Generalized image compression algorithms for arbitrarily-shaped fragments and their implementation using artificial neural networks
A.A. Sirota, M.A. Dryuchenko

 

Voronezh State University

Full text of article: Russian language.

 PDF

Abstract:
A problem of image compression in arbitrarily-shaped fragments is considered. A theoretical substantiation of hetero- and auto-associative compressive transformations on random fields fragments using neural networks is given.

Keywords:
data compression, neural networks, image processing, digital watermarks.

Citation:
Sirota AA, Dryuchenko MA. Generalized image compression algorithms for arbitrarily-shaped fragments and their implementation using artificial neural networks. Computer Optics 2015; 39(5): 751-61. DOI: 10.18287/0134-2452-2015-39-5-751-761.

References:

  1. Vatolin D, Ratushnyak A, Smirnov M, Yukin V. Data compression methods. Archive programs organization, image and video compression [In Russian]. Moscow: “Dialog-Mifi” Publisher; 2002.
  2. Nazarov LE. RSA and scanned images of the Earth surface compression using artificial neural networks [In Russian]. Earth Research From Space 1999; 5: 44-50.
  3. Haykin S. Neural Networks: A Comprehensive Foundation (second edition). Prentice Hall, NJ, USA: 1999. ISBN: 0-13-273350-1.
  4. Popov VG, Sirota AA. Properties of autoassociative two-layer linear neural network weights convergence in the construction of contraction mappings of random vectors [In Russian]. Neurocomputers 2009; 5: 3-11.
  5. Conahovich GF, Puzirenko AYu. Computer steganography. Theory and practice [In Russian]. Moscow: “MK-Press” Publisher; 2006. ISBN: 966-8806-06-9.
  6. Glumov NI, Mitekin VA. A new semi-fragile watermarking algorithm for image authentication and information hiding [In Russian]. Computer Optics 2011; 35(2): 262-7.
  7. Ossowski S. Neural networks for information processing [In Polish]. Of. Ed. Pol. Warsaw, Poland 2000.
  8. Algazinov EK, Sirota AA. Analysis and computer modeling of information processes and systems Proc. manual for high schools [In Russian]. Moscow: “Dialog-Mifi” Publisher; 2009.
  9. Sirota AA, Mitrofanova EYu. Convergence of weights of a two-layer linear neural network at construction of optimum linear estimations of casual vectors [In Russian]. Neurocomputers: Design and Applications 2011; 7: 39-48.
  10. Fukunaga K. Introduction to statistical pattern recognition (second edition). San Diego: Academic Press Professional, Inc; 1990.
  11. Rao SR. Linear Statistical Inference and its Applications (second editon). John Wiley & Sons, Inc; 2002. DOI: 10.1002/9780470316436.
  12. A set of test images “Kodak Lossless True Color Image Suite”. Source: áhttp://r0k.us/graphics/kodak/ñ.
  13. A set of test images “TESTIMAGES”. Source: áhttp://testimages.tecnick.comñ.
  14. Sirota AA, Dryuchenko MA, Mitrofanova EYu. Neural network functional models and algorithms for information conversion in order to create digital watermarks [In Russian]. Radioelectronics and Communications Systems 2015; 1(1): 3-16. DOI: 10.3103/S073527271501001X.
  15. Sirota AA, Dryuchenko MA, Mitrofanova EYu. Analysis of resistance to the typical steganography attacks of the digital watermarking algorithms based on universal contraction mapping [In Russian]. In Proceedings of the International scientific conference “Science and technology of the XXI century (C&T 2015)”, Voronezh 2015; 57-68.
© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20