SChISM: Semantic Clustering via Image Sequence Merging for Images of Human-Decomposition

Sara Mousavi, Dylan Lee, Tatianna Griffin, Kelley Cross, Dawnie Steadman, Audris Mockus; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021, pp. 2190-2199

In many domains, large image collections are key ways in which information about relevant phenomena is retained and analyzed, yet it remains challenging to use such data in research and practice. Our aim is to investigate this problem in the context of a forensic unlabeled dataset of over 1M human decomposition photos. To make this collection usable by experts, various body parts first need to be identified and traced through their evolution despite their distinct appearances at different stages of decay from "fresh" to "skeletonized". We developed an unsupervised technique for clustering images that builds sequences of similar images representing the evolution of each body part through stages of decomposition. Evaluation of our method on 34,476 human decomposition images shows that our method significantly outperforms the state of the art clustering method in this application.