3D Object Recognition Using Hyper-Graphs and Ranked Local Invariant Features

Local invariant feature-based methods such as SIFT have been proven highly effective for object recognition. However, they have made either relatively little use or too complex use of geometric constraints and are confounded when the detected features are superabundant. Here we make two contributions aimed at overcoming these problems. First, we rank the SIFT points (R-SIFT) using visual saliency. Second, we use the reduced set of R-SIFT features to construct a class specific hyper graph (CSHG) which comprehensively utilizes local SIFT and global geometric constraints. Moreover, it efficiently captures multiple object appearance instances. We show how the CSHG can be learned from example images for objects of a particular class. Experiments reveal that the method gives excellent recognition performance, with a low false-positive rate.

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

[2]  Fan Chung,et al.  Spectral Graph Theory , 1996 .

[3]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[4]  Andrew Zisserman,et al.  Scene Classification Using a Hybrid Generative/Discriminative Approach , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  ZhangJ.,et al.  Local Features and Kernels for Classification of Texture and Object Categories , 2007 .

[6]  Pietro Perona,et al.  A Bayesian hierarchical model for learning natural scene categories , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[7]  Yan Ke,et al.  PCA-SIFT: a more distinctive representation for local image descriptors , 2004, CVPR 2004.

[8]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[9]  Edwin R. Hancock,et al.  Learning shape-classes using a mixture of tree-unions , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Laurent Itti,et al.  Interesting objects are visually salient. , 2008, Journal of vision.

[11]  S. Metlapally,et al.  The effect of positive lens defocus on ocular growth and emmetropization in the tree shrew. , 2008, Journal of vision.

[12]  P. Schönemann,et al.  A generalized solution of the orthogonal procrustes problem , 1966 .

[13]  Alexei A. Efros,et al.  Discovering objects and their location in images , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[14]  Cordelia Schmid,et al.  Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[15]  Robert Marti,et al.  Which is the best way to organize/classify images by content? , 2007, Image Vis. Comput..

[16]  Edwin R. Hancock,et al.  Graph embedding using tree edit-union , 2007, Pattern Recognit..

[17]  Antti Oulasvirta,et al.  Computer Vision – ECCV 2006 , 2006, Lecture Notes in Computer Science.

[18]  Miguel Cazorla,et al.  Constellations and the Unsupervised Learning of Graphs , 2007, GbRPR.