Hand motion recognition via fuzzy active curve axis gaussian mixture models: A comparative study

Zhaojie Ju; Honghai Liu

doi:10.1109/FUZZY.2011.6007367

Hand motion recognition via fuzzy active curve axis gaussian mixture models: A comparative study

Zhaojie Ju^*
, Honghai Liu

^*Corresponding author for this work

University of Portsmouth

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

Unconstrained human hand motions consisting grasp motion and in-hand manipulation lead to a fundamental challenge that many algorithms have to face in both theoretical and practical development, mainly due to the complexity and dexterity of the human hand. In this paper, fuzzy active curve axis Gaussian Mixture Model (FAcaGMM) is proposed by introducing a weighting exponent on the fuzzy membership into active curve axis Gaussian Mixture Models (AcaGMM) to improve its convergence efficiency, and then FAcaGMM is used to recognize human hand motions. In addition, a comparative study of recognition methods including FAcaGMM, Time Clustering (TC), Empirical Copula (EC), GMM and HMM is presented to recognize human hand motions including both grasps and in-hand manipulations from different subjects with varying training samples.

Original language	English
Title of host publication	FUZZ 2011 - 2011 IEEE International Conference on Fuzzy Systems - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	699-705
Number of pages	7
ISBN (Print)	9781424473175
DOIs	https://doi.org/10.1109/FUZZY.2011.6007367
State	Published - 2011
Externally published	Yes

Publication series

Name	IEEE International Conference on Fuzzy Systems
ISSN (Print)	1098-7584

Keywords

Active Curve Axis Gaussian Mixture Models
Fuzzy Active Curve Axis Gaussian Mixture Models
Gaussian Mixture Models
Motion Recognition

Access to Document

10.1109/FUZZY.2011.6007367

Cite this

Ju, Z., & Liu, H. (2011). Hand motion recognition via fuzzy active curve axis gaussian mixture models: A comparative study. In FUZZ 2011 - 2011 IEEE International Conference on Fuzzy Systems - Proceedings (pp. 699-705). Article 6007367 (IEEE International Conference on Fuzzy Systems). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/FUZZY.2011.6007367

@inproceedings{de9cc004cb3e4604b7b75b855f804dc5,

title = "Hand motion recognition via fuzzy active curve axis gaussian mixture models: A comparative study",

abstract = "Unconstrained human hand motions consisting grasp motion and in-hand manipulation lead to a fundamental challenge that many algorithms have to face in both theoretical and practical development, mainly due to the complexity and dexterity of the human hand. In this paper, fuzzy active curve axis Gaussian Mixture Model (FAcaGMM) is proposed by introducing a weighting exponent on the fuzzy membership into active curve axis Gaussian Mixture Models (AcaGMM) to improve its convergence efficiency, and then FAcaGMM is used to recognize human hand motions. In addition, a comparative study of recognition methods including FAcaGMM, Time Clustering (TC), Empirical Copula (EC), GMM and HMM is presented to recognize human hand motions including both grasps and in-hand manipulations from different subjects with varying training samples.",

keywords = "Active Curve Axis Gaussian Mixture Models, Fuzzy Active Curve Axis Gaussian Mixture Models, Gaussian Mixture Models, Motion Recognition",

author = "Zhaojie Ju and Honghai Liu",

year = "2011",

doi = "10.1109/FUZZY.2011.6007367",

language = "英语",

isbn = "9781424473175",

series = "IEEE International Conference on Fuzzy Systems",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "699--705",

booktitle = "FUZZ 2011 - 2011 IEEE International Conference on Fuzzy Systems - Proceedings",

address = "美国",

}

Ju, Z & Liu, H 2011, Hand motion recognition via fuzzy active curve axis gaussian mixture models: A comparative study. in FUZZ 2011 - 2011 IEEE International Conference on Fuzzy Systems - Proceedings., 6007367, IEEE International Conference on Fuzzy Systems, Institute of Electrical and Electronics Engineers Inc., pp. 699-705. https://doi.org/10.1109/FUZZY.2011.6007367

Hand motion recognition via fuzzy active curve axis gaussian mixture models: A comparative study. / Ju, Zhaojie; Liu, Honghai.
FUZZ 2011 - 2011 IEEE International Conference on Fuzzy Systems - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2011. p. 699-705 6007367 (IEEE International Conference on Fuzzy Systems).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Hand motion recognition via fuzzy active curve axis gaussian mixture models

T2 - A comparative study

AU - Ju, Zhaojie

AU - Liu, Honghai

PY - 2011

Y1 - 2011

N2 - Unconstrained human hand motions consisting grasp motion and in-hand manipulation lead to a fundamental challenge that many algorithms have to face in both theoretical and practical development, mainly due to the complexity and dexterity of the human hand. In this paper, fuzzy active curve axis Gaussian Mixture Model (FAcaGMM) is proposed by introducing a weighting exponent on the fuzzy membership into active curve axis Gaussian Mixture Models (AcaGMM) to improve its convergence efficiency, and then FAcaGMM is used to recognize human hand motions. In addition, a comparative study of recognition methods including FAcaGMM, Time Clustering (TC), Empirical Copula (EC), GMM and HMM is presented to recognize human hand motions including both grasps and in-hand manipulations from different subjects with varying training samples.

AB - Unconstrained human hand motions consisting grasp motion and in-hand manipulation lead to a fundamental challenge that many algorithms have to face in both theoretical and practical development, mainly due to the complexity and dexterity of the human hand. In this paper, fuzzy active curve axis Gaussian Mixture Model (FAcaGMM) is proposed by introducing a weighting exponent on the fuzzy membership into active curve axis Gaussian Mixture Models (AcaGMM) to improve its convergence efficiency, and then FAcaGMM is used to recognize human hand motions. In addition, a comparative study of recognition methods including FAcaGMM, Time Clustering (TC), Empirical Copula (EC), GMM and HMM is presented to recognize human hand motions including both grasps and in-hand manipulations from different subjects with varying training samples.

KW - Active Curve Axis Gaussian Mixture Models

KW - Fuzzy Active Curve Axis Gaussian Mixture Models

KW - Gaussian Mixture Models

KW - Motion Recognition

UR - https://www.scopus.com/pages/publications/80053071390

U2 - 10.1109/FUZZY.2011.6007367

DO - 10.1109/FUZZY.2011.6007367

M3 - 会议稿件

AN - SCOPUS:80053071390

SN - 9781424473175

T3 - IEEE International Conference on Fuzzy Systems

SP - 699

EP - 705

BT - FUZZ 2011 - 2011 IEEE International Conference on Fuzzy Systems - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Hand motion recognition via fuzzy active curve axis gaussian mixture models: A comparative study

Abstract

Publication series

Keywords

Access to Document

Other files and links

Fingerprint

Cite this