3D ear recognition using local salience and principal manifold

• Published in: Graphical models Vol. 76; no. 5; pp. 402 - 412
• Main Authors: Sun, Xiaopeng, Wang, Guan, Wang, Lu, Sun, Hongyan, Wei, Xiaopeng
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Inc 01.09.2014; Elsevier
• Subjects: Algorithmics. Computability. Computer arithmetics; Applied sciences; Artificial intelligence; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Ear; Ear recognition; Exact sciences and technology; Feature matching; Manifolds; Matching; Mathematical analysis; Pattern recognition. Digital image processing. Computational geometry; Point cloud; Principal manifold; Salient keypoint; Sampling; Shape recognition; Software; Theoretical computing; Three dimensional; Three dimensional models; Salient keypoint; Feature matching; Point cloud; Principal manifold; Ear recognition; Biometrics; Weighted average; Image recognition; Image processing; Digitizing; Poisson distribution; Object recognition; Shape detection; Computational geometry; Experimental result; Gaussian process; Manifold; Ear; Tridimensional image; Sampling; Curve fitting; Curvature; Pattern matching; Content analysis
• ISSN: 1524-0703; 1524-0711
• DOI: 10.1016/j.gmod.2014.03.003

[Display omitted] As an emerging class of biometrics, human ear has drawn significant attention in recent years. In this paper, we propose a novel 3D ear shape matching and recognition system. First, we propose a novel method for computing saliency value of each point on 3D ear point clouds, which is based on the Gaussian-weighted average of the mean curvature and can be used to sort the keypoints accordingly. Then we propose the optimal selection of the salient key points using the Poisson Disk Sampling. Finally, we fit a surface to the neighborhood of each salient keypoint using the quadratic principal manifold method, establishing the local feature descriptor of each salient keypoint. The experimental results on ear shape matching show that, compared with other similar methods, the proposed system has higher approximation precision on shape feature detection and higher matching accuracy on the ear recognition.