Assessment of some problematic factors in facial image identification using a 2D/3D superimposition technique |
| |
Authors: | Masaru Atsuchi Akiko Tsuji Yosuke Usumoto Mineo Yoshino Noriaki Ikeda |
| |
Institution: | 1. Department of Forensic Pathology and Sciences, Graduate School of Medical Sciences, Kyushu University, Japan;2. Forensic Science Laboratory, Fukuoka Prefectural Police Headquarters, Japan;3. National Research Institute of Police Science, Japan |
| |
Abstract: | The number of criminal cases requiring facial image identification of a suspect has been increasing because a surveillance camera is installed everywhere in the city and furthermore, the intercom with the recording function is installed in the home. In this study, we aimed to analyze the usefulness of a 2D/3D facial image superimposition system for image identification when facial aging, facial expression, and twins are under consideration. As a result, the mean values of the average distances calculated from the 16 anatomical landmarks between the 3D facial images of the 50s groups and the 2D facial images of the 20s, 30s, and 40s groups were 2.6, 2.3, and 2.2 mm, respectively (facial aging). The mean values of the average distances calculated from 12 anatomical landmarks between the 3D normal facial images and four emotional expressions were 4.9 (laughter), 2.9 (anger), 2.9 (sadness), and 3.6 mm (surprised), respectively (facial expressions). The average distance obtained from 11 anatomical landmarks between the same person in twins was 1.1 mm, while the average distance between different person in twins was 2.0 mm (twins). Facial image identification using the 2D/3D facial image superimposition system demonstrated adequate statistical power and identified an individual with high accuracy, suggesting its usefulness. However, computer technology concerning video image processing and superimpose progress, there is a need to keep familiar with the morphology and anatomy as its base. |
| |
Keywords: | Facial image identification Superimposition 2D and 3D Forensic identification |
本文献已被 ScienceDirect 等数据库收录! |
|