Method of Recognition and Indexing of People’s Faces in Videos Using Model of Machine Learning

Kobets, Nataliya and Kovaliuk, Tetiana (2020) Method of Recognition and Indexing of People’s Faces in Videos Using Model of Machine Learning Advances in Intelligent Systems and Computing, 1247. pp. 534-544. ISSN 978-3-030-55505-4; 978-3-030-55506-1

[thumbnail of N_Kobets_T_Kovaliuk_ICCSEEA2020_Method face recognition_FITU.pdf] Text
N_Kobets_T_Kovaliuk_ICCSEEA2020_Method face recognition_FITU.pdf - Accepted Version
Restricted to Repository staff only

Download (534kB) | Request a copy

Abstract

This paper describes a machine learning approach for visual object detection in particular people’s faces. Developed an algorithm based on the Viola-Jones algorithm. Images are used in the integral representation, which allows you to quickly calculate the necessary objects; signs of Haar are used, with the help of which the search for the needed faces and their features; boosting is used to select the most suitable features for the desired object in a given part of the image. Features of implementation of AdaBoost algorithm for solution a problem of construction of the classifiers cascade for effective detection of objects on images are considered in this paper. The algorithm is tested on an image containing several persons. Graphs of dependence of quality of detection on quantity of iterations are received.

Item Type: Article
Additional Information: link to article: https://link.springer.com/book/10.1007/978-3-030-55506-1
Uncontrolled Keywords: Face recognition; Clustering; Viola-Jones algorithm; Adaboos
Subjects: Статті у наукометричних базах > Scopus
Divisions: Факультети > Факультет інформаційних технологій та управління > Кафедра комп'ютерних наук і математики
Depositing User: Наталія Михайлівна Кобець
Date Deposited: 09 Nov 2020 12:42
Last Modified: 14 Nov 2021 22:08
URI: https://elibrary.kubg.edu.ua/id/eprint/32560

Actions (login required)

View Item View Item