1st International ICST Workshop on Computational Forensics

Research Article

Craniofacial Superimposition in Forensic Identification using Genetic Algorithms

  • @INPROCEEDINGS{10.1109/IAS.2007.80,
        author={Lucia Ballerini and Oscar Cordon and Sergio  Damas and Jose Santamarıa and Inmaculada  Aleman and Miguel Botella},
        title={Craniofacial Superimposition in Forensic Identification using Genetic Algorithms},
        proceedings={1st International ICST Workshop on Computational Forensics},
        publisher={IEEE},
        proceedings_a={IWCF},
        year={2007},
        month={9},
        keywords={Cranial  Forensics  Genetic algorithms  Humans  Image reconstruction  Information security  Proposals  Radiometry  Skull  Software engineering},
        doi={10.1109/IAS.2007.80}
    }
    
  • Lucia Ballerini
    Oscar Cordon
    Sergio Damas
    Jose Santamarıa
    Inmaculada Aleman
    Miguel Botella
    Year: 2007
    Craniofacial Superimposition in Forensic Identification using Genetic Algorithms
    IWCF
    IEEE
    DOI: 10.1109/IAS.2007.80
Lucia Ballerini1,*, Oscar Cordon1,*, Sergio Damas1,2,*, Jose Santamarıa3,*, Inmaculada Aleman4,*, Miguel Botella4,*
  • 1: European Centre for Soft Computing Edf. Cientıfico Tecnologico, Mieres, Spain
  • 2: University of Granada, Granada, Spain
  • 3: Dept. Software Engineering University of Cadiz, Cadiz, Spain
  • 4: Physical Anthropology Lab University of Granada, Granada, Spain
*Contact email: lucia.ballerini@softcomputing.es, oscar.cordon@softcomputing.es, sergio.damas@softcomputing.es, jose.santamarialopez@uca.es, ialeman@ugr.es, mbotella@ugr.es

Abstract

Craniofacial superimposition is a process that aims to identify a person by overlaying a photograph and a model of the skull. This process is usually carried out manually by forensic anthropologists; thus being very time consuming and presenting several difficulties in finding a good fit between the 3D model of the skull and the 2D photo of the face. In this paper we present a fast and automatic procedure to tackle the superimposition problem. The proposed method is based on real-coded genetic algorithms. Synthetic data are used to validate the method. Results on a real case from our Physical Anthropology lab of the University of Granada are also presented.