Image Recognition Based on Separable Lattice Trajectory 2-D HMMs
Summary :
In this paper, a novel statistical model based on 2-D HMMs for image recognition is proposed. Recently, separable lattice 2-D HMMs (SL2D-HMMs) were proposed to model invariance to size and location deformation. However, their modeling accuracy is still insufficient because of the following two assumptions, which are inherited from 1-D HMMs: i) the stationary statistics within each state and ii) the conditional independent assumption of state output probabilities. To overcome these shortcomings in 1-D HMMs, trajectory HMMs were proposed and successfully applied to speech recognition and speech synthesis. This paper derives 2-D trajectory HMMs by reformulating the likelihood of SL2D-HMMs through the imposition of explicit relationships between static and dynamic features. The proposed model can efficiently capture dependencies between adjacent observations without increasing the number of model parameters. The effectiveness of the proposed model was evaluated in face recognition experiments on the XM2VTS database.
- Publication
- IEICE TRANSACTIONS on Information Vol.E97-D No.7 pp.1842-1854
- Publication Date
- 2014/07/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E97.D.1842
- Type of Manuscript
- PAPER
- Category
- Pattern Recognition
Authors
Akira TAMAMORI
Nagoya Institute of Technology
Yoshihiko NANKAKU
Nagoya Institute of Technology
Keiichi TOKUDA
Nagoya Institute of Technology
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Akira TAMAMORI, Yoshihiko NANKAKU, Keiichi TOKUDA, "Image Recognition Based on Separable Lattice Trajectory 2-D HMMs" in IEICE TRANSACTIONS on Information,
vol. E97-D, no. 7, pp. 1842-1854, July 2014, doi: 10.1587/transinf.E97.D.1842.
Abstract: In this paper, a novel statistical model based on 2-D HMMs for image recognition is proposed. Recently, separable lattice 2-D HMMs (SL2D-HMMs) were proposed to model invariance to size and location deformation. However, their modeling accuracy is still insufficient because of the following two assumptions, which are inherited from 1-D HMMs: i) the stationary statistics within each state and ii) the conditional independent assumption of state output probabilities. To overcome these shortcomings in 1-D HMMs, trajectory HMMs were proposed and successfully applied to speech recognition and speech synthesis. This paper derives 2-D trajectory HMMs by reformulating the likelihood of SL2D-HMMs through the imposition of explicit relationships between static and dynamic features. The proposed model can efficiently capture dependencies between adjacent observations without increasing the number of model parameters. The effectiveness of the proposed model was evaluated in face recognition experiments on the XM2VTS database.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E97.D.1842/_p
Copy
@ARTICLE{e97-d_7_1842,
author={Akira TAMAMORI, Yoshihiko NANKAKU, Keiichi TOKUDA, },
journal={IEICE TRANSACTIONS on Information},
title={Image Recognition Based on Separable Lattice Trajectory 2-D HMMs},
year={2014},
volume={E97-D},
number={7},
pages={1842-1854},
abstract={In this paper, a novel statistical model based on 2-D HMMs for image recognition is proposed. Recently, separable lattice 2-D HMMs (SL2D-HMMs) were proposed to model invariance to size and location deformation. However, their modeling accuracy is still insufficient because of the following two assumptions, which are inherited from 1-D HMMs: i) the stationary statistics within each state and ii) the conditional independent assumption of state output probabilities. To overcome these shortcomings in 1-D HMMs, trajectory HMMs were proposed and successfully applied to speech recognition and speech synthesis. This paper derives 2-D trajectory HMMs by reformulating the likelihood of SL2D-HMMs through the imposition of explicit relationships between static and dynamic features. The proposed model can efficiently capture dependencies between adjacent observations without increasing the number of model parameters. The effectiveness of the proposed model was evaluated in face recognition experiments on the XM2VTS database.},
keywords={},
doi={10.1587/transinf.E97.D.1842},
ISSN={1745-1361},
month={July},}
Copy
TY - JOUR
TI - Image Recognition Based on Separable Lattice Trajectory 2-D HMMs
T2 - IEICE TRANSACTIONS on Information
SP - 1842
EP - 1854
AU - Akira TAMAMORI
AU - Yoshihiko NANKAKU
AU - Keiichi TOKUDA
PY - 2014
DO - 10.1587/transinf.E97.D.1842
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2014
AB - In this paper, a novel statistical model based on 2-D HMMs for image recognition is proposed. Recently, separable lattice 2-D HMMs (SL2D-HMMs) were proposed to model invariance to size and location deformation. However, their modeling accuracy is still insufficient because of the following two assumptions, which are inherited from 1-D HMMs: i) the stationary statistics within each state and ii) the conditional independent assumption of state output probabilities. To overcome these shortcomings in 1-D HMMs, trajectory HMMs were proposed and successfully applied to speech recognition and speech synthesis. This paper derives 2-D trajectory HMMs by reformulating the likelihood of SL2D-HMMs through the imposition of explicit relationships between static and dynamic features. The proposed model can efficiently capture dependencies between adjacent observations without increasing the number of model parameters. The effectiveness of the proposed model was evaluated in face recognition experiments on the XM2VTS database.
ER -
English
