BackTrace: A Human-AI Collaborative Approach to Discovering Studio Backdrops in Historical Photographs
Keywords:Computer Vision, Human-AI Interaction, Content-Based Image Retrieval, Digital Humanities, Relevance Feedback, History
AbstractIn historical photo research, the presence of painted backdrops have the potential to help identify subjects, photographers, locations, and events surrounding certain photographs. However, there are few dedicated tools or resources available to aid researchers in this largely manual task. In this paper, we propose BackTrace, a human-AI collaboration system that employs a three-step workflow to retrieve and organize historical photos with similar backdrops. BackTrace is a content-based image retrieval (CBIR) system powered by deep learning that allows for the iterative refinement of search results via user feedback. We evaluated BackTrace with mixed-methods evaluation and found that it successfully aided users in finding photos with similar backdrops and grouping them into collections. Finally, we discuss how our findings can be applied to other domains, as well as implications of deploying BackTrace as a crowdsourcing system.
How to Cite
Lim, J., Mohanty, V., Dodson, T., & Luther, K. (2023). BackTrace: A Human-AI Collaborative Approach to Discovering Studio Backdrops in Historical Photographs. Proceedings of the AAAI Conference on Human Computation and Crowdsourcing, 11(1), 91-102. https://doi.org/10.1609/hcomp.v11i1.27551
Full Archival Papers