Abstract
Forensic face recognition (FFR) has been studied in recent years in forensic science. Given an automatic face recognition system, output scores of the system are used to describe the similarity of face image pairs, but not suitable for forensics. In this study, a score-mapping model based on kernel density estimation (KDE) and evidence theory is proposed. First, KDE was used to generate probability density function (PDF) for each dimensional feature vector of face image pairs. Then, the PDFs could be utilized to determine separately the basic probability assignment (BPA) of supporting the prosecution hypothesis and the defence hypothesis. Finally, the BPAs of each feature were combined by Dempster’s rule to get the final BPA, which reflects the strength of evidence support. The experimental results demonstrate that compared with the classic KDE-based likelihood ratio method, the proposed method has a better performance in terms of accuracy, sensitivity and specificity.
Highlights
In the context of forensic science, face recognition approaches have fallen into two main categories: Subjective-based and objective-based methods
The hypothesis of the prosecution Hp means that the evidences are from the same source, and the hypothesis of the defense Hd means that the evidences are from the different source
Since Openface is an available open-source toolkit, which based on the FaceNet algorithm for automatic facial identification that was created by Google [23], it is used in the experiment, and we utilize the commonly known matching indexes of accuracy, sensitivity and specificity, defined as: aaaaccccccccaaaaaaaaaaaaaaaa
Summary
In the context of forensic science, face recognition approaches have fallen into two main categories: Subjective-based and objective-based methods. Some organizations such as the European Network of Forensic Science Institutes (ENFSI), report the certainty of the statement match/nonmatch via a quantifiable amount, that is, verify whether it is the same person/different person or not [13]. Once a model for score-to-LR mapping has been set up, the strength of evidences can be obtained by plugging the scores into the model
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
