Facial image analysis in anthropology: a review - Kalina - 2011

Faces have recently become the subject of intensive research straddling the disciplines of biological or forensic anthropology, computer science, medical image analysis, statistics, and genetics. Image analysis, as a highly developed discipline of computer science, is not only devoted to applications of information technology to images but also can be described as a scientific discipline aimed at extracting information from images. This paper gives an overview of the methods used to analyse two-dimensional and three-dimensional, images, which are applicable to practical tasks of biological and forensic anthropology. We discuss the role of image pre-processing in computer-assisted methods in anthropological research. An up-to-date overview of the methods of image analysis used for various anthropological tasks is given, including methods of rigid and deformable template matching, geometric morphometrics, and statistical methods suitable for information extraction from images. For inspiration, we pay attention also to remarkable image analysis methods, which have recently been proposed in computer science for the analysis of facial images. Finally, we describe a study of face identification, which compares various approaches to dimension reduction and classification analysis and brings arguments in favour of robust image analysis that is based on robust statistical methodology.

Keywords

Face - Computer-assisted methods - Template matching - Geometric morphometrics - Robust image analysis

Full text (PDF)

Export citation

Related articles