Sciweavers

190 search results - page 19 / 38
» Markov constraints: steerable generation of Markov sequences
Sort
View
ICDAR
2003
IEEE
15 years 5 months ago
Generation of Handwritten Characters with Bayesian network based On-line Handwriting Recognizers
In this paper, we propose a new character generation method from on-line handwriting recognizers based on Bayesian networks. On-line handwriting recognizers are trained with handw...
Hyun-Il Choi, Sung-Jung Cho, Jin Hyung Kim
91
Voted
ICPR
2008
IEEE
16 years 1 months ago
Dual generative models for human motion estimation from an uncalibrated monocular camera
We propose a new approach to estimate gait kinematics from image sequences taken by a monocular uncalibrated camera. This approach involves two generative models for gait represen...
Guoliang Fan, Xin Zhang
87
Voted
ICPR
2008
IEEE
16 years 1 months ago
Automatic generation of HMM topology for sign language recognition
Sign language is used for communicating to people with hearing difficulties. Recogntion of a sign language image sequence is challenging because of the variety of hand shapes and ...
Tadashi Matsuo, Yoshiaki Shirai, Nobutaka Shimada
91
Voted
GCB
2000
Springer
75views Biometrics» more  GCB 2000»
15 years 4 months ago
Regexpcount, a Symbolic Package for Counting Problems on Regular Expressions and Words
In previous work [10], we considered algorithms related to the statistics of matches with words and regular expressions in texts generated by Bernoulli or Markov sources. In this w...
Pierre Nicodème
95
Voted
CSL
1999
Springer
15 years 2 days ago
A hidden Markov-model-based trainable speech synthesizer
This paper presents a new approach to speech synthesis in which a set of cross-word decision-tree state-clustered context-dependent hidden Markov models are used to define a set o...
R. E. Donovan, Philip C. Woodland