Exploring the Ear Recognition Process

Recognizing people by their ears has recently received significant attention in literature. The ear has been used as a mean of human recognition in forensic activities for a long time. During the investigation of several crime scenes, earprints commonly have been used to identify suspects. The purpose of this paper is to offer an approach integrating some basic techniques using ears to recognize people. This document uses Hausdorff distance, Sliding windows, Image Ray Transform (IRT) and the Haar based classifier for the detection step in order to compute SURF and LDA features as an input of two neural networks to recognize a person by the patterns of its ear.