Skip to content

Cross-Domain Image Matching with Deep Feature Maps

Journal: International Journal of Computer Vision
Published: 2019
Primary Author: Bailey Kong
Secondary Authors: James Supancic, Deva Ramana, Charless Fowlkes
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

Open Forensic Science in R

Open Forensic Science in R

This book is for anyone looking to do forensic science analysis in a data-driven and open way. Whether you are a student, teacher, or scientist, this book is for you. We take…
Quantifying the similarity of 2D images using edge pixels: An application to the forensic comparison of footwear impressions

Quantifying the similarity of 2D images using edge pixels: An application to the forensic comparison of footwear impressions

We propose a novel method to quantify the similarity between an impression (Q) from an unknown source and a test impression (K) from a known source. Using the property of…
Quantifying the similarity of 2D images using edge pixels: An application to the forensic comparison of footwear impressions

Quantifying the similarity of 2D images using edge pixels: An application to the forensic comparison of footwear impressions

We propose a novel method to quantify the similarity between an impression (Q) from an unknown source and a test impression (K) from a known source. Using the property of…
A database of two-dimensional images of footwear outsole impressions

A database of two-dimensional images of footwear outsole impressions

Footwear outsole images were obtained from 150 pairs of used shoes. The motivation for constructing the database was to enable a statistical analysis of two-dimensional (2D) images of shoe outsoles,…
Do you have 44.03 seconds?

44.3 Seconds. That is the average amount of time it takes for a visitor to provide site feedback.
Test it yourself by taking the survey.


    A scientist/researcherA member of the forensic science communityA journalist/publicationA studentOther. Please indicate.


    Learn more about CSAFE overall.Discover research CSAFE is undertaking.Explore collaboration opportunities.Find tools and education opportunities.Other. Please indicate.


    YesNo