International Journal of Computer Vision Publishes CSAFE Research on Shoe Impressions

The International Journal of Computer vision published the latest CSAFE advancements in shoeprint impression research. In the paper “Cross-Domain Image Matching with Deep Feature Maps,” researcher and University of California, Irvine computer science professor Dr. Charless Fowlkes investigates problems facing forensic examiners when determining what type of shoe left an impression found at a crime scene. The lack of comprehensive databases of shoe outsole tread patterns and the variability in types of crime scene evidence (ranging from traces of dust or oil on hard surfaces to impressions made in soil) make finding this information difficult.  CSAFE team members developed a new metric to significantly improve peformance in automatically matching crime scene shoeprints to laboratory test impressions. Review additional advancements the CSAFE team is contributing to shoeprints and treadmark research.