Abstract
Personal identification of the living from video surveillance systems usually involves 2D images. However, the potentiality of three-dimensional facial models in gaining personal identification through 3D-3D comparison still needs to be verified. This study aims at testing the reliability of a protocol for 3D-3D registration of facial models, potentially useful for personal identification. Fifty male subjects aged between 18 and 45 years were randomly chosen from a database of 3D facial models acquired through stereophotogrammetry. For each subject, two acquisitions were available; the 3D models of faces were then registered onto other models belonging to the same and different individuals according to the least point-to-point distance on the entire facial surface, for a total of 50 matches and 50 mismatches. RMS value (root mean square) of point-to-point distance between the two models was then calculated through the VAM® software. Intra- and inter-observer errors were assessed through calculation of relative technical error of measurement (rTEM). Possible statistically significant differences between matches and mismatches were assessed through Mann–Whitney test (p < 0.05). Both for intra- and inter-observer repeatability rTEM was between 2.2 and 5.2%. Average RMS point-to-point distance was 0.50 ± 0.28 mm in matches, 2.62 ± 0.56 mm in mismatches (p < 0.01). An RMS threshold of 1.50 mm could distinguish matches and mismatches in 100% of cases. This study provides an improvement to existing 3D-3D superimposition methods and confirms the great advantages which may derive to personal identification of the living from 3D facial analysis.
Highlights
The analysis and comparison of faces are fundamental for the identification of the living from video surveillance systems: in this case, facial characteristics of a culprit recorded by cameras and a possible suspect are compared to verify the possible match [1]
The database includes 3D facial models collected by the Laboratory of Functional Anatomy of the Stomatognathic System (LAFAS) – Department of Biomedical Sciences for Health
Personal identification from video surveillance systems has always brought about specific issues in forensic practice, being the most critical the quantification of differences between facial silhouettes. 2D-3D superimposition represents the most reliable procedure for a comparison between facial features of possible suspects and the culprit recorded in surveillance system [3, 7]
Summary
The analysis and comparison of faces are fundamental for the identification of the living from video surveillance systems: in this case, facial characteristics of a culprit recorded by cameras and a possible suspect are compared to verify the possible match [1]. 2D-3D superimposition, where a 3D model of the suspect is superimposed on the 2D images of the culprit from the video surveillance records [2, 3]. The 2D-3D superimposition procedure is the most used approach for a reliable comparison between facial characteristics of the culprit and the suspect, it is affected by some issues, being the most critical the quantification of differences between the two facial silhouettes and the consequent impossibility of expressing the judgement of identification in a numerical way. An attempt was performed by Yoshino et al who analysed linear distances between
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
