Classification of Images on the Basis
of the Properties of Informative Regions

D. G. Shaposhnikov*, L. N. Podladchikova*, and X. Gao**

* Research Institute of Neurocybernetics, Rostov State University, pr. Stachki 194/1, Rostov-on-Don, 344090 Russia
e-mail: nisms@krinc.ru

** Middlesex University, Bounds Green Road, London, N112NQ UK
e-mail: X.Gao@mdx.ac.uk

Abstract—Algorithms for classification of the images of faces and road signs are presented. Estimation of
facial aspects is based on the determination of mutual geometric relations between the most informative regions
(MIRs). Road sign classification is based on the description of RGB components and color oriented elements.
The correct determination of three facial poses by the cascade method in the automatic detection of the MIRs
[1] was 0.87. The recognition rate for the actual road signs using the color and shape classification algorithm
was 96%.


IAPC Nauka home page | journal home page | top

If you have any problems with this server, contact webmaster@maik.ru.