Fine-Grained Forensic Matching

Bailey Kong, James Supancic, Deva Ramanan and Charless Fowlkes

Abstract

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 convolutional neural nets are surprisingly effective descriptors for these specialized domains. However, the choice of similarity measure for matching exemplars to a query image is essential to good performance. For matching multi-channel deep features, we propose the use of multi-channel normalized cross-correlation and analyze its effectiveness.

Session

Orals - Matching

Files

Paper (PDF)
Supplementary (PDF)

DOI

10.5244/C.31.188
https://dx.doi.org/10.5244/C.31.188

Citation

Bibtex

            @inproceedings{BMVC2017_188,
                title={Fine-Grained Forensic Matching},
                author={Bailey Kong, James Supancic, Deva Ramanan and Charless Fowlkes},
                year={2017},
                month={September},
                pages={188.1-188.12},
                articleno={188},
                numpages={12},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.188},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.188}
            }