A Fast and Fully Automatic Ear Recognition Approach Based on 3D Local Surface Features

Abstract

Abstract. Sensitivity of global features to pose, illumination and scale variations encouraged researchers to use local features for object representation and recognition. Availability of 3D scanners also made the use of 3D data (which is less affected by such variations compared to its 2D counterpart) very popular in computer vision applications. In this paper, an approach is proposed for human ear recognition based on robust 3D local features. The features are constructed on distinctive locations in the 3D ear data with an approximated surface around them based on the neighborhood information. Correspondences are then established between gallery and probe features and the two data sets are aligned based on these correspondences. A minimal rectangular subset of the whole 3D ear data only containing the corresponding features is then passed to the Iterative Closest Point (ICP) algorithm for final recognition. Experiments were performed on the UND biometric database and the proposed system achieved 90, 94 and 96 percent recognition rate for rank one, two and three respectively. The approach is fully automatic, comparatively very fast and makes on assumption about the localization of the nose or the ear pit, unlike previous works on ear recognition.

Insider Misuse Identification using Transparent Biometrics

“…[22] and [20] utilized face recognition to provide continuous and transparent authentication for desktops and mobile devices respectively. [23] proposed a fast and fully automatic ear recognition approach based on 3D local surface features for generic usage; while [24] investigated an implicit authentication technique based upon ear shapes during a call session on smartphones. By using touch screens, [25] and [26] demonstrated that fingerprint identification can be utilized to provide transparent and continuous protection for mobile devices.…”

A novel 3D ear identification approach based on sparse representation

“…Instead of using traditional features like curvatures, we adopted a local PCA-based feature introduced by Islam et al in [20]. The extracted 3D-ear could be represented as a point…”

“…According to [20], δ i can actually represent the difference of first two principal axes at a local region around p i and it will be zero if the point cloud L i is planar or spherical. By calculating {δ i } for all the points {p i }, we can obtain a feature map.…”

“…For ear detection, we propose a template based scheme which is robust to ear pose change. For feature extraction, we adopt an effective PCA-based descriptor proposed in [20]. Our approach takes 3D point cloud as input and no extra color image is required.…”

3-Dimensional Ear Recognition Based Iterative Closest Point With Stochastic Clustering Matching

“…Figure 1 shows the anatomy of the human entire ear. Thus, it is considered to be a suitable alternative method or complement to the face for current human identification (Ossowskia et al, 2013;Hurley et al, 2007;Islam et al, 2008a). A biometric system is a pattern recognition system that establishes the authenticity of a specific physiological or behavioral characteristic possessed by a user.…”