recognition #Character generation #Image segmentation #Viterbi algorithm #ReconnaissanceTài liệu tham khảo
cho, 2000, Verification of graphemes using neural networks in an hmm-based on-line korean handwriting recognition system, Proc Int'l Workshop Frontiers in Handwriting Recognition, 219
10.1109/83.477074
wang, 2000, Support vector machines for the classification of western handwritten capitals, Proc Int'l Workshop Frontiers in Handwriting Recognition, 167
10.1016/S0167-8655(01)00008-3
koerich, 2000, A syntax-directed level building algorithm for large vocabulary handwritten word recognition, Proc 6th International Workshop on Document Analysis Systems, 255
10.1109/ICASSP.2002.5745418
10.1016/S0167-8655(98)00039-7
10.1109/34.784288
senior, 1994, Off-Line Cursive Handwriting Recognition Using Recurrent Neural Networks
10.1162/neco.1991.3.4.461
yaeger, 1997, Effective training of a neural network character classifier for word recognition, Proc Advances in Neural Information Processing Systems, 807
10.1109/89.260358