Two-staged algorithm for detecting and rating the object cutouts  on the images in case of additive noise and deformed distortions
Al.A.Sirota, Al.I. Solomatin, E.V. Voronova

Voronezh State University

Full text of article: Russian language.

Abstract:
In this paper there is considered a two-staged object detection algorithm on images with random cutout shape and in case of addictive noise presence. On the first stage the local image parts are analyzed using statistically optimal or neural algorithms to detect and estimate the brightness jump parameters. On the second stage the final decision are made about object presence on the image and about its cutout integrity by analyzing the local parts initial processing results using maximum likelihood algorithm There is suggested an algorithm to increase object detection process. This algorithm finds the maximum of likelihood functional by searching a minimal path on the graph by dynamic programming.

Key words: image processing, brightness jump, object recognition, object cutouts selection, neural networks.

References:

  1. Hukkel, M. Statement for Finding Cutouts on the Coded Images / M. Hukkel // Integrated robots. Part 1. – Moscow: Mir, 1973. P.225-240.
  2. Perov, A.I. Sequential Object Cutout Selection Algorithm on the 2Dimentional Digital Images / A.I. Perov, G.G. Sokolov // Radiotechnics. – 1998. – № 7. – P. 83-87.
  3. Sirota, A.A. The Brightness Jump Detection and Estimation for the Object Cutout Analysis Task / A.A. Sirota, A.I. Solomatin // Optoelectronics, Instrumentation and Data Processing. – 2009. – №5. – P. 59-69.
  4. Trifonov, A.P. Joint Discrimination of Signals and Estimation of their Parameters against an Interference Background / A.P. Trifonov, Yu.S. Shinakov – Moscow: Radio i svyaz,, 1986. – 264 p.
  5. Osowski, S. Neural Networks for The Information Processing / S. Osowski – Moscow: Finansy i statistika, 2002. – 344 p.
  6. Cormen, T. Introduction to Algorithms, Second Edition / T. Cormen, Ch. Leiserson, R. Rivest – The MIT Press 2001. – 1184 p.
  7. Sirota, A.A. Neural Algorithm for Distorted Object Images Modeling / A.A. Sirota, E.V. Voronova // Computer science: problems, methodology, technology: 9th methodological conference materials, V. 2 – Voronezh: Voronezh state university publisher. – 2009. – P. 333-338.

© 2009, ИСОИ РАН
Россия, 443001, Самара, ул. Молодогвардейская, 151; электронная почта: ko@smr.ru ; тел: +7 (846 2) 332-56-22, факс: +7 (846 2) 332-56-20