Cited 1 time in webofscience Cited 1 time in scopus

Unified deep neural networks for end-to-end recognition of multi-oriented billet identification number

Title
Unified deep neural networks for end-to-end recognition of multi-oriented billet identification number
Authors
Koo, GyogwonYun, Jong PilChoi, HyeyeonKim, Sang Woo
DGIST Authors
Koo, Gyogwon
Issue Date
2021-04
Citation
Expert Systems with Applications, 168, 114377
Type
Article
Article Type
Article
Author Keywords
Computer visionEnd-to-end text recognitionIndustrial applicationSemantic segmentationText spotting
Keywords
Billets (metal bars)Deep learningDeep neural networksMulti-task learningBillet identificationConventional algorithmsEnd to endSemi-finished productsNeural networks
ISSN
0957-4174
Abstract
In this study, a novel framework for the recognition of a billet identification number (BIN) using deep learning is proposed. Because a billet, which is a semi-finished product, could be rolled, the BIN may be rotated at various angles. Most product numbers, including BIN, are a combination of individual characters. Such product numbers are determined based on the class of each character and its order (or the positioning). In addition, the two pieces of information are constant even if the product number is rotated. Inspired by this concept, the proposed framework of deep neural networks has two outputs. One is for the class of an individual character, and the other is the order of an individual character within BIN. Compared with a previous study, the proposed network requires an additional annotation but does not require additional labor for labeling. The multi-task learning for two annotations has a positive role in the representation learning of a network, which is shown in the experiment results. Furthermore, to achieve a good performance of the BIN identification, we analyzed various networks using the proposed framework. The proposed algorithm was then compared with a conventional algorithm to evaluate the performance of the BIN identification. © 2020 Elsevier Ltd
URI
http://hdl.handle.net/20.500.11750/12727
DOI
10.1016/j.eswa.2020.114377
Publisher
Pergamon Press Ltd.
Related Researcher
Files:
There are no files associated with this item.
Collection:
ICT Research Institute1. Journal Articles


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE