Combination of Tangent Vectors and Local Representations for Handwritten Digit Recognition

Statistical classification using tangent vectors and classification based on local features are two successful methods for various image recognition problems. These two approaches tolerate global and local transformations of the images, respectively. Tangent vectors can be used to obtain global invariance with respect to small affine transformations and line thickness, for example. On the other hand, a classifier based on local representations admits the distortion of parts of the image. From these properties, a combination of the two approaches seems veryl ikely to improve on the results of the individual approaches. In this paper, we show the benefits of this combination byap plying it to the well known USPS handwritten digits recognition task. An error rate of 2.0% is obtained, which is the best result published so far for this dataset.

[1]  David G. Stork,et al.  Pattern Classification , 1973 .

[2]  Yann LeCun,et al.  Efficient Pattern Recognition Using a New Transformation Distance , 1992, NIPS.

[3]  Hermann Ney,et al.  Learning of Variability for Invariant Statistical Pattern Recognition , 2001, ECML.

[4]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[5]  Sunil Arya,et al.  An optimal algorithm for approximate nearest neighbor searching fixed dimensions , 1998, JACM.

[6]  Hermann Ney,et al.  Statistical Image Object Recognition using Mixture Densities , 2004, Journal of Mathematical Imaging and Vision.

[7]  Carla E. Brodley,et al.  Local versus global features for content-based image retrieval , 1998, Proceedings. IEEE Workshop on Content-Based Access of Image and Video Libraries (Cat. No.98EX173).

[8]  Hermann Ney,et al.  Experiments with an extended tangent distance , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[9]  Michael E. Tipping.  The Relevance Vector Machine , 1999, NIPS.

[10]  Cordelia Schmid,et al.  Local Grayvalue Invariants for Image Retrieval , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Yann LeCun,et al.  Transformation Invariance in Pattern Recognition-Tangent Distance and Tangent Propagation , 1996, Neural Networks: Tricks of the Trade.

[13]  Hermann Ney,et al.  Combined Classification of Handwritten Digits Using the 'Virtual Test Sample Method' , 2001, Multiple Classifier Systems.

[14]  Juan Carlos Pérez-Cortes,et al.  Local Representations and a direct Voting Scheme for Face Recognition , 2001, PRIS.

[15]  Bernhard Schölkopf,et al.  Prior Knowledge in Support Vector Kernels , 1997, NIPS.

[16]  Bernard Victorri,et al.  Transformation invariance in pattern recognition: Tangent distance and propagation , 2000 .