eprintid: 17293
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/72/93
datestamp: 2023-12-19 03:23:42
lastmod: 2023-12-19 03:23:42
status_changed: 2023-12-19 03:07:48
type: conference_item
metadata_visibility: show
creators_name: Bhanbhro, H.
creators_name: Hooi, Y.K.
creators_name: Hassan, Z.
creators_name: Sohu, N.
title: Modern Deep Learning Approaches for Symbol Detection in Complex Engineering Drawings
ispublished: pub
keywords: Deep learning; Engineering education; Engineering research; Object detection; Signal detection, Complex engineering; Complexes structure; Deep learning; Engineering drawing; Learning approach; Learning models; Object detection method; Objects detection; Objects recognition; Symbols detection, Object recognition
note: cited By 2; Conference of 2022 International Conference on Digital Transformation and Intelligence, ICDI 2022 ; Conference Date: 1 December 2022 Through 2 December 2022; Conference Code:185994
abstract: Due to the rapid advances in object detection methods, object recognition in the engineering drawings has gained researchers' attention in recent years. Usually, engineering drawings are analysed using traditional object detection methods. However, complex structures and their connections sometimes make it challenging for the traditional object detection architectures to process the engineering drawings. With the rapid development in deep learning models, more powerful methods-which are able to interpret high-level and complex features-are introduced to address the challenges exhibited by the traditional methods. These models have different training strategies and thus portray varied behaviors. In this paper, we present a comparative analysis of the deep learning models for object recognition in engineering drawings. Furthermore, real-life scenario on how to process and analyses information from specific engineering drawings, namely, piping and instrumentation diagrams (P&IDs) is discussed in details. Finally, future directions are presented which can serve as research guidelines to work in this domain. © 2022 IEEE.
date: 2022
publisher: Institute of Electrical and Electronics Engineers Inc.
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85147002843&doi=10.1109%2fICDI57181.2022.10007281&partnerID=40&md5=92533310bfdb0e859ca451723d3db275
id_number: 10.1109/ICDI57181.2022.10007281
full_text_status: none
publication: 2022 International Conference on Digital Transformation and Intelligence, ICDI 2022 - Proceedings
pagerange: 121-126
refereed: TRUE
isbn: 9798350397000
citation:   Bhanbhro, H. and Hooi, Y.K. and Hassan, Z. and Sohu, N.  (2022) Modern Deep Learning Approaches for Symbol Detection in Complex Engineering Drawings.  In: UNSPECIFIED.