Document Type

Conference Proceeding

Conference

2017 British Machine Vision Conference

Publication Version

Published Version

Publication Date

9-2017

Journal or Book Title

Proceedings of British Machine Vision Conference

Conference Date

September 4-7, 2017

City

London, United Kingdom

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. Finally, we introduce a discriminatively trained variant and fine-tune our system end-to-end, obtaining state-of-the-art performance.

Comments

This proceeding is published as Kong, Bailey, J. Supancic, Deva Ramanan, and Charless Fowlkes. "Cross-domain forensic shoeprint matching." In British Machine Vision Conference (BMVC), pp. 1-5. 2017. Posted with permission of CSAFE.

Copyright Owner

The Authors

Language

en

File Format

application/pdf

Share

Article Location

 
COinS