Skip to main content

Research Repository

Advanced Search

A deep learning digitisation framework to mark up corrosion circuits in piping and instrumentation diagrams.

Toral, Luis; Moreno-García, Carlos Francisco; Elyan, Eyad; Memon, Shahram

Authors

Luis Toral

Profile Image

Professor Eyad Elyan e.elyan@rgu.ac.uk
Professor & Lead of the Interactive Machine Vision Research Group

Shahram Memon



Contributors

Elisa H. Barney Smith
Editor

Umapada Pal
Editor

Abstract

Corrosion circuit mark up in engineering drawings is one of the most crucial tasks performed by engineers. This process is currently done manually, which can result in errors and misinterpretations depending on the person assigned for the task. In this paper, we present a semi-automated framework which allows users to upload an undigitised Piping and Instrumentation Diagram, i.e. without any metadata, so that two key shapes, namely pipe specifications and connection points, can be localised using deep learning. Afterwards, a heuristic process is applied to obtain the text, orient it and read it with minimal error rates. Finally, a user interface allows the engineer to mark up the corrosion sections based on these findings. Experimental validation shows promising accuracy rates on finding the two shapes of interest and enhance the functionality of optical character recognition when reading the text of interest.

Citation

TORAL, L., MORENO-GARCIA, C.F., ELYAN, E. and MEMON, S. 2021. A deep learning digitisation framework to mark up corrosion circuits in piping and instrumentation diagrams. In Barney Smith, E.H. and Pal, U. (eds.) Document analysis and recognition: ICDAR 2021 workshops, part II: proceedings of 16th International conference on document analysis and recognition 2021 (ICDAR 2021), 5-10 September 2021, Lausanne, Switzerland. Lecture notes in computer science, 12917. Cham: Springer [online], pages 268-276. Available from: https://doi.org/10.1007/978-3-030-86159-9_18

Conference Name 16th International conference on document analysis and recognition 2021 (ICDAR 2021)
Conference Location Lausanne, Switzerland
Start Date Sep 5, 2021
End Date Sep 10, 2021
Acceptance Date Jul 13, 2021
Online Publication Date Sep 2, 2021
Publication Date Dec 31, 2021
Deposit Date Sep 6, 2021
Publicly Available Date Sep 7, 2021
Publisher Springer
Pages 268-276
Series Title Lecture notes in computer science (LNCS)
Series Number 12917
Series ISSN 0302-9743
Book Title Proceedings of document analysis and recognition: ICDAR 2021 workshops, part II.
ISBN 9783030861582
DOI https://doi.org/10.1007/978-3-030-86159-9_18
Keywords Digitisation; Corrosion detection; Piping and instrumentation diagrams; Convolutional neural networks
Public URL https://rgu-repository.worktribe.com/output/1446851

Files

TORAL 2021 A deep learning digitisation (AAM) (542 Kb)
PDF

Copyright Statement
The final authenticated version is available online at https://doi.org/10.1007%2F978-3-030-86159-9_18. This pre-copyedited version is made available under the Springer terms of reuse for AAMs: https://www.springer.com/gp/open-access/publication-policies/aam-terms-of-use.





You might also like



Downloadable Citations