Morphological investigations of skulls for sex determination based on sparse principal component analysis

Abstract

Sex determination from skeletons is a significant step in the analysis of forensic anthropology. The relationship between morphological characteristics and the gender of skull is of great importance in forensic anthropology research. This paper presents an automatic method relating the local morphological characteristics of the skull to the sex classification based on sparse principle component analysis (SPCA). Our contributions are: (1)A set of important local characteristics on the skull are obtained using sparse principal component analysis, which correspond to local areas on the skull. The importance of the local characteristics in sex classification are obtained; (2)Experiments on Chinese skulls including 127 males and 81 females are given. The results show the effectiveness of SPCA on Sex determination. © Springer International Publishing 2013.