Ear verification based on a novel local feature extraction

This paper proposes a novel local feature approach for human verification using 2D ear imaging based on Polar Sine Transform (PST). The proposed approach consists mainly of four steps. Firstly, normalizing the training and testing images, then, combining the normalized images together. Secondly, dividing the fused image into blocks, then, PST is used to extract the invariant features from each block. Thirdly, the Approximate Nearest Neighbors (ANN) searching criterion is adopted to collect the most similar blocks by means of Locality Sensitive Hashing (LSH). Finally, some morphological operations are used to reduce the number of false matching blocks, then, the system verifies the human ear. False Reject Rate (FRR) versus False Acceptance Rate (FAR) and ROC curve are used to evaluate the performance of the proposed approach. The experiments are performed on IIT Delhi database to validate the proposed approach. The results demonstrate that the proposed approach has better performance compared with the existing methods.