Geodesic
Construction of robust features for detection and classification of objects
Informacionnye tehnologii i vyčislitelnye sistemy, no. 1 (2014), pp. 53-60.

Voir la notice de l'article provenant de la source Math-Net.Ru

The paper describes a new class of feature for object detection and classification in images. These features are shown to be robust to significant illumination changes. The performance of the proposed method is studied on the modified Viola-Jones algorithm as applied to vehicle axle detection and embossed number recognition tasks.
Keywords: computer vision, object detection, robust features, Viola-Jones algorithm. 
@article{ITVS_2014_1_a5,
     author = {S. A. Gladilin and A. A. Kotov and D. P. Nikolaev and S. A. Usilin},
     title = {Construction of robust features  for detection and classification of objects},
     journal = {Informacionnye tehnologii i vy\v{c}islitelnye sistemy},
     pages = {53--60},
     publisher = {mathdoc},
     number = {1},
     year = {2014},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/ITVS_2014_1_a5/}
}
TY  - JOUR
AU  - S. A. Gladilin
AU  - A. A. Kotov
AU  - D. P. Nikolaev
AU  - S. A. Usilin
TI  - Construction of robust features  for detection and classification of objects
JO  - Informacionnye tehnologii i vyčislitelnye sistemy
PY  - 2014
SP  - 53
EP  - 60
IS  - 1
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/ITVS_2014_1_a5/
LA  - ru
ID  - ITVS_2014_1_a5
ER  - 
%0 Journal Article
%A S. A. Gladilin
%A A. A. Kotov
%A D. P. Nikolaev
%A S. A. Usilin
%T Construction of robust features  for detection and classification of objects
%J Informacionnye tehnologii i vyčislitelnye sistemy
%D 2014
%P 53-60
%N 1
%I mathdoc
%U http://geodesic.mathdoc.fr/item/ITVS_2014_1_a5/
%G ru
%F ITVS_2014_1_a5
S. A. Gladilin; A. A. Kotov; D. P. Nikolaev; S. A. Usilin. Construction of robust features  for detection and classification of objects. Informacionnye tehnologii i vyčislitelnye sistemy, no. 1 (2014), pp. 53-60. http://geodesic.mathdoc.fr/item/ITVS_2014_1_a5/