Fast and accurate Nearest Neighbor search in the manifolds of symmetric positive definite matrices

In this paper, we present a fast and accurate Nearest Neighbor (NN) search method in the Riemannian manifolds formed by a kind of structured data - symmetric positive definite (SPD) matrices. We use an ensemble of vocabulary trees based on hierarchical k-means clustering and query these trees to find the NN candidates in sub-linear time. As generating these vocabulary trees with widely used affine-invariant Riemannian metric (AIRM) will be very time-demanding, we propose to use the second-order approximation to AIRM (SOA-AIRM). We evaluate the proposed NN search algorithm in the application scenario of near-duplicate image detection in a large database. Experimental results demonstrate that the proposed method significantly outperforms state of the art techniques in terms of both accuracy and speed.

[1]  Stanley C. Ahalt,et al.  Competitive learning algorithms for vector quantization , 1990, Neural Networks.

[2]  Jiwu Huang,et al.  Efficient coarse-to-fine near-duplicate image detection in riemannian manifold , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[3]  P. Thomas Fletcher,et al.  Riemannian geometry for the statistical analysis of diffusion tensor data , 2007, Signal Process..

[4]  Cordelia Schmid,et al.  Evaluation of GIST descriptors for web-scale image search , 2009, CIVR '09.

[5]  Nicholas Ayache,et al.  Fast and Simple Calculus on Tensors in the Log-Euclidean Framework , 2005, MICCAI.

[6]  Anoop Cherian,et al.  Efficient similarity search for covariance matrices via the Jensen-Bregman LogDet Divergence , 2011, 2011 International Conference on Computer Vision.

[7]  Xavier Pennec,et al.  A Riemannian Framework for Tensor Computing , 2005, International Journal of Computer Vision.

[8]  Yuri Ivanov,et al.  Fast Approximate Nearest Neighbor Methods for Non-Euclidean Manifolds with Applications to Human Activity Analysis in Videos , 2010, ECCV.

[9]  Andrew Zisserman,et al.  Video Google: a text retrieval approach to object matching in videos , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[10]  Xiaoqin Zhang,et al.  Single and Multiple Object Tracking Using Log-Euclidean Riemannian Subspace and Block-Division Appearance Model , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  David Nistér,et al.  Scalable Recognition with a Vocabulary Tree , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[12]  Roger Godement.  Introduction a la Th?eorie des Groupes de Lie , 1982 .

[13]  Trevor Darrell,et al.  Adaptive Vocabulary Forests br Dynamic Indexing and Category Learning , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[14]  Piotr Indyk,et al.  Approximate nearest neighbors: towards removing the curse of dimensionality , 1998, STOC '98.

[15]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[16]  X. Pennec.  Probabilities and Statistics on Riemannian Manifolds : A Geometric approach , 2004 .

[17]  Jiwu Huang,et al.  Salient covariance for near-duplicate image and video detection , 2011, 2011 18th IEEE International Conference on Image Processing.

[18]  Rama Chellappa,et al.  Nearest-neighbor search algorithms on non-Euclidean manifolds for computer vision applications , 2010, ICVGIP '10.

[19]  W. Förstner,et al.  A Metric for Covariance Matrices , 2003 .

[20]  Piotr Indyk,et al.  Approximate Nearest Neighbor: Towards Removing the Curse of Dimensionality , 2012, Theory Comput..

[21]  Yanqiang Lei,et al.  Near-Duplicate Image Detection in a Visually Salient Riemannian Space , 2012, IEEE Transactions on Information Forensics and Security.

[22]  Maher Moakher,et al.  Symmetric Positive-Definite Matrices: From Geometry to Applications and Visualization , 2006, Visualization and Processing of Tensor Fields.