Multimodal ear recognition based on 2d+3d feature fusion

Authors:
Mingduo Guo;Zhichun Mu;Li Yuan
Affiliations:
School of Automation and Electronic Engineering, University of Sience and Technology Beijing, Beijing, China;School of Automation and Electronic Engineering, University of Sience and Technology Beijing, Beijing, China;School of Automation and Electronic Engineering, University of Sience and Technology Beijing, Beijing, China
Venue:
CCBR'12 Proceedings of the 7th Chinese conference on Biometric Recognition
Year:
2012

Citing 6
Cited 0

Face Recognition by Elastic Bunch Graph Matching

IEEE Transactions on Pattern Analysis and Machine Intelligence
Distortion Invariant Object Recognition in the Dynamic Link Architecture

IEEE Transactions on Computers
Local Gabor Binary Pattern Histogram Sequence (LGBPHS): A Novel Non-Statistical Model for Face Representation and Recognition

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Human Ear Recognition in 3D

IEEE Transactions on Pattern Analysis and Machine Intelligence
A fast algorithm for ICP-based 3D shape biometrics

Computer Vision and Image Understanding
Multi-biometrics 2d and 3d ear recognition

AVBPA'05 Proceedings of the 5th international conference on Audio- and Video-Based Biometric Person Authentication

Quantified Score

Hi-index	0.00

Visualization

Abstract

According to the limitation of 2D or 3D ear recognition and the complementarity between two recognition strategies, a multimodal ear recognition method based on 2D and 3D ear feature-level fusion is presented in this paper. Firstly, LGBP algorithm is used to describe textural feature of 2D ear and depth feature of 3D ear respectively. Then two feature vectors are concatenated to form a high dimensional fused feature. Finally, the KPCA,ReliefF method is proposed to eliminate the correlation between 2D and 3D ear images and remove the redundancy data. Experimental results show that the multimodal ear recognition outperforms either using 2D or 3D alone, especially under illumination variation, partial occlusion and posture change.