Evaluation of Existing Methods for Earprint Recognition
Year: 2014
Type: dissertation
Abstract: Ear as a part of human body has been used in forensic practice but the use of earprints as \nevidence in criminal trials remains arguable. The Forensic Ear Identification (FearID) research \nproject was started in order to study the strength of evidence of earprints found on crime scenes. \nA limited number of publications exist related to computerized methods used for earprint \nidentification. The study presented here compares existing methods for earprint image \nidentification. Two of them are point based methods that use Scale Invariant Feature Transform\n(SIFT) and Curvature Scale Space (CSS) feature for recognition process. The other is \nbased on the image intensity value that compares two images by registration algorithm. We \napplied two different similarity metrics for evaluating registration. All methods carried out on a\nsubset of FearID database. Equal error rate and hitlist behavior on our small dataset show that \nCSS is not useful in earprint recognition whereas SIFT and image registration technique have \npromising results.
Author: Hiroo Azadi
Language: English
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2123721187