An experimental comparison of trajectory-based and history-based representation for gesture recognition

Kenny Morrison; Stephen J. McKenna

An experimental comparison of trajectory-based and history-based representation for gesture recognition

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

Abstract

Automatic visual recognition of gestures can be performed using either a trajectory-based or a history-based representation. The former characterises the gesture using 2D trajectories of the hands. The latter summarises image sequences using values computed from individual pixel histories. A direct experimental comparison of these two approaches is presented using skin colour as a common visual cue and recognition methods based on hidden Markov models, moment features and normalised template matching. Skin history images are proposed as a useful history-based representation. Results are reported on a database of sixty gestures and the relative advantages and disadvantages of the different methods are highlighted.

Original language	English
Title of host publication	Gesture-Based Communication in Human-Computer Interaction
Subtitle of host publication	5th International Gesture Workshop, GW 2003, Genova, Italy, April 15-17, 2003, Selected Revised Papers
Editors	Antonio Camurri, Gualtiero Volpe
Place of Publication	Berlin
Publisher	Springer
Pages	152-163
Number of pages	12
ISBN (Electronic)	9783540245988
ISBN (Print)	9783540210726
Publication status	Published - 2004
Event	5th International Gesture Workshop - Genova, Italy Duration: 15 Apr 2003 → 17 Apr 2003

Publication series

Name	Lecture notes in computer science
Publisher	Springer
Volume	2915

Workshop

Workshop	5th International Gesture Workshop
Abbreviated title	GW 2003
Country/Territory	Italy
City	Genova
Period	15/04/03 → 17/04/03

Access to Document

http://link.springer.com/chapter/10.1007%2F978-3-540-24598-8_15

Cite this

Morrison, K., & McKenna, S. J. (2004). An experimental comparison of trajectory-based and history-based representation for gesture recognition. In A. Camurri, & G. Volpe (Eds.), Gesture-Based Communication in Human-Computer Interaction: 5th International Gesture Workshop, GW 2003, Genova, Italy, April 15-17, 2003, Selected Revised Papers (pp. 152-163). (Lecture notes in computer science; Vol. 2915). Springer . http://link.springer.com/chapter/10.1007%2F978-3-540-24598-8_15

Morrison, Kenny ; McKenna, Stephen J. / An experimental comparison of trajectory-based and history-based representation for gesture recognition. Gesture-Based Communication in Human-Computer Interaction: 5th International Gesture Workshop, GW 2003, Genova, Italy, April 15-17, 2003, Selected Revised Papers. editor / Antonio Camurri ; Gualtiero Volpe. Berlin : Springer , 2004. pp. 152-163 (Lecture notes in computer science).

@inproceedings{4e346a30805d49c1985c1912f6b3ab9d,

title = "An experimental comparison of trajectory-based and history-based representation for gesture recognition",

abstract = "Automatic visual recognition of gestures can be performed using either a trajectory-based or a history-based representation. The former characterises the gesture using 2D trajectories of the hands. The latter summarises image sequences using values computed from individual pixel histories. A direct experimental comparison of these two approaches is presented using skin colour as a common visual cue and recognition methods based on hidden Markov models, moment features and normalised template matching. Skin history images are proposed as a useful history-based representation. Results are reported on a database of sixty gestures and the relative advantages and disadvantages of the different methods are highlighted.",

author = "Kenny Morrison and McKenna, {Stephen J.}",

year = "2004",

language = "English",

isbn = "9783540210726",

series = "Lecture notes in computer science",

publisher = "Springer ",

pages = "152--163",

editor = "Camurri, {Antonio } and Volpe, {Gualtiero }",

booktitle = "Gesture-Based Communication in Human-Computer Interaction",

}

Morrison, K & McKenna, SJ 2004, An experimental comparison of trajectory-based and history-based representation for gesture recognition. in A Camurri & G Volpe (eds), Gesture-Based Communication in Human-Computer Interaction: 5th International Gesture Workshop, GW 2003, Genova, Italy, April 15-17, 2003, Selected Revised Papers. Lecture notes in computer science, vol. 2915, Springer , Berlin, pp. 152-163, 5th International Gesture Workshop, Genova, Italy, 15/04/03. <http://link.springer.com/chapter/10.1007%2F978-3-540-24598-8_15>

An experimental comparison of trajectory-based and history-based representation for gesture recognition. / Morrison, Kenny; McKenna, Stephen J.
Gesture-Based Communication in Human-Computer Interaction: 5th International Gesture Workshop, GW 2003, Genova, Italy, April 15-17, 2003, Selected Revised Papers. ed. / Antonio Camurri; Gualtiero Volpe. Berlin: Springer , 2004. p. 152-163 (Lecture notes in computer science; Vol. 2915).

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

TY - GEN

T1 - An experimental comparison of trajectory-based and history-based representation for gesture recognition

AU - Morrison, Kenny

AU - McKenna, Stephen J.

PY - 2004

Y1 - 2004

N2 - Automatic visual recognition of gestures can be performed using either a trajectory-based or a history-based representation. The former characterises the gesture using 2D trajectories of the hands. The latter summarises image sequences using values computed from individual pixel histories. A direct experimental comparison of these two approaches is presented using skin colour as a common visual cue and recognition methods based on hidden Markov models, moment features and normalised template matching. Skin history images are proposed as a useful history-based representation. Results are reported on a database of sixty gestures and the relative advantages and disadvantages of the different methods are highlighted.

AB - Automatic visual recognition of gestures can be performed using either a trajectory-based or a history-based representation. The former characterises the gesture using 2D trajectories of the hands. The latter summarises image sequences using values computed from individual pixel histories. A direct experimental comparison of these two approaches is presented using skin colour as a common visual cue and recognition methods based on hidden Markov models, moment features and normalised template matching. Skin history images are proposed as a useful history-based representation. Results are reported on a database of sixty gestures and the relative advantages and disadvantages of the different methods are highlighted.

UR - http://www.scopus.com/inward/record.url?scp=7444234373&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:7444234373

SN - 9783540210726

T3 - Lecture notes in computer science

SP - 152

EP - 163

BT - Gesture-Based Communication in Human-Computer Interaction

A2 - Camurri, Antonio

A2 - Volpe, Gualtiero

PB - Springer

CY - Berlin

T2 - 5th International Gesture Workshop

Y2 - 15 April 2003 through 17 April 2003

ER -

Morrison K, McKenna SJ. An experimental comparison of trajectory-based and history-based representation for gesture recognition. In Camurri A, Volpe G, editors, Gesture-Based Communication in Human-Computer Interaction: 5th International Gesture Workshop, GW 2003, Genova, Italy, April 15-17, 2003, Selected Revised Papers. Berlin: Springer . 2004. p. 152-163. (Lecture notes in computer science).

An experimental comparison of trajectory-based and history-based representation for gesture recognition

Abstract

Publication series

Workshop

Access to Document

Other files and links

Fingerprint

Cite this