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

Abstract

The possibility of identifying people by the shape of their outer ear was first discovered by the French criminologist Bertillon, and refined by the American police officer Iannarelli, who proposed a first ear recognition system based on only seven features.The detailed structure of the ear is not only unique, but also permanent, as the appearance of the ear does not change over the course of a human life. Additionally, the acquisition of ear images does not necessarily require a person's cooperation but is nevertheless considered to be non-intrusive by most people.Because of these qualities, the interest in ear recognition systems has grown significantly in recent years. In this survey, we categorize and summarize approaches to ear detection and recognition in 2D and 3D images. Then, we provide an outlook over possible future research in the field of ear recognition, in the context of smart surveillance and forensic image analysis, which we consider to be the most important application of ear recognition characteristic in the near future.

A Data-Augmented 3D Morphable Model of the Ear

“…T ∈ R 2M , we define the selection matrices S ∈ [0, 1] 3M ×3N that select the M vertices which are the correspondences of the 2D landmarks. This linear system can be written as:…”

“…The shape of the ear has long been recognised as a means of biometric identification [1], [2], [3], [4]. There are many existing ear recognition systems in the literature [5], [6], [7], [8], [9], [10], with a recent survey by Emersic et al [11] and ear biometrics continues to be an active research area [12].…”

Another Attempt at Estimating the Camera Angle in Ear Recognition

“…However, these studies were limited to in-plane rotations [3][4][5]. The authors developed the technologies necessary to implement criminal investigation-assistance systems for ear images.…”

AR Model Based Human Identification using Ear Biometrics

“…Xie and MU [32] proposed an improved locally linear embedding (LLE) algorithm for reducing the dimensionality of ear features. A general classification algorithm based on the theory of compressive sensing has been used in [33] A complete survey of all the approaches of ear biometrics is given in [34,35].…”