Please use this identifier to cite or link to this item:
https://dspace.ncfu.ru/handle/20.500.12258/494
Title: | Using virtual data for training deep model for hand gesture recognition |
Authors: | Nikolaev, E. I. Николаев, Е. И. Dvoryaninov, P. V. Дворянинов, П. В. Lensky, Y. Y. Ленский, Я. Ю. Drozdovsky, N. S. Дроздовский, Н. С. |
Keywords: | Deep neural networks;E-learning;Information system;Network architecture;Neural networks;Palmprint recognition |
Issue Date: | 2018 |
Publisher: | Institute of Physics Publishing |
Citation: | 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 |
Series/Report no.: | Journal of Physics: Conference Series |
Abstract: | 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 |
URI: | 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 |
Appears in Collections: | Статьи, проиндексированные в SCOPUS, WOS |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
scopusresults (62).pdf Restricted Access | 61.47 kB | Adobe PDF | View/Open | |
WoS 313 .pdf Restricted Access | 472.24 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.