3D face recognition using an expression insensitive dynamic mask

Authors:
Sadegh Salahshoor;Karim Faez
Affiliations:
E.E. Dept. Electrical Engineering, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran;E.E. Dept. Electrical Engineering, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran
Venue:
ICISP'12 Proceedings of the 5th international conference on Image and Signal Processing
Year:
2012

Citing 7
Cited 0

A Method for Registration of 3-D Shapes

IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
2D and 3D face recognition: A survey

Pattern Recognition Letters
An Efficient Multimodal 2D-3D Hybrid Approach to Automatic Face Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Bosphorus Database for 3D Face Analysis

Biometrics and Identity Management
Automatic 3D face recognition from depth and intensity Gabor features

Pattern Recognition
A survey of approaches and challenges in 3D and multi-modal 3D+2D face recognition

Computer Vision and Image Understanding
3D Face Recognition Using Simulated Annealing and the Surface Interpenetration Measure

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Human face recognition is one of the most popular biometric approaches. In last decade 3D face recognition attracted much attention. In this paper, we present an automatic face recognition algorithm and demonstrate its performance on the Bosphorus 3D face database. A novel Dynamic mask is used to segment automatically the regions of face which are less sensitive to expressions. We applied a multilayer perceptron (MLP) to compute maskable region (MR). MR shows which percentage of face image pixels must be masked to produce the expression insensitive binary mask for 3D faces. We applied a modified nearest neighbor classifier for identification. We only used one neutral frontal face of each subject as gallery images and tested our algorithm with emotional expression images. The identification rate obtained is 85.36 percent in non-neutral expression.