relation: https://khub.utp.edu.my/scholars/17626/
title: Enhanced Symbol Recognition based on Advanced Data Augmentation for Engineering Diagrams
creator: Bin, O.K.
creator: Hooi, Y.K.
creator: Kadir, S.J.A.
creator: Fujita, H.
creator: Rosli, L.H.
description: Symbol recognition has generated research interest for image analytics of engineering diagrams. Techniques including structural, syntactic, statistical, Convolution Neural Network (CNN) were studied to identify gaps of research. Despite popularity, CNN requires huge learning dataset, which often involves costly procurement. To address this, combination between CycleGAN and CNN is proposed. CycleGAN generates more learning dataset synthetically, thus yielding opportunity to improve accuracy of symbol recognition. In the domain of for engineering symbols, standard CNN model is developed and used in experimental testing. Different ratios of training dataset were tested in multiple experiments using Piping and Instrument Diagram (P&IDs) drawings. Result of highest accuracy for symbol recognition is up to 92.85 against baseline and other method. The results determined that gradual reduction of training samples, the effectiveness of recognition accuracy performance after using proposed method was remained substantially stable. © 2022. International Journal of Advanced Computer Science and Applications. All Rights Reserved.
publisher: Science and Information Organization
date: 2022
type: Article
type: PeerReviewed
identifier:   Bin, O.K. and Hooi, Y.K. and Kadir, S.J.A. and Fujita, H. and Rosli, L.H.  (2022) Enhanced Symbol Recognition based on Advanced Data Augmentation for Engineering Diagrams.  International Journal of Advanced Computer Science and Applications, 13 (5).  pp. 537-546.  ISSN 2158107X     
relation: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85131400870&doi=10.14569%2fIJACSA.2022.0130563&partnerID=40&md5=e6e273ecba3174ee42957a0f0f44cd4e
relation: 10.14569/IJACSA.2022.0130563
identifier: 10.14569/IJACSA.2022.0130563