Historical maps provide crucial insights into past landscapes, yet their traditional analogue format restricts accessibility and analysis. Digitization and vectorization of these maps can enhance their usability by integrating them with Geographic Information Systems (GIS). This paper presents the result of the ongoing study for the vectorization of a 19th- century Austro-Hungarian cadastral map of Trentino, Italy, using Object-Based Image Analysis (OBIA) and other image processing techniques. Initial OBIA methods faced challenges with segmentation sensitivity due to the colour variations and scan resolution. Adjustments in threshold parameters led to over-segmentation and under-segmentation issues. Other approaches like zero crossing and colour filtering were tried but none of the tested approach has yield satisfactory results. The paper highlights the need for tailored vectorization approaches and continued methodological advancements to effectively process historical maps for large-scale digitization projects. Despite ongoing challenges, this study underscores the potential of combining various techniques to improve the accuracy and efficiency of transforming historical maps into valuable geospatial datasets
From Paper to GIS: An Example of Historical Maps Vectorization / Sarzotti, Ettore; Gabellieri, Nicola; Zatelli, Paolo; Besana, Angelo. - In: E-PERIMETRON. - ISSN 1790-3769. - 2025, 20:1(2025), pp. 1-11.
From Paper to GIS: An Example of Historical Maps Vectorization
Sarzotti, Ettore;Gabellieri, Nicola;Zatelli, Paolo;Besana, Angelo
2025-01-01
Abstract
Historical maps provide crucial insights into past landscapes, yet their traditional analogue format restricts accessibility and analysis. Digitization and vectorization of these maps can enhance their usability by integrating them with Geographic Information Systems (GIS). This paper presents the result of the ongoing study for the vectorization of a 19th- century Austro-Hungarian cadastral map of Trentino, Italy, using Object-Based Image Analysis (OBIA) and other image processing techniques. Initial OBIA methods faced challenges with segmentation sensitivity due to the colour variations and scan resolution. Adjustments in threshold parameters led to over-segmentation and under-segmentation issues. Other approaches like zero crossing and colour filtering were tried but none of the tested approach has yield satisfactory results. The paper highlights the need for tailored vectorization approaches and continued methodological advancements to effectively process historical maps for large-scale digitization projects. Despite ongoing challenges, this study underscores the potential of combining various techniques to improve the accuracy and efficiency of transforming historical maps into valuable geospatial datasets| File | Dimensione | Formato | |
|---|---|---|---|
|
Sarzotti_et_al.pdf
accesso aperto
Descrizione: International Web Journal
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
1.16 MB
Formato
Adobe PDF
|
1.16 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione



