Dynamic Gesture Recognition System with Gesture Spotting Based on Self-Organizing Maps
In this paper, a real-time dynamic hand gesture recognition system with gesture spotting function is proposed. In the proposed system, input video frames are converted to feature vectors, and they are used to form a posture sequence vector that represents the input gesture. Then, gesture identificat...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-02-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/11/4/1933 |
id |
doaj-4a043a583c4648a7be7e11ecee9cf45a |
---|---|
record_format |
Article |
spelling |
doaj-4a043a583c4648a7be7e11ecee9cf45a2021-02-23T00:05:10ZengMDPI AGApplied Sciences2076-34172021-02-01111933193310.3390/app11041933Dynamic Gesture Recognition System with Gesture Spotting Based on Self-Organizing MapsHiroomi Hikawa0Yuta Ichikawa1Hidetaka Ito2Yutaka Maeda3Kansai University, Facultiy of Engineering Science, Osaka 564-8680, JapanKansai University, Facultiy of Engineering Science, Osaka 564-8680, JapanKansai University, Facultiy of Engineering Science, Osaka 564-8680, JapanKansai University, Facultiy of Engineering Science, Osaka 564-8680, JapanIn this paper, a real-time dynamic hand gesture recognition system with gesture spotting function is proposed. In the proposed system, input video frames are converted to feature vectors, and they are used to form a posture sequence vector that represents the input gesture. Then, gesture identification and gesture spotting are carried out in the self-organizing map (SOM)-Hebb classifier. The gesture spotting function detects the end of the gesture by using the vector distance between the posture sequence vector and the winner neuron’s weight vector. The proposed gesture recognition method was tested by simulation and real-time gesture recognition experiment. Results revealed that the system could recognize nine types of gesture with an accuracy of 96.6%, and it successfully outputted the recognition result at the end of gesture using the spotting result.https://www.mdpi.com/2076-3417/11/4/1933dynamic gesture recognitiongesture spottingself-organizing map |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hiroomi Hikawa Yuta Ichikawa Hidetaka Ito Yutaka Maeda |
spellingShingle |
Hiroomi Hikawa Yuta Ichikawa Hidetaka Ito Yutaka Maeda Dynamic Gesture Recognition System with Gesture Spotting Based on Self-Organizing Maps Applied Sciences dynamic gesture recognition gesture spotting self-organizing map |
author_facet |
Hiroomi Hikawa Yuta Ichikawa Hidetaka Ito Yutaka Maeda |
author_sort |
Hiroomi Hikawa |
title |
Dynamic Gesture Recognition System with Gesture Spotting Based on Self-Organizing Maps |
title_short |
Dynamic Gesture Recognition System with Gesture Spotting Based on Self-Organizing Maps |
title_full |
Dynamic Gesture Recognition System with Gesture Spotting Based on Self-Organizing Maps |
title_fullStr |
Dynamic Gesture Recognition System with Gesture Spotting Based on Self-Organizing Maps |
title_full_unstemmed |
Dynamic Gesture Recognition System with Gesture Spotting Based on Self-Organizing Maps |
title_sort |
dynamic gesture recognition system with gesture spotting based on self-organizing maps |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2021-02-01 |
description |
In this paper, a real-time dynamic hand gesture recognition system with gesture spotting function is proposed. In the proposed system, input video frames are converted to feature vectors, and they are used to form a posture sequence vector that represents the input gesture. Then, gesture identification and gesture spotting are carried out in the self-organizing map (SOM)-Hebb classifier. The gesture spotting function detects the end of the gesture by using the vector distance between the posture sequence vector and the winner neuron’s weight vector. The proposed gesture recognition method was tested by simulation and real-time gesture recognition experiment. Results revealed that the system could recognize nine types of gesture with an accuracy of 96.6%, and it successfully outputted the recognition result at the end of gesture using the spotting result. |
topic |
dynamic gesture recognition gesture spotting self-organizing map |
url |
https://www.mdpi.com/2076-3417/11/4/1933 |
work_keys_str_mv |
AT hiroomihikawa dynamicgesturerecognitionsystemwithgesturespottingbasedonselforganizingmaps AT yutaichikawa dynamicgesturerecognitionsystemwithgesturespottingbasedonselforganizingmaps AT hidetakaito dynamicgesturerecognitionsystemwithgesturespottingbasedonselforganizingmaps AT yutakamaeda dynamicgesturerecognitionsystemwithgesturespottingbasedonselforganizingmaps |
_version_ |
1724255361987248128 |