Performance analysis of human gesture recognition techniques

Mansi Goyal, Bhavya Shahi, K. V. Prema, N. V.S.Subba Reddy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Today, a lot of research is being done in the area of human gesture recognition due to its various uses such as traffic management, surveillance, healthcare management etc. In this paper the performance of different filters, namely Gabor and Canny for edge detection during preprocessing of image sequences has been studied. Subsequently, the preprocessed images are used for human gesture recognition. The focus is mainly on two gestures-walk and bend. The different classifiers that are used are KNN (K-Nearest Neighbour), NN (Nearest Neighbour) and SVM (Support Vector Machine). The results are then compared for different training dataset sizes for each model. It is found that in general, the Gabor filter gave better results than the Canny edge detection method.

Original languageEnglish
Title of host publicationRTEICT 2017 - 2nd IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages111-115
Number of pages5
Volume2018-January
ISBN (Electronic)9781509037049
DOIs
Publication statusPublished - 12-01-2018
Event2nd IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2017 - Bangalore, India
Duration: 19-05-201720-05-2017

Conference

Conference2nd IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2017
CountryIndia
CityBangalore
Period19-05-1720-05-17

Fingerprint

Gabor filters
Gesture recognition
Gesture Recognition
Gabor Filter
edge detection
Edge Detection
Edge detection
Performance Analysis
Nearest Neighbor
Traffic Management
preprocessing
Gesture
surveillance
Image Sequence
classifiers
Walk
Surveillance
Healthcare
traffic
performance

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications
  • Media Technology
  • Control and Optimization
  • Instrumentation
  • Transportation
  • Communication

Cite this

Goyal, M., Shahi, B., Prema, K. V., & Reddy, N. V. S. S. (2018). Performance analysis of human gesture recognition techniques. In RTEICT 2017 - 2nd IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, Proceedings (Vol. 2018-January, pp. 111-115). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/RTEICT.2017.8256568
Goyal, Mansi ; Shahi, Bhavya ; Prema, K. V. ; Reddy, N. V.S.Subba. / Performance analysis of human gesture recognition techniques. RTEICT 2017 - 2nd IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, Proceedings. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 111-115
@inproceedings{00594a8e9fbd4bc39f74da3a3c729c0f,
title = "Performance analysis of human gesture recognition techniques",
abstract = "Today, a lot of research is being done in the area of human gesture recognition due to its various uses such as traffic management, surveillance, healthcare management etc. In this paper the performance of different filters, namely Gabor and Canny for edge detection during preprocessing of image sequences has been studied. Subsequently, the preprocessed images are used for human gesture recognition. The focus is mainly on two gestures-walk and bend. The different classifiers that are used are KNN (K-Nearest Neighbour), NN (Nearest Neighbour) and SVM (Support Vector Machine). The results are then compared for different training dataset sizes for each model. It is found that in general, the Gabor filter gave better results than the Canny edge detection method.",
author = "Mansi Goyal and Bhavya Shahi and Prema, {K. V.} and Reddy, {N. V.S.Subba}",
year = "2018",
month = "1",
day = "12",
doi = "10.1109/RTEICT.2017.8256568",
language = "English",
volume = "2018-January",
pages = "111--115",
booktitle = "RTEICT 2017 - 2nd IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Goyal, M, Shahi, B, Prema, KV & Reddy, NVSS 2018, Performance analysis of human gesture recognition techniques. in RTEICT 2017 - 2nd IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, Proceedings. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 111-115, 2nd IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2017, Bangalore, India, 19-05-17. https://doi.org/10.1109/RTEICT.2017.8256568

Performance analysis of human gesture recognition techniques. / Goyal, Mansi; Shahi, Bhavya; Prema, K. V.; Reddy, N. V.S.Subba.

RTEICT 2017 - 2nd IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, Proceedings. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 111-115.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Performance analysis of human gesture recognition techniques

AU - Goyal, Mansi

AU - Shahi, Bhavya

AU - Prema, K. V.

AU - Reddy, N. V.S.Subba

PY - 2018/1/12

Y1 - 2018/1/12

N2 - Today, a lot of research is being done in the area of human gesture recognition due to its various uses such as traffic management, surveillance, healthcare management etc. In this paper the performance of different filters, namely Gabor and Canny for edge detection during preprocessing of image sequences has been studied. Subsequently, the preprocessed images are used for human gesture recognition. The focus is mainly on two gestures-walk and bend. The different classifiers that are used are KNN (K-Nearest Neighbour), NN (Nearest Neighbour) and SVM (Support Vector Machine). The results are then compared for different training dataset sizes for each model. It is found that in general, the Gabor filter gave better results than the Canny edge detection method.

AB - Today, a lot of research is being done in the area of human gesture recognition due to its various uses such as traffic management, surveillance, healthcare management etc. In this paper the performance of different filters, namely Gabor and Canny for edge detection during preprocessing of image sequences has been studied. Subsequently, the preprocessed images are used for human gesture recognition. The focus is mainly on two gestures-walk and bend. The different classifiers that are used are KNN (K-Nearest Neighbour), NN (Nearest Neighbour) and SVM (Support Vector Machine). The results are then compared for different training dataset sizes for each model. It is found that in general, the Gabor filter gave better results than the Canny edge detection method.

UR - http://www.scopus.com/inward/record.url?scp=85046279533&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046279533&partnerID=8YFLogxK

U2 - 10.1109/RTEICT.2017.8256568

DO - 10.1109/RTEICT.2017.8256568

M3 - Conference contribution

VL - 2018-January

SP - 111

EP - 115

BT - RTEICT 2017 - 2nd IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Goyal M, Shahi B, Prema KV, Reddy NVSS. Performance analysis of human gesture recognition techniques. In RTEICT 2017 - 2nd IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, Proceedings. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 111-115 https://doi.org/10.1109/RTEICT.2017.8256568