Perspective methods of human identification: Ear biometrics

Abstract

Geometrical methods of feature extraction from ear images in order to perform human identification are presented. Geometrical approach is motivated by the actual procedures used by police and forensic experts (so-called ear otoscopy). In their work, geometrical features of ears such as size, height, width, and shapes of earlobe are useful and valid proofs of identity. The contribution of the article is development of the new and original methods of geometrical feature extraction from 2D ear images. Four novel algorithms of ear feature extraction from contour images are described in detail. Moreover, identification results obtained for each of the methods, based on the distance of feature vectors in the feature space, are presented.

Ear biometrics: a survey of detection, feature extraction and recognition methods

“…Choras proposes a set of geometric feature extraction methods inspired by the work of Iannarelli [57]. He proposes four different ways of feature location in edge images.…”

“…(a) Concentric Circles [57] (b) SIFT features [53] (c) Active Contour [62] (d) Force Field [41] Figure 7: Examples for feature extraction for 2D ear images.…”

External ear anthroposcopy in female students of the University of Szczecin

“…This constitutes a very strong argument for using the ear in personal identification analyses (Choraś 2004). To describe ear shape, Mark Burge and Wilhelm Burger (1996) created a system based on an adjacency graph built from the Voronoi diagram describing geometrical curve segments (graph matching method) (Choraś 2004). The main problem with ear biometrics is posed by hair and headgear, which cover the outer ear and contribute to numerous errors (Pacut et al 2003).…”

“…The advantage of ear biometrics compared to face biometrics is that the former remain relatively stable over time, which means that reference images do not need to be updated very often. This constitutes a very strong argument for using the ear in personal identification analyses (Choraś 2004). To describe ear shape, Mark Burge and Wilhelm Burger (1996) created a system based on an adjacency graph built from the Voronoi diagram describing geometrical curve segments (graph matching method) (Choraś 2004).…”

“…In a series of experiments, he managed to prove that ear structures are unique, not only in unrelated individuals, but also in twins. His analysis involved a comparison of 12 ear measurements between reference points oriented in relation to a central point (Choraś 2004). The measurements were taken using aligned and size-standardised photographs of the ear.…”