A framework for real-time hand gesture recognition in uncontrolled environments with partition matrix model based on hidden conditional random fields

Yi Yao; Chang Tsun Li

doi:10.1109/SMC.2013.209

A framework for real-time hand gesture recognition in uncontrolled environments with partition matrix model based on hidden conditional random fields

Yi Yao, Chang Tsun Li

University of Warwick

Research output: Book chapter/Published conference paper › Conference paper › peer-review

1 Citation (Scopus)

Abstract

The main obstructions of making hand gesture recognition methods robust in real-world applications are the challenges from the uncontrolled environments, including: gesturing hand out of the scene, pause during gestures, complex background, skin-coloured regions moving in background, performers wearing short sleeve and face overlapping with hand. Therefore, a framework for real-time hand gesture recognition in uncontrolled environments is proposed in this paper. A novel tracking scheme is proposed to track multiple hand candidates in unconstrained background, and a weighting model for gesture classification based on Hidden Conditional Random Fields which takes trajectories of multiple hand candidates under different frame rates into consideration is also introduced. The framework achieved invariance under change of scale, speed and location of the hand gestures. The Experimental results of the proposed framework on Palm Graffiti Digits database and Warwick Hand Gesture database show that it can perform well in uncontrolled environments.

Original language	English
Title of host publication	Proceedings: 2013 IEEE International Conference on Systems, Man, and Cybernetics SMC 2013
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	1205-1210
Number of pages	6
ISBN (Print)	9780769551548
DOIs	https://doi.org/10.1109/SMC.2013.209
Publication status	Published - 2013
Event	2013 IEEE International Conference on Systems, Man and Cybernetics (SMC 2013) - Midland Hotel, Manchester, United Kingdom Duration: 13 Oct 2013 → 16 Oct 2013 https://www.ieee.org/conferences_events/conferences/conferencedetails/index.html?Conf_ID=20015

Conference

Conference	2013 IEEE International Conference on Systems, Man and Cybernetics (SMC 2013)
Abbreviated title	Cyber Systems Enabling Knowledge Integration: The Smart Response to Emerging Societal Challenges
Country/Territory	United Kingdom
City	Manchester
Period	13/10/13 → 16/10/13
Other	SMC 2013 targets advances in Systems Science and Engineering Human-machine Systems and Cybernetics involving state-of-the-art technologies interacting with humans to provide an enriching experience and thereby improving the quality of lives including theories, methodologies and emerging applications.
Internet address	https://www.ieee.org/conferences_events/conferences/conferencedetails/index.html?Conf_ID=20015

Access to Document

10.1109/SMC.2013.209

Cite this

Yao, Y., & Li, C. T. (2013). A framework for real-time hand gesture recognition in uncontrolled environments with partition matrix model based on hidden conditional random fields. In Proceedings: 2013 IEEE International Conference on Systems, Man, and Cybernetics SMC 2013 (pp. 1205-1210). [6721962] IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/SMC.2013.209

@inproceedings{3bfe91606d684095a3faf606c24fbb46,

title = "A framework for real-time hand gesture recognition in uncontrolled environments with partition matrix model based on hidden conditional random fields",

abstract = "The main obstructions of making hand gesture recognition methods robust in real-world applications are the challenges from the uncontrolled environments, including: gesturing hand out of the scene, pause during gestures, complex background, skin-coloured regions moving in background, performers wearing short sleeve and face overlapping with hand. Therefore, a framework for real-time hand gesture recognition in uncontrolled environments is proposed in this paper. A novel tracking scheme is proposed to track multiple hand candidates in unconstrained background, and a weighting model for gesture classification based on Hidden Conditional Random Fields which takes trajectories of multiple hand candidates under different frame rates into consideration is also introduced. The framework achieved invariance under change of scale, speed and location of the hand gestures. The Experimental results of the proposed framework on Palm Graffiti Digits database and Warwick Hand Gesture database show that it can perform well in uncontrolled environments.",

keywords = "Hand gesture recognition, Hidden conditional random fields, Surf tracking, Uncontrolled environments",

author = "Yi Yao and Li, {Chang Tsun}",

year = "2013",

doi = "10.1109/SMC.2013.209",

language = "English",

isbn = "9780769551548",

pages = "1205--1210",

booktitle = "Proceedings: 2013 IEEE International Conference on Systems, Man, and Cybernetics SMC 2013",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

note = "2013 IEEE International Conference on Systems, Man and Cybernetics (SMC 2013), Cyber Systems Enabling Knowledge Integration: The Smart Response to Emerging Societal Challenges ; Conference date: 13-10-2013 Through 16-10-2013",

url = "https://www.ieee.org/conferences_events/conferences/conferencedetails/index.html?Conf_ID=20015",

}

Yao, Y & Li, CT 2013, A framework for real-time hand gesture recognition in uncontrolled environments with partition matrix model based on hidden conditional random fields. in Proceedings: 2013 IEEE International Conference on Systems, Man, and Cybernetics SMC 2013., 6721962, IEEE, Institute of Electrical and Electronics Engineers, pp. 1205-1210, 2013 IEEE International Conference on Systems, Man and Cybernetics (SMC 2013), Manchester, United Kingdom, 13/10/13. https://doi.org/10.1109/SMC.2013.209

A framework for real-time hand gesture recognition in uncontrolled environments with partition matrix model based on hidden conditional random fields. / Yao, Yi; Li, Chang Tsun.

Proceedings: 2013 IEEE International Conference on Systems, Man, and Cybernetics SMC 2013. IEEE, Institute of Electrical and Electronics Engineers, 2013. p. 1205-1210 6721962.

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - A framework for real-time hand gesture recognition in uncontrolled environments with partition matrix model based on hidden conditional random fields

AU - Yao, Yi

AU - Li, Chang Tsun

PY - 2013

Y1 - 2013

N2 - The main obstructions of making hand gesture recognition methods robust in real-world applications are the challenges from the uncontrolled environments, including: gesturing hand out of the scene, pause during gestures, complex background, skin-coloured regions moving in background, performers wearing short sleeve and face overlapping with hand. Therefore, a framework for real-time hand gesture recognition in uncontrolled environments is proposed in this paper. A novel tracking scheme is proposed to track multiple hand candidates in unconstrained background, and a weighting model for gesture classification based on Hidden Conditional Random Fields which takes trajectories of multiple hand candidates under different frame rates into consideration is also introduced. The framework achieved invariance under change of scale, speed and location of the hand gestures. The Experimental results of the proposed framework on Palm Graffiti Digits database and Warwick Hand Gesture database show that it can perform well in uncontrolled environments.

AB - The main obstructions of making hand gesture recognition methods robust in real-world applications are the challenges from the uncontrolled environments, including: gesturing hand out of the scene, pause during gestures, complex background, skin-coloured regions moving in background, performers wearing short sleeve and face overlapping with hand. Therefore, a framework for real-time hand gesture recognition in uncontrolled environments is proposed in this paper. A novel tracking scheme is proposed to track multiple hand candidates in unconstrained background, and a weighting model for gesture classification based on Hidden Conditional Random Fields which takes trajectories of multiple hand candidates under different frame rates into consideration is also introduced. The framework achieved invariance under change of scale, speed and location of the hand gestures. The Experimental results of the proposed framework on Palm Graffiti Digits database and Warwick Hand Gesture database show that it can perform well in uncontrolled environments.

KW - Hand gesture recognition

KW - Hidden conditional random fields

KW - Surf tracking

KW - Uncontrolled environments

UR - http://www.scopus.com/inward/record.url?scp=84893580694&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893580694&partnerID=8YFLogxK

U2 - 10.1109/SMC.2013.209

DO - 10.1109/SMC.2013.209

M3 - Conference paper

AN - SCOPUS:84893580694

SN - 9780769551548

SP - 1205

EP - 1210

BT - Proceedings: 2013 IEEE International Conference on Systems, Man, and Cybernetics SMC 2013

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - 2013 IEEE International Conference on Systems, Man and Cybernetics (SMC 2013)

Y2 - 13 October 2013 through 16 October 2013

ER -

A framework for real-time hand gesture recognition in uncontrolled environments with partition matrix model based on hidden conditional random fields

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this