The mapKurator System: A Complete Pipeline for Extracting and Linking Text from Historical Maps (2306.17059v2)
Abstract: Scanned historical maps in libraries and archives are valuable repositories of geographic data that often do not exist elsewhere. Despite the potential of machine learning tools like the Google Vision APIs for automatically transcribing text from these maps into machine-readable formats, they do not work well with large-sized images (e.g., high-resolution scanned documents), cannot infer the relation between the recognized text and other datasets, and are challenging to integrate with post-processing tools. This paper introduces the mapKurator system, an end-to-end system integrating machine learning models with a comprehensive data processing pipeline. mapKurator empowers automated extraction, post-processing, and linkage of text labels from large numbers of large-dimension historical map scans. The output data, comprising bounding polygons and recognized text, is in the standard GeoJSON format, making it easily modifiable within Geographic Information Systems (GIS). The proposed system allows users to quickly generate valuable data from large numbers of historical maps for in-depth analysis of the map content and, in turn, encourages map findability, accessibility, interoperability, and reusability (FAIR principles). We deployed the mapKurator system and enabled the processing of over 60,000 maps and over 100 million text/place names in the David Rumsey Historical Map collection. We also demonstrated a seamless integration of mapKurator with a collaborative web platform to enable accessing automated approaches for extracting and linking text labels from historical map scans and collective work to improve the results.
- An interactive tool for manual, semi-automatic and automatic video annotation. Computer Vision and Image Understanding 131 (2015), 88–99.
- Enriching Word Vectors with Subword Information. arXiv preprint arXiv:1607.04606 (2016).
- Using historical maps in scientific studies: Applications, challenges, and best practices. Springer.
- Synthetic data for text localisation in natural images. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2315–2324.
- Swintextspotter: Scene text spotting via better synergy between text detection and text recognition. In Proc. of CVPR ’22. 4593–4603.
- Intelligent map reader: A framework for topographic map understanding with deep learning and gazetteer. IEEE Access 6 (2018), 25363–25376.
- An Automatic Approach for Generating Rich, Linked Geo-Metadata from Historical Map Images. In Proc. of ACM SIGKDD ’20. 3290–3298.
- Synthetic Map Generation to Provide Unlimited Training Data for Historical Map Text Detection. In Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery. 17–26.
- Min Namgung and Yao-Yi Chiang. 2022. Incorporating Spatial Context for Post-OCR in Map Images. In Proc. of the 5th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery (GeoAI ’22). Association for Computing Machinery, New York, NY, USA, 14–17.
- Robert E Roth. 2012. Cartographic interaction primitives: Framework and synthesis. The Cartographic Journal 49, 4 (2012), 376–395.
- David Rumsey and Meredith Williams. 2002. Historical maps in GIS.
- LabelMe: a database and web-based tool for image annotation. International Journal of Computer Vision 77, 1 (2008), 157–173.
- Deep neural networks for text detection and recognition in historical maps. In Proc. of IEEE ICDAR ’19. IEEE, 902–909.
- The FAIR Guiding Principles for scientific data management and stewardship. Scientific data 3, 1 (2016), 1–9.
- Text spotting transformers. In Proc. of CVPR ’22. 9519–9528.
- Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020).
- Jina Kim (12 papers)
- Zekun Li (73 papers)
- Yijun Lin (9 papers)
- Min Namgung (5 papers)
- Leeje Jang (3 papers)
- Yao-Yi Chiang (30 papers)