Будь ласка, використовуйте цей ідентифікатор, щоб цитувати або посилатися на цей матеріал: http://hdl.handle.net/123456789/11461
Назва: Identity documents recognition and detection using semantic segmentation with convolutional neural network
Автори: Kozlenko, Mykola
Sendetskyi, Volodymyr
Simkiv, Oleksiy
Savchenko, Nazar
Bosyi, Andrii
Козленко, Микола Іванович
Ключові слова: identity document
object detection
semantic segmentation
document recognition
document classification
deep learning
neural network
Дата публікації: 28-січ-2021
Видавництво: CEUR-WS
Бібліографічний опис: M. Kozlenko, V. Sendetskyi, O. Simkiv, N. Savchenko, and A. Bosyi, "Identity documents recognition and detection using semantic segmentation with convolutional neural network," in CEUR Workshop Proceedings, vol. 2923, Kyiv, Ukraine, Jan. 28, 2021, pp. 234-242, doi: 10.5281/zenodo.5758182
Серія/номер: CEUR Workshop Proceedings;
Короткий огляд (реферат): Object recognition and detection are well-studied problems with a developed set of almost standard solutions. Identity documents recognition, classification, detection, and localization are the tasks required in a number of applications, particularly, in physical access control security systems at critical infrastructure premises. In this paper, we propose the new original architecture of a model based on an artificial convolutional neural network and semantic segmentation approach for recognition and detection of identity documents in images. The challenge with the processing of such images is the limited computational performance and the limited amount of memory when such an application is running on industrial one-board microcomputer hardware. The aim of this research is to prove the feasibility of the proposed technique and to obtain quality metrics. The methodology of the research is to evaluate the deep learning detection model trained on the mobile identity document video dataset. The dataset contains five hundred video clips for fifty different identity document types. The numerical results from simulations are used to evaluate the quality metrics. We present the results as accuracy versus threshold of the intersection over union value. The paper reports the accuracy above 0.75 for the intersection over union (IoU) threshold value of 0.8. Besides, we assessed the size of the model and proved the feasibility of running the model on industrial one-board microcomputer or smartphone hardware.
URI (Уніфікований ідентифікатор ресурсу): http://ceur-ws.org/Vol-2923/paper25.pdf
http://hdl.handle.net/123456789/11461
ISSN: 1613-0073
Розташовується у зібраннях:Статті та тези (ФМІ)

Файли цього матеріалу:
Файл Опис РозмірФормат 
paper25.pdf1.39 MBAdobe PDFПереглянути/Відкрити


Усі матеріали в архіві електронних ресурсів захищені авторським правом, всі права збережені.