Ear Identification by Fusion of Segmented Slice Regions using Invariant Features: An Experimental Manifold with Dual Fusion Approach

TL;DR

This paper introduces a robust ear identification system that fuses invariant SIFT features from segmented color regions using dual fusion methods, achieving high accuracy on a large database.

Contribution

It presents a novel fusion approach combining concatenation and Dempster-Shafer theory for ear identification using invariant features and GMM modeling.

Findings

Achieved 98.25% identification accuracy on IIT Kanpur ear database.

Demonstrated effectiveness of dual fusion methods in biometric identification.

Validated robustness of the proposed system with a large dataset.

Abstract

This paper proposes a robust ear identification system which is developed by fusing SIFT features of color segmented slice regions of an ear. The proposed ear identification method makes use of Gaussian mixture model (GMM) to build ear model with mixture of Gaussian using vector quantization algorithm and K-L divergence is applied to the GMM framework for recording the color similarity in the specified ranges by comparing color similarity between a pair of reference ear and probe ear. SIFT features are then detected and extracted from each color slice region as a part of invariant feature extraction. The extracted keypoints are then fused separately by the two fusion approaches, namely concatenation and the Dempster-Shafer theory. Finally, the fusion approaches generate two independent augmented feature vectors which are used for identification of individuals separately. The proposed identification technique is tested on IIT Kanpur ear database of 400 individuals and is found to achieve 98.25% accuracy for identification while top 5 matched criteria is set for each subject.