Development of multistage algorithm for text objects recognition in images; Control and Communications (SIBCON)

Development of multistage algorithm for text objects recognition in images; Control and Communications (SIBCON)

Bibliographic Details
Parent link:Control and Communications (SIBCON).— 2016.— [5 p.]
Main Author: Cherneta D. S. Dmitry Sergeevich
Corporate Author: Томский политехнический университет Институт кибернетики, ИК
Other Authors: Druki A. A. Aleksey Alekseevich, Spitsyn V. G. Vladimir Grigorievich
Summary:Title screen
The relevance of this study is stipulated by the necessity of designing algorithms allowing to improve the efficiency of characters recognition on images with complex backgrounds subjected to noise, affine and projective transformations. Purpose: Development of algorithms and software system allowing to improve the efficiency of characters recognition on images with complex backgrounds subjected to noise, affine and projective transformations. Experimental research to be carried out into the efficiency of developed algorithms and their comparison to their existing analogs. Findings: Viola-Jones object detection algorithm is suggested to detect the area of character location on images with complex background. The image normalization includes the following operations: boundary identification, Hough transformation, search for closed loops, image leveling. The structure of convolutional neural network (CNN) is suggested for characters recognition. The implementation of the developed algorithms is presented by characters recognition on images of vehicle number plates.
Режим доступа: по договору с организацией-держателем ресурса
Language:English
Published: 2016
Subjects:
электронный ресурс
труды учёных ТПУ
распознавание объектов
обработка изображений
преобразование
искусственные нейронные сети
Online Access:http://dx.doi.org/10.1109/SIBCON.2016.7491714
Format: Electronic Book Chapter
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=650493

Similar Items

Similar Items