Automatic Class Characteristic Recognition in Shoe Tread Images

dc.contributor.author Stack, Jayden
dc.contributor.author Stone, Rick
dc.contributor.author Fales, Colton
dc.contributor.author VanderPlas, Susan
dc.contributor.department Center for Statistics and Applications in Forensic Evidence
dc.date.accessioned 2022-07-08T14:33:02Z
dc.date.available 2022-07-08T14:33:02Z
dc.date.issued 2022-02
dc.description.abstract One of the fundamental problems in footwear forensics is that the distribution of class characteristics in the local population is not currently knowable. Surveillance devices for gathering this data are just half of the battle -- it is also necessary to process the data gathered using these devices and identify relevant features. This presentation will describe progress made in automatic identification of relevant footwear features - brand, shoe size, and tread pattern elements, as well as complications which arise when combining machine learning algorithms with human-friendly features. Using transfer learning to connect pre-trained neural networks to newly gathered and labeled training data, this method bridges the gap between unfriendly numerical features and descriptors used by examiners in practice. Leveraging both clean training data and "messy" data gathered from the local community using newly developed footwear surveillance devices, the authors will present developments in footwear forensics which will enable examiners to testify as to the frequency of class characteristics in the local population in the very near future.
dc.description.comments The following was presented at the 74th Annual Scientific Conference of the American Academy of Forensic Sciences (AAFS), Seattle, Washington, February 21-25, 2022. Posted with permission of CSAFE.
dc.identifier.uri https://dr.lib.iastate.edu/handle/20.500.12876/avVOl0Dr
dc.language.iso en
dc.publisher Copyright 2022, The Authors
dc.title Automatic Class Characteristic Recognition in Shoe Tread Images
dc.type Presentation
dspace.entity.type Publication
relation.isOrgUnitOfPublication d8a3c72b-850f-40f6-87c4-8812547080c7
File
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
2022-Stack-AutomaticClass.pdf
Size:
23.02 MB
Format:
Adobe Portable Document Format
Description: