| M. Y. Chen, A. Kundu, and J. Zhou. O#--line handwritten word recognition using a hidden markov model type stochastic network. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16(5):481--496, 1994. |
.... of the stroke edges in core, ascenders and descenders regions are used in [24] 25] the distances of the foreground background transitions from the median line of the core region are proposed in [26] 27] the percentages of foreground pixels in core, ascenders and descenders region are applied in [28][29] To have an overall description of the shape, features like curvature [24] 25] center of mass [29] histogram of the strokes directions [14] 29] 30] are used. In several works, the small strokes are considered deformations of the elements of a basic set of strokes and the deformation ....
....performance has been achieved in [29] with a system based on HMMs. The result is achieved IDIAP RR 00 43 13 Authors DB size performance Chen et al. 46] 996 90.8 Gader et al. 26] 1000 85.8 Kim et al. 13] 3000 88.2 Mohamed et al. 27] 10567 89.3 Kundu et al. 79] 3000 88.3 Chen et al. [28] 1583 72.3 El Yacoubi et al. 12] 19447 96.3 Table 2: Performances in postal applications. For each work cited in the rst column, the database size and the performance (in terms of percentage of words correctly recognized) for a 100 word lexicon is reported. The double horizontal line ....
[Article contains additional citation context not shown here]
M. Chen, A. Kundu, J. Zhou, O-line handwritten word recognition using a Hidden Markov Model type stochastic network, IEEE Transactions on Pattern Analysis and Machine Intelligence 16 (5) (1994) 481-496.
....no control over the dynamics of the system, and the stochastic behavior is completely speci ed by the states, transitions and probabilities. They are widely used in a variety of areas such as natural language understanding [Cha93] speech recognition [Rab89, RJ93] 2 handwritten text analysis [CKZ94, BG95] and protein and DNA representation [Chu89, BCH 93, KBM 94] Hidden Markov models can be extended to model decision processes in which control is exercised, by introducing actions into the model. The extended models are known as partially observable Markov decision process (pomdp) ....
M.-Y. Chen, A. Kundu and J. Zhou, O-Line Handwritten Word Recognition Using a Hidden Markov Model Type Stochastic Network, IEEE Transactions on Pattern Analysis and Machine Intelligence, 16 (5), pp. 481-496, 1994.
No context found.
M. Y. Chen, A. Kundu, and J. Zhou. O#--line handwritten word recognition using a hidden markov model type stochastic network. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16(5):481--496, 1994.
No context found.
M. Y. Chen, A. Kundu, and J. Zhou. O-line handwritten word recognition using a hidden Markov model type stochastic network. IEEE Trans. on Pattern Analysis and Machine Intelligence, 16(5):481496, 1994.
No context found.
M. Y. Chen, A. Kundu, and J. Zhou. O#--line handwritten word recognition using a hidden markov model type stochastic network. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16(5):481--496, 1994.
No context found.
M. Y. Chen, A. Kundu, and J. Zhou. O-line handwritten word recognition using a hidden Markov model type stochastic network. IEEE Trans. on Pattern Analysis and Machine Intelligence, 16(5):481496, 1994.
No context found.
M. Chen, A. Kundu, J. Zhou, O-line handwritten word recognition using a Hidden Markov Model type stochastic network, IEEE Transactions on Pattern Analysis and Machine Intelligence 16 (5) (1994) 481-496.
No context found.
M.Y. Chen, A. Kundu, and J. Zhou. O-line handwritten word recognition using a Hidden Markov Model type stochastic network. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16(5):481-496, May 1994.
No context found.
M. Y. Chen, A. Kundu and J. Zhou. O##Line Handwritten Word Recognition Using a Hidden Markov Model Type Stochastic Network. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16 #5#: 481#496, May 1994.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC