Comparing Some Distances in Template-based 2D Gesture Recognition

Jean Vanderdonckt, Bruno Dumas, Mauro Cherubini

Research output: Contribution in Book/Catalog/Report/Conference proceedingConference contribution

Abstract

Euclidean distance is traditionally used to compare a gesture candidate against gesture templates in two-dimensional gesture recognizers. This paper compares two distances borrowed from other domains of computer science used in template-based two-dimensional gesture recognizers: the Mahalanobis distance, typically used in computer vision and statistics, and the Jaro-Winckler distance, typically used in information retrieval and pattern recognition. Although the geometric interpretation of these distances is less straightforward for designers, there is a significant impact of the Mahalanobis distance on recognition rate, but not for the Jaro-Winkler one.

Original languageEnglish
Title of host publicationCHI 2018 - Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems
Subtitle of host publicationEngage with CHI
PublisherACM Press
Pages1-6
Number of pages6
Volume2018-April
ISBN (Electronic)9781450356206, 9781450356213
ISBN (Print)9781450356213
DOIs
Publication statusPublished - 21 Apr 2018

Fingerprint

Gesture recognition
Information retrieval
Computer science
Computer vision
Pattern recognition
Statistics

Keywords

  • Gesture recognition
  • Gesture recognizer
  • Template-based recognition

Cite this

Vanderdonckt, J., Dumas, B., & Cherubini, M. (2018). Comparing Some Distances in Template-based 2D Gesture Recognition. In CHI 2018 - Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems: Engage with CHI (Vol. 2018-April, pp. 1-6). [LBW121] ACM Press. https://doi.org/10.1145/3170427.3188452
Vanderdonckt, Jean ; Dumas, Bruno ; Cherubini, Mauro. / Comparing Some Distances in Template-based 2D Gesture Recognition. CHI 2018 - Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems: Engage with CHI. Vol. 2018-April ACM Press, 2018. pp. 1-6
@inproceedings{2d856f347a0d4a39bb69a1367753c3e7,
title = "Comparing Some Distances in Template-based 2D Gesture Recognition",
abstract = "Euclidean distance is traditionally used to compare a gesture candidate against gesture templates in two-dimensional gesture recognizers. This paper compares two distances borrowed from other domains of computer science used in template-based two-dimensional gesture recognizers: the Mahalanobis distance, typically used in computer vision and statistics, and the Jaro-Winckler distance, typically used in information retrieval and pattern recognition. Although the geometric interpretation of these distances is less straightforward for designers, there is a significant impact of the Mahalanobis distance on recognition rate, but not for the Jaro-Winkler one.",
keywords = "Gesture recognition, Gesture recognizer, Template-based recognition",
author = "Jean Vanderdonckt and Bruno Dumas and Mauro Cherubini",
year = "2018",
month = "4",
day = "21",
doi = "https://doi.org/10.1145/3170427.3188452",
language = "English",
isbn = "9781450356213",
volume = "2018-April",
pages = "1--6",
booktitle = "CHI 2018 - Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems",
publisher = "ACM Press",
address = "United States",

}

Vanderdonckt, J, Dumas, B & Cherubini, M 2018, Comparing Some Distances in Template-based 2D Gesture Recognition. in CHI 2018 - Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems: Engage with CHI. vol. 2018-April, LBW121, ACM Press, pp. 1-6. https://doi.org/10.1145/3170427.3188452

Comparing Some Distances in Template-based 2D Gesture Recognition. / Vanderdonckt, Jean; Dumas, Bruno; Cherubini, Mauro.

CHI 2018 - Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems: Engage with CHI. Vol. 2018-April ACM Press, 2018. p. 1-6 LBW121.

Research output: Contribution in Book/Catalog/Report/Conference proceedingConference contribution

TY - GEN

T1 - Comparing Some Distances in Template-based 2D Gesture Recognition

AU - Vanderdonckt, Jean

AU - Dumas, Bruno

AU - Cherubini, Mauro

PY - 2018/4/21

Y1 - 2018/4/21

N2 - Euclidean distance is traditionally used to compare a gesture candidate against gesture templates in two-dimensional gesture recognizers. This paper compares two distances borrowed from other domains of computer science used in template-based two-dimensional gesture recognizers: the Mahalanobis distance, typically used in computer vision and statistics, and the Jaro-Winckler distance, typically used in information retrieval and pattern recognition. Although the geometric interpretation of these distances is less straightforward for designers, there is a significant impact of the Mahalanobis distance on recognition rate, but not for the Jaro-Winkler one.

AB - Euclidean distance is traditionally used to compare a gesture candidate against gesture templates in two-dimensional gesture recognizers. This paper compares two distances borrowed from other domains of computer science used in template-based two-dimensional gesture recognizers: the Mahalanobis distance, typically used in computer vision and statistics, and the Jaro-Winckler distance, typically used in information retrieval and pattern recognition. Although the geometric interpretation of these distances is less straightforward for designers, there is a significant impact of the Mahalanobis distance on recognition rate, but not for the Jaro-Winkler one.

KW - Gesture recognition

KW - Gesture recognizer

KW - Template-based recognition

UR - http://www.scopus.com/inward/record.url?scp=85052021367&partnerID=8YFLogxK

U2 - https://doi.org/10.1145/3170427.3188452

DO - https://doi.org/10.1145/3170427.3188452

M3 - Conference contribution

SN - 9781450356213

VL - 2018-April

SP - 1

EP - 6

BT - CHI 2018 - Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems

PB - ACM Press

ER -

Vanderdonckt J, Dumas B, Cherubini M. Comparing Some Distances in Template-based 2D Gesture Recognition. In CHI 2018 - Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems: Engage with CHI. Vol. 2018-April. ACM Press. 2018. p. 1-6. LBW121 https://doi.org/10.1145/3170427.3188452