Random subwindows for robust image classification

We present a novel, generic image classification method based on a recent machine learning algorithm (ensembles of extremely randomized decision trees). Images are classified using randomly extracted subwindows that are suitably normalized to yield robustness to certain image transformations. Our method is evaluated on four very different, publicly available datasets (COIL-100, ZuBuD, ETH-80, WANG). Our results show that our automatic approach is generic and robust to illumination, scale, and viewpoint changes. An extension of the method is proposed to improve its robustness with respect to rotation changes.

[1]  Raphaël Marée,et al.  Decision Trees and Random Subwindows for Object Recognition , 2005 .

[2]  Bernt Schiele,et al.  Analyzing appearance and contour based methods for object categorization , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[3]  Hermann Ney,et al.  Classification error rate for quantitative evaluation of content-based image retrieval systems , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[4]  Cordelia Schmid,et al.  A Performance Evaluation of Local Descriptors , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[6]  Stepán Obdrzálek,et al.  Object recognition methods based on transformation covariant features , 2004, 2004 12th European Signal Processing Conference.

[7]  Zhi-Hua Zhou,et al.  Recognizing partially occluded, expression variant faces from single training image per person with SOM and soft k-NN ensemble , 2005, IEEE Transactions on Neural Networks.

[8]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[9]  Horst Bischof,et al.  Learning Informative SIFT Descriptors for Attentive Object Recognition , 2005 .

[10]  IEEE conference on computer vision and pattern recognition , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[11]  Cordelia Schmid,et al.  A Comparison of Affine Region Detectors , 2005, International Journal of Computer Vision.

[12]  Pierre Geurts,et al.  Extremely randomized trees , 2006, Machine Learning.

[13]  Hermann Ney,et al.  Features for Image Retrieval: A Quantitative Comparison , 2004, DAGM-Symposium.

[14]  Pierre Geurts,et al.  Contributions to decision tree induction: bias/variance tradeoff and time series classification , 2002 .

[15]  Raphaël Marée,et al.  A generic approach for image classification based on decision tree ensembles and local sub-windows , 2004 .

[16]  Hermann Ney,et al.  Automatic categorization of medical images for content-based retrieval and data mining. , 2005, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[17]  Hiroshi Murase,et al.  Learning and recognition of 3D objects from appearance , 1993, [1993] Proceedings IEEE Workshop on Qualitative Vision.

[18]  Tricia Walker,et al.  Computer science , 1996, English for academic purposes series.

[19]  Aleix M. Martinez,et al.  The AR face database , 1998 .

[20]  Yixin Chen,et al.  Image Categorization by Learning and Reasoning with Regions , 2004, J. Mach. Learn. Res..

[21]  Raphaël Marée.  Classification automatique d'images par arbres de d'ecision , 2005 .