Sciweavers

6291 search results - page 427 / 1259
» Components Are from Mars
Sort
View
ICMCS
2005
IEEE
185views Multimedia» more  ICMCS 2005»
16 years 13 days ago
Automatic Object Trajectory-Based Motion Recognition Using Gaussian Mixture Models
In this paper, we propose a novel technique for modelbased recognition of complex object motion trajectories using Gaussian Mixture Models (GMM). We build our models on Principal ...
Faisal I. Bashir, Ashfaq A. Khokhar, Dan Schonfeld
PREMI
2005
Springer
16 years 9 days ago
Illumination Invariant Face Alignment Using Multi-band Active Appearance Model
Abstract. In this study, we present a new multi-band image representation for improving AAM segmentation accuracy for illumination invariant face alignment. AAM is known to be very...
Fatih Kahraman, Muhittin Gökmen
157
Voted
ICDAR
2003
IEEE
16 years 3 days 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
AIIA
2003
Springer
16 years 1 days ago
Incremental Induction of Rules for Document Image Understanding
This paper aims at presenting the application of first-order logic machine learning techniques to two document domains in order to learn rules for recognizing the semantic role of...
Stefano Ferilli, Nicola Di Mauro, Teresa Maria Alt...
ICCSA
2003
Springer
16 years 1 days ago
Efficient Speaker Identification Based on Robust VQ-PCA
Abstract. In this paper, an efficient speaker identification based on robust vector quantization principal component analysis (VQ-PCA) is proposed to solve the problems from outlie...
Younjeong Lee, Joohun Lee, Ki Yong Lee