Automated Human Identification Scheme using Ear Biometrics Technology

Biometrics identification methods have proved to be very efficient, more natural and easy for users than traditional methods of human identification. Biometrics methods truly identify humans, not keys and cards they posses or passwords they should remember. Ear on the other hand, has a more uniform distribution of color, so almost all information is conserved when converting the original image into gray scales. We propose the ear as a biometric and investigate it with both 2D and 3D data. The ICP-based algorithm also demonstrates good scalability with size of dataset. These results are encouraging in that they suggest a strong potential for 3D ear shape as a biometric. Multi-biometric 2D and 3D ear recognition are also explored. The proposed automatic ear detection method will integrate with the current system, and the performance will be evaluated with the original one. The investigation of ear recognition under less controlled conditions will focus on the robustness and variability of ear biometrics. Multi-modal biometrics using 3D ear images will be explored, and the performance will be compared to existing biometrics experimental results.