A hand gesture recognition sensor using reflected impulses

Seo Yul Kim, Hong Gul Han, Jin Woo Kim, Sanghoon Lee, Tae Wook Kim

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

This paper introduces a hand gesture recognition sensor using ultra-wideband impulse signals, which are reflected from a hand. The reflected waveforms in time domain are determined by the reflection surface of a target. Thus every gesture has its own reflected waveform. Thus we propose to use machine learning, such as convolutional neural network (CNN) for the gesture classification. The CNN extracts its own feature and constructs classification model then classifies the reflected waveforms. Six hand gestures from american sign language (ASL) are used for an experiment and the result shows more than 90% recognition accuracy. For fine movements, a rotating plaster model is measured with 10° step. An average recognition accuracy is also above 90%.

Original languageEnglish
Article number7874149
Pages (from-to)2975-2976
Number of pages2
JournalIEEE Sensors Journal
Volume17
Issue number10
DOIs
Publication statusPublished - 2017 May 15

Fingerprint

Gesture recognition
impulses
waveforms
Neural networks
Plaster
sensors
Sensors
Ultra-wideband (UWB)
plasters
Learning systems
machine learning
broadband
Experiments

All Science Journal Classification (ASJC) codes

  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

Kim, Seo Yul ; Han, Hong Gul ; Kim, Jin Woo ; Lee, Sanghoon ; Kim, Tae Wook. / A hand gesture recognition sensor using reflected impulses. In: IEEE Sensors Journal. 2017 ; Vol. 17, No. 10. pp. 2975-2976.
@article{a75fbccd00884608940d67b9d98ce128,
title = "A hand gesture recognition sensor using reflected impulses",
abstract = "This paper introduces a hand gesture recognition sensor using ultra-wideband impulse signals, which are reflected from a hand. The reflected waveforms in time domain are determined by the reflection surface of a target. Thus every gesture has its own reflected waveform. Thus we propose to use machine learning, such as convolutional neural network (CNN) for the gesture classification. The CNN extracts its own feature and constructs classification model then classifies the reflected waveforms. Six hand gestures from american sign language (ASL) are used for an experiment and the result shows more than 90{\%} recognition accuracy. For fine movements, a rotating plaster model is measured with 10° step. An average recognition accuracy is also above 90{\%}.",
author = "Kim, {Seo Yul} and Han, {Hong Gul} and Kim, {Jin Woo} and Sanghoon Lee and Kim, {Tae Wook}",
year = "2017",
month = "5",
day = "15",
doi = "10.1109/JSEN.2017.2679220",
language = "English",
volume = "17",
pages = "2975--2976",
journal = "IEEE Sensors Journal",
issn = "1530-437X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "10",

}

A hand gesture recognition sensor using reflected impulses. / Kim, Seo Yul; Han, Hong Gul; Kim, Jin Woo; Lee, Sanghoon; Kim, Tae Wook.

In: IEEE Sensors Journal, Vol. 17, No. 10, 7874149, 15.05.2017, p. 2975-2976.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A hand gesture recognition sensor using reflected impulses

AU - Kim, Seo Yul

AU - Han, Hong Gul

AU - Kim, Jin Woo

AU - Lee, Sanghoon

AU - Kim, Tae Wook

PY - 2017/5/15

Y1 - 2017/5/15

N2 - This paper introduces a hand gesture recognition sensor using ultra-wideband impulse signals, which are reflected from a hand. The reflected waveforms in time domain are determined by the reflection surface of a target. Thus every gesture has its own reflected waveform. Thus we propose to use machine learning, such as convolutional neural network (CNN) for the gesture classification. The CNN extracts its own feature and constructs classification model then classifies the reflected waveforms. Six hand gestures from american sign language (ASL) are used for an experiment and the result shows more than 90% recognition accuracy. For fine movements, a rotating plaster model is measured with 10° step. An average recognition accuracy is also above 90%.

AB - This paper introduces a hand gesture recognition sensor using ultra-wideband impulse signals, which are reflected from a hand. The reflected waveforms in time domain are determined by the reflection surface of a target. Thus every gesture has its own reflected waveform. Thus we propose to use machine learning, such as convolutional neural network (CNN) for the gesture classification. The CNN extracts its own feature and constructs classification model then classifies the reflected waveforms. Six hand gestures from american sign language (ASL) are used for an experiment and the result shows more than 90% recognition accuracy. For fine movements, a rotating plaster model is measured with 10° step. An average recognition accuracy is also above 90%.

UR - http://www.scopus.com/inward/record.url?scp=85018359440&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018359440&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2017.2679220

DO - 10.1109/JSEN.2017.2679220

M3 - Article

AN - SCOPUS:85018359440

VL - 17

SP - 2975

EP - 2976

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

SN - 1530-437X

IS - 10

M1 - 7874149

ER -