The search algorithm for image in databases
Desyatnikov I.E., Utrobin V.A.

Full text of article: Russian language.

Abstract:
This paper briefly discusses the existing methods for image lookup in video databases. A new method of image lookup is suggested; it is based upon active perception theory which is being developed at the Computing Systems and Technologies department of NSTU. Its key advantage is its low computing cost and thus high performance. According to the method, every image is represented as a 15-dimensional vector. Not only the original images are matched; the algorithm also handles noisy, edited, corrupted, rotated images. An algorithm for matching similar images is proposed as well. Its reliability and performance allow it to compete with existing commercially available image lookup technologies.

Key words:
image retrieval, active perception theor.

References:

  1. Vasil'eva, N. Establishing a correspondence between low-level features and semantics of static images / N. Vasil'eva, B. Novikov. – Proceedings of the 7th Russian Scientific Conference “Digital Libraries: Advanced methods and Technologies, Digital Collections”. – Yaroslavl, 2005. – (in Russian).
  2. Swain, M.J. Color Indexing / M.J. Swain, D.H. Ballard // International Journal of Computer Vision. – 1991. – Vol. 7(1). – P. 11-32.
  3. Tamura, H. Textural features corresponding to visual perception / H. Tamura, S. Mori, T. Yamawaki // IEEE Transactions on Systems, Man, and Cybernetics. – 1978. – Vol. 8(6). – P. 460-473.
  4. Manjunath, B.S. Texture features for browsing and retrieval of image data / B.S. Manjunath, W.Y. Ma // IEEE Transactions on Pattern Analysis and Machine Intelligence. – 1996 – Vol. 18 (8). – P. 837-842.
  5. Zhang, D. Content-Based Shape Retrieval Using Different Shape Descriptors / D. Zhang, G. Lu // A Comparative Study, In IEEE International Conference on Multimedia and Expo. – 2001. – P. 289-293.
  6. Rubner, Y. A Metric for Distributions with Applications to Image Databases / Y. Rubner, C. Tomasi // In Proceedings of the Sixth International Conference on Computer Vision, IEEE Computer Society. – 1998. – P. 59.
  7. Utrobin, V.A. Information models of visual perception for the problems of computer image processing / V.A. Utrobin. – Nizhny Novgorod: “NSTU” Publisher, 2001. – 234 p. – (in Russian).
  8. Utrobin, V.A. Physical interpretation of the elements of the images / V.A. Utrobin // Successes of Physical Sciences. – 2004. – V. 174, N 10. – P. 1089-1104. – (in Russian).
  9. Demidov, V.E. As we can see what we see / V.E. Demidov. – oscow: “Knowledge” Publisher, 1987. – 240 p. – (in Russian).

© 2009, IPSI RAS
Institution of Russian Academy of Sciences, Image Processing Systems Institute of RAS, Russia, 443001, Samara, Molodogvardeyskaya Street 151; E-mail: ko@smr.ru; Phones: +7 (846) 332-56-22, Fax: +7 (846) 332-56-20