Improvement of early recognition of gesture patterns based on a self-organizing map

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

We propose an approach to achieving early recognition of gesture patterns. Early recognition is a method for recognizing sequential patterns at their earliest stage. Therefore, in the case of gesture recognition, we can get a recognition result for human gestures before the gestures are finished. The most difficult problem in early recognition is knowing when the system has determined the result. Most traditional approaches suffer from this problem, since gestures are often ambiguous. At the start of a gesture, in particular, it is very difficult to determinate the recognition result since insufficient input data have been observed. Therefore, we have improved on the traditional approach by using a self-organizing map.

Original languageEnglish
Pages (from-to)198-201
Number of pages4
JournalArtificial Life and Robotics
Volume16
Issue number2
DOIs
Publication statusPublished - Sep 1 2011

Fingerprint

Gesture recognition
Gestures
Self organizing maps

All Science Journal Classification (ASJC) codes

  • Biochemistry, Genetics and Molecular Biology(all)
  • Artificial Intelligence

Cite this

Improvement of early recognition of gesture patterns based on a self-organizing map. / Shimada, Atsushi; Kawashima, Manabu; Taniguchi, Rin ichiro.

In: Artificial Life and Robotics, Vol. 16, No. 2, 01.09.2011, p. 198-201.

Research output: Contribution to journalArticle

@article{0a5e0af5e3bb4366905d4a9e8ae8b1ce,
title = "Improvement of early recognition of gesture patterns based on a self-organizing map",
abstract = "We propose an approach to achieving early recognition of gesture patterns. Early recognition is a method for recognizing sequential patterns at their earliest stage. Therefore, in the case of gesture recognition, we can get a recognition result for human gestures before the gestures are finished. The most difficult problem in early recognition is knowing when the system has determined the result. Most traditional approaches suffer from this problem, since gestures are often ambiguous. At the start of a gesture, in particular, it is very difficult to determinate the recognition result since insufficient input data have been observed. Therefore, we have improved on the traditional approach by using a self-organizing map.",
author = "Atsushi Shimada and Manabu Kawashima and Taniguchi, {Rin ichiro}",
year = "2011",
month = "9",
day = "1",
doi = "10.1007/s10015-011-0917-9",
language = "English",
volume = "16",
pages = "198--201",
journal = "Artificial Life and Robotics",
issn = "1433-5298",
publisher = "Springer Japan",
number = "2",

}

TY - JOUR

T1 - Improvement of early recognition of gesture patterns based on a self-organizing map

AU - Shimada, Atsushi

AU - Kawashima, Manabu

AU - Taniguchi, Rin ichiro

PY - 2011/9/1

Y1 - 2011/9/1

N2 - We propose an approach to achieving early recognition of gesture patterns. Early recognition is a method for recognizing sequential patterns at their earliest stage. Therefore, in the case of gesture recognition, we can get a recognition result for human gestures before the gestures are finished. The most difficult problem in early recognition is knowing when the system has determined the result. Most traditional approaches suffer from this problem, since gestures are often ambiguous. At the start of a gesture, in particular, it is very difficult to determinate the recognition result since insufficient input data have been observed. Therefore, we have improved on the traditional approach by using a self-organizing map.

AB - We propose an approach to achieving early recognition of gesture patterns. Early recognition is a method for recognizing sequential patterns at their earliest stage. Therefore, in the case of gesture recognition, we can get a recognition result for human gestures before the gestures are finished. The most difficult problem in early recognition is knowing when the system has determined the result. Most traditional approaches suffer from this problem, since gestures are often ambiguous. At the start of a gesture, in particular, it is very difficult to determinate the recognition result since insufficient input data have been observed. Therefore, we have improved on the traditional approach by using a self-organizing map.

UR - http://www.scopus.com/inward/record.url?scp=80052483757&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052483757&partnerID=8YFLogxK

U2 - 10.1007/s10015-011-0917-9

DO - 10.1007/s10015-011-0917-9

M3 - Article

AN - SCOPUS:80052483757

VL - 16

SP - 198

EP - 201

JO - Artificial Life and Robotics

JF - Artificial Life and Robotics

SN - 1433-5298

IS - 2

ER -