
Journal: International Journal of Computer Vision
Published: 2019
Primary Author: Bailey Kong
Secondary Authors: James Supancic, Deva Ramana, Charless Fowlkes
Type: Publication
Research Area: Footwear
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.
Related Resources


Forensic Footwear: A Retrospective of the Development of the MANTIS Shoe Scanning System
July 10, 2025
There currently are no shoe-scanning devices developed in the United States that can operate in a real-world, variable-weather environment in …

Examiner consistency in perceptions of fingerprint minutia rarity
July 10, 2025
Friction ridge examiners (FREs) identify distinctive features (minutiae) in fingerprints and consider how rare these observed minutiae are in their …