Geodesic
Selecting optimal strategy for combining per-frame character recognition results in video stream
Informacionnye tehnologii i vyčislitelnye sistemy, no. 3 (2017), pp. 45-55

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

This paper considers a problem of combining classification results from several observations of the same object. The task is seen as a case of collective decision making by a group of experts with estimated competence levels. Precision of different classification result combination methods is analyzed with different input data model, having per-frame character recognition results combination problem in video stream as an example. Experiments show that the strategy which selects a single most competent expert performs better with input data model without any non-relevant observations (in the context of character recognition in video stream — without characters location and segmentation errors). At the same time experiments show that strategies which combine several most competent experts using product rule or voting procedure outperform single-expect strategy with input data containing non-relevant observations.
Keywords: decision theory, pattern recognition, recognition in video stream
Mots-clés : ensemble classifiers. 
@article{ITVS_2017_3_a4,
     author = {K. B. Bulatov},
     title = {Selecting optimal strategy for combining per-frame character recognition results in video stream},
     journal = {Informacionnye tehnologii i vy\v{c}islitelnye sistemy},
     pages = {45--55},
     publisher = {mathdoc},
     number = {3},
     year = {2017},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/ITVS_2017_3_a4/}
}
TY  - JOUR
AU  - K. B. Bulatov
TI  - Selecting optimal strategy for combining per-frame character recognition results in video stream
JO  - Informacionnye tehnologii i vyčislitelnye sistemy
PY  - 2017
SP  - 45
EP  - 55
IS  - 3
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/ITVS_2017_3_a4/
LA  - ru
ID  - ITVS_2017_3_a4
ER  - 
%0 Journal Article
%A K. B. Bulatov
%T Selecting optimal strategy for combining per-frame character recognition results in video stream
%J Informacionnye tehnologii i vyčislitelnye sistemy
%D 2017
%P 45-55
%N 3
%I mathdoc
%U http://geodesic.mathdoc.fr/item/ITVS_2017_3_a4/
%G ru
%F ITVS_2017_3_a4
K. B. Bulatov. Selecting optimal strategy for combining per-frame character recognition results in video stream. Informacionnye tehnologii i vyčislitelnye sistemy, no. 3 (2017), pp. 45-55. http://geodesic.mathdoc.fr/item/ITVS_2017_3_a4/