Towards a methodology for retrieving suspects using 3D facial descriptors

Naoufel Werghi , Hassen Drira (1)

1 CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189

In this paper, We propose a first investigation towards a methodology for exploiting 3D facial images for suspect retrieval in the context of crime investigation. In this field, the standard method is to construct a facial composite, based on witness description, by an artist of via a software, then search a match for it in legal databases. An alternative or complementary scheme would be to define a system of 3D facial attributes that can fit human verbal face description and use them to annotate face databases. Such framework would allow a more efficient search of legal face database and more effective suspect shortlisting. In this contribution, we describe some first steps towards that goal, whereby we define some novel 3D face attributes, we analyze their capacity for face categorization though a hieratical clustering analysis. Then we present some experiments, using a cohort of 107 subjects, assessing the extent to which faces annotation based on some of these attributes meets its human-based counterpart. Both the clustering analysis and the experiments results reveal encouraging indicators for this novel proposed scheme.

Mots clés: 3D Face; clustering; face recognition

Domaines: Informatique [cs]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Naoufel Werghi, Hassen Drira. Towards a methodology for retrieving suspects using 3D facial descriptors. RFMI, 2016, Sidi Bou Said, Tunisia. ⟨hal-01703251⟩