The HisVis project was a collaboration with the Noord-Hollands Archief. In this project, we examined to what extent Computer Vision, and more specifically, Scene Detection could be applied to a collection of historical press photographs. The key aspect of scene recognition is to identify the place in which the objects seat. We trained a computer vision model to automatically segment and correctly orient images from photo negatives, to automatically recognize specific scenes on historical press photographs, like a ‘protest’, ‘marriage’, ‘shopping street’ or ‘baseball game’, and to detect whether a photograph was taken indoors or outdoors.
The specific aim of the enrichments provided by scene detection was to benefit users of the archive and cultural historians studying historical photographs.
Publications
- Wevers, Melvin. 2021. “Scene Detection in De Boer Historical Photo Collection.” In Proceedings of the 13th International Conference on Agents and Artificial Intelligence. Vienna.
- Wevers, Melvin, Nico Vriend, and Alexander de Bruin. 2022. “What to Do with 2.000.000 Historical Press Photos? The Challenges and Opportunities of Applying a Scene Detection Algorithm to a Digitised Press Photo Collection.” TMG Journal for Media History 25 (1): 1–24.
- Wevers. (2022). Fotopersbureau De Boer Training Set on Scene Detection (0.2) [Data set]. Zenodo
- Vriend, Nico, and Melvin Wevers. n.d. “Historische Foto’s Beter Doorzoekbaar Met AI - Noord-Hollands Archief.” NHALab