Cross-Domain Image Matching with Deep Feature Maps

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 th...

Full description

Saved in:
Bibliographic Details
Published in:International journal of computer vision 2019-12, Vol.127 (11-12), p.1738-1750
Main Authors: Kong, Bailey, Supanc̆ic̆, James, Ramanan, Deva, Fowlkes, Charless C.
Format: Article
Language:English
Subjects:
Artificial Intelligence
Computer Imaging
Computer Science
Correlation analysis
Crime
Crime scenes
Domains
Feature extraction
Feature maps
Footwear
Image management
Image Processing and Computer Vision
Image retrieval
Image segmentation
Laboratory tests
Matching
Neural networks
Pattern Recognition
Pattern Recognition and Graphics
Performance enhancement
State of the art
Vision
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-018-01143-3