(38-4) 35 * << * >> * Russian * English * Content * All Issues

Near-duplicate image recognition based on the rank distribution of the brightness clusters cardinality
V.B. Nemirovskiy, A.K. Stoyanov

 

Institute of Cybernetics, National Research Tomsk Polytechnic University

PDF, 1280 kB

Full text of article: Russian language.

DOI: 10.18287/0134-2452-2014-38-4-811-817

Pages: 811-817.

Abstract:
In this paper the usage of multi-step segmentation for near-duplicate image recognition is investigated. The clustering of image pixels brightness is used for segmentation. The clustering is realized by means of a recurrent neural network.
The search pattern based on the rank distributions of the brightness clusters cardinality is suggested. Experimental results on the near-duplicate image recognition based on the application of the suggested search pattern are given. It is shown that the use of a multi-step segmentation and rank distributions of the brightness clusters cardinality allows one to successfully recognize the duplicates, which are received by a considerable visual distortion of the original image or by the change of image scale.

Key words:
image, pixel, point mapping, recurrent neural network, clustering, segmentation, image recognition, ranking distribution.

Citation:
Nemirovskiy VB, Stoyanov AK. Near-duplicate image recognition based on the rank distribution of the brightness clusters cardinality. Computer Optics 2014; 38(4): 811-817. DOI: 10.18287/0134-2452-2014-38-4-811-817.

References:

  1. Shapiro, L.G. Computer vision / L.G. Shapiro, G.C. Stockman. – Prentice Hall, 2001 – 580 p.
  2. Pimenov, V.Iu. Near-Duplicate Image Detection with Local Interest Point Extraction / V.Iu. Pimenov // Trudy ROMIP 2007-2008 (Proc. ROMIP 2007-2008). – Saint Petersburg.: NU TCSI. – 2008. – P. 145-158. – (In Russian).
  3. Christlein, V. An Evaluation of Popular Copy-Move Forgery Detection Approaches / V. Christlein, C. Riess, J. Jordan, C. Riess, E. Angelopoulou // IEEE Transactions on information forensics and security. – 2012. – Vol. 7(6). – P. 1841-1854.
  4. Farid, H. Image Forgery Detection / H. Farid // IEEE Signal processing magazine. – 2009. – P. 16-25.
  5. Sridevi, M. Comparative Study of Image forgery and Copy-move Techniques / M. Sridevi, C. Mala, S. Sanyam. – Proceedings of the Second International Conference on Computer Science, Engineering and Applications (ICCSEA 2012). – New Delhi, India, 2012. – P. 715-723.
  6. Glumov, N.I. The Algorithm for Copy-move Detection on Digital Images / N.I. Glumov, A.V. Kuznetsov, V.V. Myasnikov // Computer Optics. – 2013. – V. 37(3). – P. 360-368.
  7. Kuznetcov, A.V. Efficient Linear Local Features Based Copy-Move Detection Algorithm / A.V. Kuznetsov, V.V. My­asnikov / Computer Optics. – 2013. – V. 37(4). – P. 489-496.
  8. Melnichenko, A. Image retrieval methods by the visual similarity and the detection of near-duplicate image. / A. Melnichenko, A. Goncharov // Trudy ROMIP 2009 (Proceedings ROMIP 2009). – Saint Petersburg.: NU TCSI. –2009 – P. 108-121. – (In Russian).
  9. Baigarova, N.S. Various Questions Connected with Content-Based Search of Visual Information and Videoinformation [Electronical Resource] / N.S. Baigarova, Iu.A. Bukh­shtab, N.N. Evteeva, D.A. Koriagin // Preprint, Inst. Appl. Math., the Russian Academy of Science]. – Available at: http://www.keldysh.ru/papers/2002/prep78/prep2002_78.html (accessed 26 May 2014). – (In Russian).
  10. Kotov, V.V. Use of histogram estimates in recognition tasks / V.V. Kotov // Uspehi sovremennogo estestvoznaniia. – 2004. – N 4. – P. 40-42. – Available at: http://www.rae.ru/use/?section=content&op=show_article&article_id=7780895 (accessed 12 March 2014). – (In Russian).
  11. Nemirovsky, V.B. Image Segmentation by Recurrent Neural Network / V.B. Nemirovsky, A.K. Stoyanov // Bulletin of the Tomsk Polytechnic University. – 2012. – Vol. 321(5). – P. 205-210.
  12. Nemirovsky, V.B. Multi-Step Segmentation of Images by Means of a Recurrent Neural Network / V.B. Nemirovsky, A.K. Stoyanov // 7th International Forum on Strategic Technology (IFOST – 2012): Proceedings: in 2 vol., Tomsk, September 18-21, 2012. – Tomsk: TPU Press, 2012. – Vol. 1. – P. 557-560.
  13. Stoyanov, A.K. Distribution of two-dimensional areas in Euclidean space / A.K. Stoyanov // Bulletin of the Tomsk Polytechnic University. – 2009. – Vol. 315(5). – P. 144-149. – (In Russian).
  14. Kudrin, B.I. Mathematics of cenoses: species, the rank of species, ranking in the parameter hyperbolic H-distribution laws Lotka, Zipf, Pareto, and Mandelbrot / B.I. Kudrin // “Cenologicheskie issledovaniia”, Issue 25. – Moscow: “Centr sistemnykh issledovanii” Publisher, 2004. – 248 p. – (In Russian).
  15. Photoblog about fashion and style 2012-2014 [Electronical Resource]. – Available at: http://mens.by/style/shine/470-mustache-sideburns (26 May 2014).
  16. Children's Portraits in Black and White [Electronical Resource]. – Available at: http://www.liveinternet.ru / users/katiava/post285466584 (accessed 26 May 2014).
  17. Black and White wallpaper [Electronical Resource]. – Available at: http://oboiny.ru/cherno-belye-oboi-dlya-rabo­chego-stola (accessed 26 May 2014).
  18. Dalal, N. Histograms of Oriented Gradients for Human Detection / N. Dalal, W. Triggs // IEEE Computer Society Conference on Computer Vision and Pattern Recognition CVPR05. – 2005. – Vol. 1(3). – P. 886-893.
  19. Nemirovsky, V.B. Segmentation of color Images of naturel Objects by Recurrent Neural Network / V.B. Nemirovsky, A.K. Stoyanov // Bulletin of the Tomsk Polytechnic University. – 2013. – Vol. 323(1). – P. 212-216. – (In Russian).
© 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