Kong, B., Supancic, J., Ramanan, D. and Fowlkes, C. Cross-Domain Forensic Shoeprint Matching. British Machine Vision Conference (BMVC), London, (Sept 2017).
We investigate the problem of automatically determining what type of shoe left an impression found at a crime scene. This recognition problem is made difficult by the variability in types of crime scene evidence (ranging from traces of dust or oil on hard surfaces to impressions made in soil) and the lack of comprehensive databases of shoe outsole tread patterns. We find that mid-level features extracted by pre-trained convo- lutional neural nets are surprisingly effective descriptors for these specialized domains. However, the choice of similarity measure for matching exemplars to a query image is es- sential to good performance. For matching multi-channel deep features, we propose the use of multi-channel normalized cross-correlation and analyze its effectiveness. Finally, we introduce a discriminatively trained variant and fine-tune our system end-to-end, ob- taining state-of-the-art performance.