Using virtual data for training deep model for hand gesture recognition

Deep learning has shown real promise for the classification efficiency for hand gesture recognition problems. In this paper, the authors present experimental results for a deeply-trained model for hand gesture recognition through the use of hand images. The authors have trained two deep convolutiona...

Deskribapen osoa

Gorde:

Xehetasun bibliografikoak
Egile Nagusiak:	Nikolaev, E. I., Николаев, Е. И., Dvoryaninov, P. V., Дворянинов, П. В., Lensky, Y. Y., Ленский, Я. Ю., Drozdovsky, N. S., Дроздовский, Н. С.
Formatua:	Статья
Hizkuntza:	English
Argitaratua:	Institute of Physics Publishing 2018
Gaiak:	Deep neural networks E-learning Information system Network architecture Neural networks Palmprint recognition
Sarrera elektronikoa:	https://www.scopus.com/record/display.uri?eid=2-s2.0-85047744167&origin=resultslist&sort=plf-f&src=s&nlo=1&nlr=20&nls=afprfnm-t&affilName=nort+caucas+fed+univ&sid=e8b1e6bfede530617390e7deae26e9c5&sot=afnl&sdt=afsp&sl=53&s=%28AF-ID%28%22North+Caucasus+Federal+University%22+60070541%29%29&relpos=3&citeCnt=0&searchTerm= https://dspace.ncfu.ru:443/handle/20.500.12258/494
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!

id	ir-20.500.12258-494
record_format	dspace
spelling	ir-20.500.12258-4942020-07-10T08:15:59Z Using virtual data for training deep model for hand gesture recognition Nikolaev, E. I. Николаев, Е. И. Dvoryaninov, P. V. Дворянинов, П. В. Lensky, Y. Y. Ленский, Я. Ю. Drozdovsky, N. S. Дроздовский, Н. С. Deep neural networks E-learning Information system Network architecture Neural networks Palmprint recognition Deep learning has shown real promise for the classification efficiency for hand gesture recognition problems. In this paper, the authors present experimental results for a deeply-trained model for hand gesture recognition through the use of hand images. The authors have trained two deep convolutional neural networks. The first architecture produces the hand position as a 2D-vector by input hand image. The second one predicts the hand gesture class for the input image. The first proposed architecture produces state of the art results with an accuracy rate of 89% and the second architecture with split input produces accuracy rate of 85.2%. In this paper, the authors also propose using virtual data for training a supervised deep model. Such technique is aimed to avoid using original labelled images in the training process. The interest of this method in data preparation is motivated by the need to overcome one of the main challenges of deep supervised learning: using a copious amount of labelled data during training 2018-06-07T08:58:55Z 2018-06-07T08:58:55Z 2018 Статья Nikolaev, E.I., Dvoryaninov, P.V., Lensky, Y.Y., Drozdovsky, N.S. Using virtual data for training deep model for hand gesture recognition // Journal of Physics: Conference Series. - 2018. - Volume 1015. - Issue 4. - статья № 042045 https://www.scopus.com/record/display.uri?eid=2-s2.0-85047744167&origin=resultslist&sort=plf-f&src=s&nlo=1&nlr=20&nls=afprfnm-t&affilName=nort+caucas+fed+univ&sid=e8b1e6bfede530617390e7deae26e9c5&sot=afnl&sdt=afsp&sl=53&s=%28AF-ID%28%22North+Caucasus+Federal+University%22+60070541%29%29&relpos=3&citeCnt=0&searchTerm= https://dspace.ncfu.ru:443/handle/20.500.12258/494 en Journal of Physics: Conference Series application/pdf application/pdf Institute of Physics Publishing
institution	СКФУ
collection	Репозиторий
language	English
topic	Deep neural networks E-learning Information system Network architecture Neural networks Palmprint recognition
spellingShingle	Deep neural networks E-learning Information system Network architecture Neural networks Palmprint recognition Nikolaev, E. I. Николаев, Е. И. Dvoryaninov, P. V. Дворянинов, П. В. Lensky, Y. Y. Ленский, Я. Ю. Drozdovsky, N. S. Дроздовский, Н. С. Using virtual data for training deep model for hand gesture recognition
description	Deep learning has shown real promise for the classification efficiency for hand gesture recognition problems. In this paper, the authors present experimental results for a deeply-trained model for hand gesture recognition through the use of hand images. The authors have trained two deep convolutional neural networks. The first architecture produces the hand position as a 2D-vector by input hand image. The second one predicts the hand gesture class for the input image. The first proposed architecture produces state of the art results with an accuracy rate of 89% and the second architecture with split input produces accuracy rate of 85.2%. In this paper, the authors also propose using virtual data for training a supervised deep model. Such technique is aimed to avoid using original labelled images in the training process. The interest of this method in data preparation is motivated by the need to overcome one of the main challenges of deep supervised learning: using a copious amount of labelled data during training
format	Статья
author	Nikolaev, E. I. Николаев, Е. И. Dvoryaninov, P. V. Дворянинов, П. В. Lensky, Y. Y. Ленский, Я. Ю. Drozdovsky, N. S. Дроздовский, Н. С.
author_facet	Nikolaev, E. I. Николаев, Е. И. Dvoryaninov, P. V. Дворянинов, П. В. Lensky, Y. Y. Ленский, Я. Ю. Drozdovsky, N. S. Дроздовский, Н. С.
author_sort	Nikolaev, E. I.
title	Using virtual data for training deep model for hand gesture recognition
title_short	Using virtual data for training deep model for hand gesture recognition
title_full	Using virtual data for training deep model for hand gesture recognition
title_fullStr	Using virtual data for training deep model for hand gesture recognition
title_full_unstemmed	Using virtual data for training deep model for hand gesture recognition
title_sort	using virtual data for training deep model for hand gesture recognition
publisher	Institute of Physics Publishing
publishDate	2018
url	https://www.scopus.com/record/display.uri?eid=2-s2.0-85047744167&origin=resultslist&sort=plf-f&src=s&nlo=1&nlr=20&nls=afprfnm-t&affilName=nort+caucas+fed+univ&sid=e8b1e6bfede530617390e7deae26e9c5&sot=afnl&sdt=afsp&sl=53&s=%28AF-ID%28%22North+Caucasus+Federal+University%22+60070541%29%29&relpos=3&citeCnt=0&searchTerm= https://dspace.ncfu.ru:443/handle/20.500.12258/494
work_keys_str_mv	AT nikolaevei usingvirtualdatafortrainingdeepmodelforhandgesturerecognition AT nikolaevei usingvirtualdatafortrainingdeepmodelforhandgesturerecognition AT dvoryaninovpv usingvirtualdatafortrainingdeepmodelforhandgesturerecognition AT dvorâninovpv usingvirtualdatafortrainingdeepmodelforhandgesturerecognition AT lenskyyy usingvirtualdatafortrainingdeepmodelforhandgesturerecognition AT lenskijâû usingvirtualdatafortrainingdeepmodelforhandgesturerecognition AT drozdovskyns usingvirtualdatafortrainingdeepmodelforhandgesturerecognition AT drozdovskijns usingvirtualdatafortrainingdeepmodelforhandgesturerecognition
_version_	1760600315507245056

Using virtual data for training deep model for hand gesture recognition

Antzeko izenburuak