An Approach to the Determination of Efficient Features and Synthesis of an Optimal Band-Separating Classifier of Dactyl Elements of Sign Language

详细信息    查看全文

• 作者：Iu. V. Krak ; Iu. G. Kryvonos ; O. V. Barmak…
• 关键词：dactyl alphabet of sign language ; recognition ; hyperplane classification
• 刊名：Cybernetics and Systems Analysis
• 出版年：2016
• 出版时间：March 2016
• 年：2016
• 卷：52
• 期：2
• 页码：173-180
• 全文大小：132 KB
• 参考文献：1.Formational Units in Sign Languages, Sign Language Typology, Ser. 3, R. Channon and H. van der Hulst (eds.), Shara Press/Mouton de Gruyter, Nijmegen (Netherlands)-Berlin (2011).
  2.Augmentative and Alternative Communication (AAC), http://​www.​asha.​org/​public/​speech/​disorders/​AAC/​ .
  3.Iu. G. Kryvonos, Iu. V. Krak, O. V. Barmak, and D. V. Shkilniuk, “Construction and identification of elements of sign communication,” Cybernetics and Systems Analysis, 49, No. 2, 163–172 (2013).
  4.Yu. G. Krivonos, Yu. V. Krak, Yu. V. Barchukova, and B. A. Trotsenko, “Human hand motion parametrization for modeling dactylemes,” Journal of Automation and Information Science, 2011, 43, No. 12, 1–11 (2011).
  5.Courses of a Computer Graphics Laboratory [in Russian], http://​courses.​graphicon.​ru .
  6.Ya. A. Furman, A. V. Krevetskii, A. K. Peredreev, et al., Introduction to Contour Analysis [in Russian], Fizmatlit, Moscow (2003).
  7.V. N. Vapnik, Statistical Learning Theory: Adaptive and Learning systems for Signal Processing, Communications, and Control, Wiley, New York (1998).
  8.W. H. Press, S. A. Teukolsky, W. T. Vetterling, and B. P. Flannery, “Support Vector Machines (Sect. 16.5),” in: Numerical Recipes: The Art of Scientific Computing (3rd Ed.), Cambridge University Press, New York (2007), pp. 883–888.
  9.N. F. Kirichenko, “Analytical representation of perturbations of pseudoinverse matrices,” Cybernetics and Systems Analysis, 33, No. 2, 230–238 (1997).
  10.N. F. Kirichenko, Yu. V. Krak, and A. A. Polishchuk, “Pseudoinverse and projection matrices in problems of synthesis of functional transformers,” Cybernetics and Systems Analysis, 40, No. 3, 407–419 (2004).
  11.N. F. Kirichenko and G. I. Kudin, “Analysis and synthesis of signal classification systems by perturbing pseudoinverse and projection operations,” Cybernetics and Systems Analysis, 45, No. 4, 613–622 (2009).
  
• 作者单位：Iu. V. Krak (1) (2)
  Iu. G. Kryvonos (1)
  O. V. Barmak (3)
  A. S. Ternov (1)
  
  1. V. M. Glushkov Institute of Cybernetics, National Academy of Sciences of Ukraine, Kyiv, Ukraine
  2. Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
  3. Khmelnytskyi National University, Khmelnytskyi, Ukraine
  
• 刊物类别：Mathematics and Statistics
• 刊物主题：Mathematics
  Systems Theory and Control
  Artificial Intelligence and Robotics
  Processor Architectures
  Software Engineering, Programming and Operating Systems
  Russian Library of Science
  
• 出版者：Springer New York
• ISSN：1573-8337

文摘

This article presents new results on the solution of the problem of definition of efficient features and synthesis of an optimal band-separating classifier for elements of the dactyl alphabet of deaf sign language. Approaches to the qualitative evaluation of the separability of elements of dactyl alphabet for different feature spaces are considered. An algorithm is proposed for obtaining a hyperplane classifier separating groups of dactylemes in a feature space.