Menu
Publications
2024
2023
2022
2021
2020
2019
2018
2017
2016
2015
2014
2013
2012
2011
2010
2009
2008
2007
2006
2005
2004
2003
2002
2001
Editor-in-Chief
Nikiforov
Vladimir O.
D.Sc., Prof.
Partners
FEATURE DETECTORS IN THE VIOLA-JONES METHOD ON THE BASIS OF FINITE AUTOMATA
Read the full article ';
Abstract
Modification of the Viola-Jones method, one of the most effective methods for image classification, is
considered. Feature detectors built on the base of finite automata are used instead of the rectangular features detectors in the proposed modification. The use of finite automata allows for reducing the number of levels in the cascade and the number of detectors on each level due to the fact that the automata-based detector can detect more complicated features than simple rectangles.
Keywords:
images classification, finite automata, machine learning