View in EDS

A feasibility study of applying generative deep learning models for map labeling

Saved in:
Bibliographic Details
Title: A feasibility study of applying generative deep learning models for map labeling
Authors: Oucheikh, Rachid, Harrie, Lars
Contributors: Lund University, Faculty of Science, Dept of Physical Geography and Ecosystem Science, Lunds universitet, Naturvetenskapliga fakulteten, Institutionen för naturgeografi och ekosystemvetenskap, Originator, Lund University, Profile areas and other strong research environments, Strategic research areas (SRA), eSSENCE: The e-Science Collaboration, Lunds universitet, Profilområden och andra starka forskningsmiljöer, Strategiska forskningsområden (SFO), eSSENCE: The e-Science Collaboration, Originator
Source: Cartography and Geographic Information Science. 51(1):168-191
Subject Terms: Natural Sciences, Computer and Information Sciences, Other Computer and Information Science, Naturvetenskap, Data- och informationsvetenskap (Datateknik), Annan data- och informationsvetenskap
Description: The automation of map labeling is an ongoing research challenge. Currently, the map labeling algorithms are based on rules defined by experts for optimizing the placement of the text labels on maps. In this paper, we investigate the feasibility of using well-labeled map samples as a source of knowledge for automating the labeling process. The basic idea is to train deep learning models, specifically the generative models CycleGAN and Pix2Pix, on a large number of map examples. Then, the trained models are used to predict good locations of the labels given unlabeled raster maps. We compare the results obtained by the deep learning models to manual map labeling and a state-of-the-art optimization-based labeling method. A quantitative evaluation is performed in terms of legibility, association and map readability as well as a visual evaluation performed by three professional cartographers. The evaluation indicates that the deep learning models are capable of finding appropriate positions for the labels, but thatthey, in this implementation, are not well suited for selecting the labels to show and to determine the size of the labels. The result provides valuable insights into the current capabilities of generative models for such task, while also identifying the key challenges that will shape future research directions.
Access URL: https://doi.org/10.1080/15230406.2023.2291051
Database: SwePub
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://doi.org/10.1080/15230406.2023.2291051#
    Name: EDS - SwePub (s4221598)
    Category: fullText
    Text: View record in SwePub
  – Url: https://resolver.ebscohost.com/openurl?sid=EBSCO:edsswe&genre=article&issn=15230406&ISBN=&volume=51&issue=1&date=20240101&spage=168&pages=168-191&title=Cartography and Geographic Information Science&atitle=A%20feasibility%20study%20of%20applying%20generative%20deep%20learning%20models%20for%20map%20labeling&aulast=Oucheikh%2C%20Rachid&id=DOI:10.1080/15230406.2023.2291051
    Name: Full Text Finder
    Category: fullText
    Text: Full Text Finder
    Icon: https://imageserver.ebscohost.com/branding/images/FTF.gif
    MouseOverText: Full Text Finder
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Oucheikh%20R
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsswe
DbLabel: SwePub
An: edsswe.oai.portal.research.lu.se.publications.44c1bca6.73cc.4137.bda2.a4ef28bbfe12
RelevancyScore: 1064
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1064.41540527344
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: A feasibility study of applying generative deep learning models for map labeling
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Oucheikh%2C+Rachid%22">Oucheikh, Rachid</searchLink><br /><searchLink fieldCode="AR" term="%22Harrie%2C+Lars%22">Harrie, Lars</searchLink>
– Name: Author
  Label: Contributors
  Group: Au
  Data: Lund University, Faculty of Science, Dept of Physical Geography and Ecosystem Science, Lunds universitet, Naturvetenskapliga fakulteten, Institutionen för naturgeografi och ekosystemvetenskap, Originator<br />Lund University, Profile areas and other strong research environments, Strategic research areas (SRA), eSSENCE: The e-Science Collaboration, Lunds universitet, Profilområden och andra starka forskningsmiljöer, Strategiska forskningsområden (SFO), eSSENCE: The e-Science Collaboration, Originator
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <i>Cartography and Geographic Information Science</i>. 51(1):168-191
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Natural+Sciences%22">Natural Sciences</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+and+Information+Sciences%22">Computer and Information Sciences</searchLink><br /><searchLink fieldCode="DE" term="%22Other+Computer+and+Information+Science%22">Other Computer and Information Science</searchLink><br /><searchLink fieldCode="DE" term="%22Naturvetenskap%22">Naturvetenskap</searchLink><br /><searchLink fieldCode="DE" term="%22Data-+och+informationsvetenskap+%28Datateknik%29%22">Data- och informationsvetenskap (Datateknik)</searchLink><br /><searchLink fieldCode="DE" term="%22Annan+data-+och+informationsvetenskap%22">Annan data- och informationsvetenskap</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: The automation of map labeling is an ongoing research challenge. Currently, the map labeling algorithms are based on rules defined by experts for optimizing the placement of the text labels on maps. In this paper, we investigate the feasibility of using well-labeled map samples as a source of knowledge for automating the labeling process. The basic idea is to train deep learning models, specifically the generative models CycleGAN and Pix2Pix, on a large number of map examples. Then, the trained models are used to predict good locations of the labels given unlabeled raster maps. We compare the results obtained by the deep learning models to manual map labeling and a state-of-the-art optimization-based labeling method. A quantitative evaluation is performed in terms of legibility, association and map readability as well as a visual evaluation performed by three professional cartographers. The evaluation indicates that the deep learning models are capable of finding appropriate positions for the labels, but thatthey, in this implementation, are not well suited for selecting the labels to show and to determine the size of the labels. The result provides valuable insights into the current capabilities of generative models for such task, while also identifying the key challenges that will shape future research directions.
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://doi.org/10.1080/15230406.2023.2291051" linkWindow="_blank">https://doi.org/10.1080/15230406.2023.2291051</link>
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsswe&AN=edsswe.oai.portal.research.lu.se.publications.44c1bca6.73cc.4137.bda2.a4ef28bbfe12
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1080/15230406.2023.2291051
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 24
        StartPage: 168
    Subjects:
      – SubjectFull: Natural Sciences
        Type: general
      – SubjectFull: Computer and Information Sciences
        Type: general
      – SubjectFull: Other Computer and Information Science
        Type: general
      – SubjectFull: Naturvetenskap
        Type: general
      – SubjectFull: Data- och informationsvetenskap (Datateknik)
        Type: general
      – SubjectFull: Annan data- och informationsvetenskap
        Type: general
    Titles:
      – TitleFull: A feasibility study of applying generative deep learning models for map labeling
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Oucheikh, Rachid
      – PersonEntity:
          Name:
            NameFull: Harrie, Lars
      – PersonEntity:
          Name:
            NameFull: Lund University, Faculty of Science, Dept of Physical Geography and Ecosystem Science, Lunds universitet, Naturvetenskapliga fakulteten, Institutionen för naturgeografi och ekosystemvetenskap, Originator
      – PersonEntity:
          Name:
            NameFull: Lund University, Profile areas and other strong research environments, Strategic research areas (SRA), eSSENCE: The e-Science Collaboration, Lunds universitet, Profilområden och andra starka forskningsmiljöer, Strategiska forskningsområden (SFO), eSSENCE: The e-Science Collaboration, Originator
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 15230406
            – Type: issn-locals
              Value: SWEPUB_FREE
            – Type: issn-locals
              Value: LU_SWEPUB
          Numbering:
            – Type: volume
              Value: 51
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Cartography and Geographic Information Science
              Type: main
ResultId 1