Towards Digitisation of Technical Drawings in Architecture: Evaluation of CNN Classification on the Perdaw Dataset

Alexandru Filip, Stella Graßhof

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

Abstract

In a highly digitalised world, this paper aims at closing the gap towards automatic digitisation from 2D architectural drawings. We present the new image dataset Plan, and Elevation Representations of Doors And Windows (Perdaw) which provides a baseline for different classification problems with varying complexity. We investigate the performance of three machine learning models in distinguishing different types of doors and windows in their plan and elevation views. Our findings show that Inception V3 slightly outperforms MobileNet V2, which suggests that the latter solves the same classification tasks with less computational resources with only a minimal compromise in accuracy. Among the three investigated models, ResNet50 yields the lowest quality metrics within a small margin. Overall, all models perform better at classifying building components in their elevation views compared to their plan views. We consistently observed that the models yield the best results with 100{\%} accuracy for the binary classification problems, and dropped to close to 70{\%} accuracy for the 40-class classification problems.
Original languageEnglish
Title of host publicationEngineering Applications of Neural Networks
EditorsLazaros Iliadis , Ilias Maglogiannis , Antonios Papaleonidas , Elias Pimenidis , Chrisina Jayne
Number of pages12
PublisherSpringer Nature Switzerland
Publication dateJun 2024
Pages288-300
ISBN (Print)978-3-031-62494-0
ISBN (Electronic)978-3-031-62495-7
DOIs
Publication statusPublished - Jun 2024
EventInternational Conference on Engineering Applications of Neural Networks - Corfu, Greece
Duration: 27 Jun 202430 Jun 2024
https://eannconf.org/2024/

Conference

ConferenceInternational Conference on Engineering Applications of Neural Networks
Country/TerritoryGreece
CityCorfu
Period27/06/202430/06/2024
Internet address
SeriesCommunications in Computer and Information Science
Volume2141
ISSN1865-0929

Keywords

  • Architecture
  • Convolutional Neural Networks
  • Machine learning
  • Floor plans
  • Deep Learning
  • Object Classification
  • Technical Symbols
  • Architectural Symbols

Fingerprint

Dive into the research topics of 'Towards Digitisation of Technical Drawings in Architecture: Evaluation of CNN Classification on the Perdaw Dataset'. Together they form a unique fingerprint.

Cite this