Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Footwear Impression Analysis: Implementing a Model for Automatic Shoeprint Recognition to Use in Forensic Science
Blekinge Institute of Technology, Faculty of Engineering, Department of Applied Signal Processing.
2015 (English)Independent thesis Advanced level (degree of Master (Two Years))Student thesis
Abstract [en]

Footwear impression is a common phenomenon in crime investigation cas-es. It is frequently found where the crime is committed. To identify this impression manually is quite difficult and time consuming. Due to the var-ious qualities, inconsistency of the impressions and variety of footwear outsole designs, make it impossible to identify foot print impressions man-ually in certain cases. The purpose of this thesis was to implement a model for identification the impression from a known set of outsole prints. If the impression is not in data set, the implemented model can determine simi-larity between the crime scene impressions with the suspect’s shoeprint impressions. Forensic experts can investigate the sources of impression as well as the suspects which can help the prosecution. Different algorithms are investigated during the implementation of the model. An automatic image processing method to improve the quality of a query image as well as reference images has been studied. To evaluate the similarity between the known footwear impression and unknown one several features have been extracted from the images. The extracted features are limited to such geometrical shapes as lines and circles. The similarity between extracted features is evaluated using bin-by-bin distance and cross-bin distance using histograms named Features Distance Calculation (FDC). The implemented model compares the features with pre-computed features of database.

Place, publisher, year, edition, pages
2015. , 57 p.
Keyword [en]
Footwear Impression, Shoeprint Recognition
National Category
Signal Processing
Identifiers
URN: urn:nbn:se:bth-2399Local ID: oai:bth.se:arkivex3EAD0292B439FECCC1257DE3004301E6OAI: oai:DiVA.org:bth-2399DiVA: diva2:829673
Uppsok
Technology
Supervisors
Available from: 2015-04-22 Created: 2015-02-05 Last updated: 2015-06-30Bibliographically approved

Open Access in DiVA

fulltext(4337 kB)186 downloads
File information
File name FULLTEXT01.pdfFile size 4337 kBChecksum SHA-512
ea9e5710455852a200ac5588970640d2d55b141ae36b39a143795e2ae044184790e2a3a44baa52f9aef861f46b907b1e07aa624dd7f006b47895f1fcaff60c49
Type fulltextMimetype application/pdf

By organisation
Department of Applied Signal Processing
Signal Processing

Search outside of DiVA

GoogleGoogle Scholar
Total: 186 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 269 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf