СROSS PLATFORM TOOLS FOR MODELING AND RECOGNITION OF THE FINGERSPELLING ALPHABET OF GESTURE LANGUAGE

Serhii Kondratiuk


Taras Shevchenko National University of Kyiv (Ukraine)
http://orcid.org/0000-0002-5048-2576

Iurii Krak

krak@univ.kiev.ua
1Taras Shevchenko National University of Kyiv, 2Glushkov Institute of Cybernetics of NAS of Ukraine (Ukraine)
http://orcid.org/0000-0002-8043-0785

Waldemar Wójcik


Lublin Univeristy of Technology, Institute of Electronics and Computer Science (Poland)
http://orcid.org/0000-0002-0843-8053

Abstract

A solution for the problems of the finger spelling alphabet of gesture language modelling and recognition based on cross-platform technologies is proposed. Modelling and recognition performance can be flexible and adjusted, based on the hardware it operates or based on the availability of an internet connection. The proposed approach tunes the complexity of the 3D hand model based on the CPU type, amount of available memory and internet connection speed. Sign recognition is also performed using cross-platform technologies and the tradeoff in model size and performance can be adjusted.  the methods of convolutional neural networks are used as tools for gestures of alphabet recognition. For the gesture recognition experiment, a dataset of 50,000 images was collected, with 50 different hands recorded, with almost 1,000 images per each person. The experimental researches demonstrated the effectiveness of proposed approaches.


Keywords:

cross platform, sign language, fingerspelling alphabet, 3D modeling, Convolutional Neural Networks

Apple Touchless Gesture System for iDevices http://www.patentlyapple.com/patently-apple/2014/12/apple-invents-a-highly-advanced-air-gesturing-system-for-future-idevices-and-beyond.html (available 15.05.2019).
  Google Scholar

ASL Sign language dictionary http://www.signasl.org/sign/model (available 15.05.2019).
  Google Scholar

Howard A.G., Wang W.: MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications https://arxiv.org/pdf/1704.04861.pdf (available 15.05.2019).
  Google Scholar

Khan R.Z., Ibraheem N.A., Meghanathan N., et al.: Comparative study of hand gesture recognition system. SIPM, FCST, ITCA, WSE, ACSIT, CS & IT 06/2012, 203–213.
  Google Scholar

Krak I., Kondratiuk S.: Cross-platform software for the development of sign communication system: Dactyl language modelling, Proceedings of the 12th International Scientific and Technical Conference on Computer Sciences and Information Technologies, CSIT 1/2017, 167–170 [DOI: 10.1109/STC-CSIT.2017.8098760].
  Google Scholar

Krizhevsky I. Sutskever, Hinton G.E.: Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 2012, 1097–1105.
  Google Scholar

Kryvonos I.G., Krak I.V., Barchukova Y., Trotsenko B.A.: Human hand motion parametrization for dactylemes modeling. Journal of Automation and Information Sciences 43(12)/2011, 1–11.
  Google Scholar

Kryvonos I.G., Krak I.V., Barmak O.V., Shkilniuk D.V.: Construction and identification of elements of sign communication. Cybernetics and Systems Analysis 49(2)/2013, 163–172.
  Google Scholar

Kryvonos I.G., Krak I.V.: Modeling human hand movements, facial expressions, and articulation to synthesize and visualize gesture information. Cybernetics and Systems Analysis 47(4)/2011, 501–505.
  Google Scholar

Mell P., Grance T.: The NIST Definition of Cloud Computing (Technical report). National Institute of Standards and Technology: U.S. Department of Commerce, 2011 [DOI:10.6028/NIST.SP.800-145].
  Google Scholar

Neff M., Kipp M., Albrecht I., Seidel H.P.: Gesture Modeling and Animation by Imitation. MPI–I 4/2006.
  Google Scholar

Ong E.I., et al. : Sign language recognition using sequential pattern trees. Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 2012, 2200–2207.
  Google Scholar

Raheja J.: Android based portable hand sign recognition system. 2015 [DOI: 10.15579/gcsr.vol3.ch1].
  Google Scholar

Shapiro A., Chu D., Allen B., Faloutsos P.: Dynamic Controller Toolkit, 2005 http://www.arishapiro.com/Sandbox07_DynamicToolkit.pdf (available 15.05.2019).
  Google Scholar

Smith J., Navi R.: The Architecture of Virtual Machines. Computer. IEEE Computer Society 38(5)/2005, 32–38.
  Google Scholar

Tensorflow framework documentation https://www.tensorflow.org/api/ (available 15.05.2019).
  Google Scholar

The Linux Information Project, Cross-platform Definition.
  Google Scholar

Unity3D framework https://unity3d.com/ (available 15.05.2019).
  Google Scholar

YAML – The Official YAML Web Site http://yaml.org/ (available 15.05.2019).
  Google Scholar

Download


Published
2019-06-21

Cited by

Kondratiuk, S., Krak, I., & Wójcik, W. (2019). СROSS PLATFORM TOOLS FOR MODELING AND RECOGNITION OF THE FINGERSPELLING ALPHABET OF GESTURE LANGUAGE. Informatyka, Automatyka, Pomiary W Gospodarce I Ochronie Środowiska, 9(2), 24–27. https://doi.org/10.5604/01.3001.0013.2542

Authors

Serhii Kondratiuk 

Taras Shevchenko National University of Kyiv Ukraine
http://orcid.org/0000-0002-5048-2576

Authors

Iurii Krak 
krak@univ.kiev.ua
1Taras Shevchenko National University of Kyiv, 2Glushkov Institute of Cybernetics of NAS of Ukraine Ukraine
http://orcid.org/0000-0002-8043-0785

Authors

Waldemar Wójcik 

Lublin Univeristy of Technology, Institute of Electronics and Computer Science Poland
http://orcid.org/0000-0002-0843-8053

Statistics

Abstract views: 336
PDF downloads: 179


Most read articles by the same author(s)

1 2 > >>