(14-15(01)) * << * >> * Russian * English * Content * All Issues

Scheme of logic syntheses of imaging models admitted by efficient recognition operators
I.B. Gurevich

 PDF, 2933 kB

Pages: 133-147.

Full text of article: Russian language.

Abstract:
Within the framework of the Descriptive Approach to image recognition, a class of logical transformations is introduced (the Class of Descriptive Logical Transformations - DLT class), which provide the transition from the original image being the object of analysis / recognition to a formalized description of this image and the solution of the recognition problem based on such description. The process of solving the problem of image recognition includes two main stages:
a) bringing the image to a recognition-friendly form;
b) application of an effective recognition algorithm to the “adjusted” image.
The DLT class includes two types of transformations. The DLT-1 transformations transform the original image into the description specified by the disjunctive normal form. DLT-2 transformations represent the recognition operators of the logical model of Recognition Algorithms
based on the Calculation of Estimates, and provide the recognition process itself. The DLT class has the following important advantages:
a) local and global information reproduced by the image is used in the recognition process;
b) the recognition operators used are computationally efficient;
c) the logical description of the image is stable with respect to large-scale and structural deformations.

Citation:
Gurevich IB. Scheme of logic syntheses of imaging models admitted by efficient recognition operators. Computer Optics 1995; 14-15(1): 133-147.

References:
  1. Gurevich IB. The Descriptive Framework for an Image Recognition Problem. Proceedings of The 6th Scandinavian Conference on Image Analysis Oulu: V.1. Pattern Recognition Society of Finland; 1989; 220-227.
  2. Gurevich IB. Descriptive Technique for Image Description, Representation and Recognition. Pattern Recognition and Image Analysis: Advances in Mathematical Theory and Applications in the USSR; 1991; l (1): 50-53.
  3. Zhuravlev YI, Gurevich IB. Pattern Recognition and Image Recognition // Pattern Recognition and Image Analysis: Advances in Mathematical Theory and Applications in the USSR; 1991; 1(2): 149-181.
  4. Zhuravlev YI. On algebraic approach to solve the problems of recognition and classification. Problems of Cybernetics. Moscow: Nauka; 1978; 33: 5–68 .

© 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