Computer-based craniofacial superimposition in forensic identification using soft computing

Abstract

One of the most important tasks in forensic anthropology is human identification. Over the past decades, forensic anthropologists have focused on improving techniques to increase the accuracy of identification. Following a thorough examination of unidentified human remains, the investigator chooses a specific identification technique to be applied, depending on the availability of ante mortem and post mortem data. Craniofacial superimposition is a forensic process in which photographs of a missing person are compared with a skull in order to determine whether is the individual depicted and the skeletal remains are the same person. After more than one century of development, craniofacial superimposition has become an interdisciplinary research field where computer science has acquired a key role as a complement of forensic sciences. Moreover, the availability of new digital equipment has resulted in a significant advance in the applicability of this forensic identification technique. In this paper, we review a semi-automatic method devised to assist the forensic anthropologist in the identification process using craniofacial superimposition. The technique is based on a three-stage methodology. The first two are performed automatically by soft computing techniques. However, the final decision corresponds to the forensic expert. The performance of the proposed method is illustrated using several real-world identification cases.