Local autocorrelation of similarities with subspaces for shift invariant scene classification

This paper presents a shift invariant scene classification method based on local autocorrelation of similarities with subspaces. Although conventional scene classification methods used bag-of-visual words for scene classification, superior accuracy of kernel principal component analysis (KPCA) of visual words to bag-of-visual words was reported. Here we also use KPCA of visual words to extract rich information for classification. In the original KPCA of visual words, all local parts mapped into subspace were integrated by summation to be robust to the order, the number, and the shift of local parts. This approach discarded the effective properties for scene classification such as the relation with neighboring regions. To use them, we use (normalized) local autocorrelation (LAC) feature of the similarities with subspaces (outputs of KPCA of visual words). The feature has both the relation with neighboring regions and the robustness to shift of objects in scenes. The proposed method is compared with conventional scene classification methods using the same database and protocol, and we demonstrate the effectiveness of the proposed method.

[1]  Jiebo Luo,et al.  Image transform bootstrapping and its applications to semantic scene classification , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[2]  Andrew Zisserman,et al.  Scene Classification Via pLSA , 2006, ECCV.

[3]  J. P. Jones,et al.  An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. , 1987, Journal of neurophysiology.

[4]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[5]  Kazuhiro Hotta,et al.  Scene Classification Based on Multi-resolution Orientation Histogram of Gabor Features , 2008, ICVS.

[6]  Pietro Perona,et al.  Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[7]  Gunnar Rätsch,et al.  An introduction to kernel-based learning algorithms , 2001, IEEE Trans. Neural Networks.

[8]  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).

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

[10]  Cor J. Veenman,et al.  Kernel Codebooks for Scene Categorization , 2008, ECCV.

[11]  Kazuhiro Hotta,et al.  Estimation of Object Position Based on Color and Shape Contextual Information , 2009, ICIAP.

[12]  Kazuhiro Hotta,et al.  Object Categorization Based on Kernel Principal Component Analysis of Visual Words , 2008, 2008 IEEE Workshop on Applications of Computer Vision.

[13]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

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

[15]  Rameswar Debnath,et al.  Kernel Selection for the Support Vector Machine , 2004, IEICE Trans. Inf. Syst..

[16]  Antonio Torralba,et al.  Contextual Priming for Object Detection , 2003, International Journal of Computer Vision.

[17]  Kazuhiro Hotta,et al.  Scene classification based on local autocorrelation of similarities with subspaces , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[18]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[19]  Terrence J. Sejnowski,et al.  The “independent components” of natural scenes are edge filters , 1997, Vision Research.

[21]  Ravi Kothari,et al.  Kernel based subspace pattern classification , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[22]  Massimiliano Pontil,et al.  Support Vector Machines for 3D Object Recognition , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Bernhard Schölkopf,et al.  Extracting Support Data for a Given Task , 1995, KDD.

[24]  Takio Kurita,et al.  A New Scheme for Practical Flexible and Intelligent Vision Systems , 1988, MVA.

[25]  Joachim M. Buhmann,et al.  Distortion Invariant Object Recognition in the Dynamic Link Architecture , 1993, IEEE Trans. Computers.

[26]  Tomaso A. Poggio,et al.  Face recognition: component-based versus global approaches , 2003, Comput. Vis. Image Underst..

[27]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[28]  N. Otsu,et al.  Action and simultaneous multiple-person identification using cubic higher-order local auto-correlation , 2004, ICPR 2004.

[29]  Kazuhiro Hotta,et al.  Non-Linear Feature Extraction by Linear Principal Component Analysis Using Local Kernel , 2010 .

[30]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.