Document Type

Article

Publication Version

Accepted Manuscript

Publication Date

1-4-2019

Journal or Book Title

International Journal of Computer Vision

Volume

127

First Page

1738

Last Page

1750

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 this 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. Our proposed metric significantly improves performance in matching crime scene shoeprints to laboratory test impressions. We also show its effectiveness in other cross-domain image retrieval problems: matching facade images to segmentation labels and aerial photos to map images. Finally, we introduce a discriminatively trained variant and fine-tune our system through our proposed metric, obtaining state-of-the-art performance.

Comments

This is an accepted manuscript of an article published as Kong, Bailey, James Supanc̆ic̆, Deva Ramanan, and Charless C. Fowlkes. "Cross-domain image matching with deep feature maps." International Journal of Computer Vision 127, no. 11-12 (2019): 1738-1750. Posted with permission of CSAFE.

Copyright Owner

Springer Science+Business Media, LLC

Language

en

File Format

application/pdf

Share

COinS