Sciweavers

6553 search results - page 381 / 1311
» Face modeling for recognition
Sort
View
ICPR
2004
IEEE
16 years 8 months ago
Local Context in Non-Linear Deformation Models for Handwritten Character Recognition
We evaluate different two-dimensional non-linear deformation models for handwritten character recognition. Starting from a true two-dimensional model, we derive pseudo-two-dimensi...
Daniel Keysers, Christian Gollan, Hermann Ney
NAACL
2007
15 years 8 months ago
Joint Versus Independent Phonological Feature Models within CRF Phone Recognition
We compare the effect of joint modeling of phonological features to independent feature detectors in a Conditional Random Fields framework. Joint modeling of features is achieved ...
Ilana Bromberg, Jeremy Morris, Eric Fosler-Lussier
FGR
2006
IEEE
148views Biometrics» more  FGR 2006»
16 years 27 days ago
Gait Tracking and Recognition Using Person-Dependent Dynamic Shape Model
Characteristics of the 2D shape deformation in human motion contain rich information for human identification and pose estimation. In this paper, we introduce a framework for sim...
Chan-Su Lee, Ahmed M. Elgammal
MIR
2006
ACM
220views Multimedia» more  MIR 2006»
16 years 24 days ago
Robust scene recognition using language models for scene contexts
We propose a robust scene recognition framework using scene context information for multimedia contents. Multimedia contents consist of scene sequences that are more likely to hap...
Ryoichi Ando, Koichi Shinoda, Sadaoki Furui, Takah...
ICPR
2006
IEEE
16 years 8 months ago
Pen-Coordinate Information Modeling by SCPR-based HMM for On-line Japanese Handwriting Recognition
This paper describes stochastic modeling of pencoordinate information in HMMs with structured character pattern representation (SCPR) for on-line Japanese handwriting recognition....
Akihito Kitadai, Gleidson Pegoretti da Silva, Junk...