Deformation Models for Image Recognition

We present the application of different nonlinear image deformation models to the task of image recognition. The deformation models are especially suited for local changes as they often occur in the presence of image object variability. We show that, among the discussed models, there is one approach that combines simplicity of implementation, low-computational complexity, and highly competitive performance across various real-world image recognition tasks. We show experimentally that the model performs very well for four different handwritten digit recognition tasks and for the classification of medical images, thus showing high generalization capacity. In particular, an error rate of 0.54 percent on the MNIST benchmark is achieved, as well as the lowest reported error rate, specifically 12.6 percent, in the 2005 international ImageCLEF evaluation of medical image specifically categorization.

[1]  Geoffrey E. Hinton,et al.  Adaptive Elastic Models for Hand-Printed Character Recognition , 1991, NIPS.

[2]  Kazuhiko Yamamoto,et al.  Research on Machine Recognition of Handprinted Characters , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Seiichi Uchida,et al.  A Survey of Elastic Matching Techniques for Handwritten Character Recognition , 2005, IEICE Trans. Inf. Syst..

[4]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[5]  David J. Burr,et al.  Elastic Matching of Line Drawings , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Lawrence D. Jackel,et al.  Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[7]  Hermann Ney,et al.  Combination of Tangent Distance and an Image Distortion Model for Appearance-Based Sign Language Recognition , 2005, DAGM-Symposium.

[8]  Geoffrey E. Hinton,et al.  Recognizing Hand-written Digits Using Hierarchical Products of Experts , 2002, NIPS.

[9]  Hans Burkhardt,et al.  Adjustable invariant features by partial Haar-integration , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[10]  Isabelle Guyon,et al.  Comparison of classifier methods: a case study in handwritten digit recognition , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).

[11]  Michael I. Jordan,et al.  Mixtures of Probabilistic Principal Component Analyzers , 2001 .

[12]  Robert Sabourin,et al.  Combining Model-Based and Discriminative Approaches in a Modular Two-stage Classification System: Application to isolated Handwritten Digit Recognition , 2009, Progress in Computer Vision and Image Analysis.

[13]  Bernhard Schölkopf,et al.  Training Invariant Support Vector Machines , 2002, Machine Learning.

[14]  Ethem Alpaydin,et al.  Cascading classifiers , 1998, Kybernetika.

[15]  K. Mardia,et al.  A review of image-warping methods , 1998 .

[16]  Daniel Keysers,et al.  Elastic image matching is NP-complete , 2003, Pattern Recognit. Lett..

[17]  Cheng-Lin Liu,et al.  Handwritten digit recognition: benchmarking of state-of-the-art techniques , 2003, Pattern Recognit..

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

[19]  Oscar E. Agazzi,et al.  Keyword Spotting in Poorly Printed Documents using Pseudo 2-D Hidden Markov Models , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

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

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

[22]  Loo-Nin Teow,et al.  Robust vision-based features and classification schemes for off-line handwritten digit recognition , 2002, Pattern Recognit..

[23]  Geoffrey E. Hinton,et al.  Modeling the manifolds of images of handwritten digits , 1997, IEEE Trans. Neural Networks.

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

[25]  Ching Y. Suen,et al.  Speed and accuracy: large-scale machine learning algorithms and their applications , 2003 .

[26]  Christopher M. Bishop,et al.  Mixtures of Probabilistic Principal Component Analyzers , 1999, Neural Computation.

[27]  Hyun-Chul Kim,et al.  A numeral character recognition using the PCA mixture model , 2002, Pattern Recognit. Lett..

[28]  Seiichi Uchida,et al.  A monotonic and continuous two-dimensional warping based on dynamic programming , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[29]  Donald E. Knuth,et al.  The Stanford GraphBase - a platform for combinatorial computing , 1993 .

[30]  Seiichi Uchida,et al.  Eigen-deformations for elastic matching based handwritten character recognition , 2003, Pattern Recognit..

[31]  Hermann Ney,et al.  Local context in non-linear deformation models for handwritten character recognition , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[32]  Bernard Haasdonk,et al.  Tangent distance kernels for support vector machines , 2002, Object recognition supported by user interaction for service robots.

[33]  Jinhai Cai,et al.  Integration of structural and statistical information for unconstrained handwritten numeral recognition , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[34]  Christopher M. Bishop,et al.  Non-linear Bayesian Image Modelling , 2000, ECCV.

[35]  Loo-Nin Teow,et al.  Handwritten digit recognition with a novel vision model that extracts linearly separable features , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

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

[37]  Hermann Ney,et al.  Combination of Tangent Vectors and Local Representations for Handwritten Digit Recognition , 2002, SSPR/SPR.

[38]  Hermann Ney,et al.  Adaptation in statistical pattern recognition using tangent vectors , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[39]  Patrice Y. Simard,et al.  Metrics and Models for Handwritten Character Recognition , 1998 .

[40]  Norbert Krüger,et al.  Face recognition by elastic bunch graph matching , 1997, Proceedings of International Conference on Image Processing.

[41]  Thomas Martin Deserno,et al.  The CLEF 2005 Cross-Language Image Retrieval Track , 2005, CLEF.

[42]  Seiichi Uchida,et al.  Handwritten character recognition using piecewise linear two-dimensional warping , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[43]  D. Burr.  A dynamic model for image registration , 1981 .

[44]  Kenneth Rose,et al.  Iterative decoding of two-dimensional hidden Markov models , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

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

[46]  Hermann Ney,et al.  Pixel-to-Pixel Matching for Image Recognition Using Hungarian Graph Matching , 2004, DAGM-Symposium.

[47]  Roberto Pieraccini,et al.  Dynamic planar warping for optical character recognition , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[48]  Harris Drucker,et al.  Boosting Performance in Neural Networks , 1993, Int. J. Pattern Recognit. Artif. Intell..

[49]  Paul A. Viola,et al.  Alignment by Maximization of Mutual Information , 1997, International Journal of Computer Vision.

[50]  T M Lehmann,et al.  Content-based Image Retrieval in Medical Applications , 2004, Methods of Information in Medicine.

[51]  Karl Sims,et al.  Handwritten Character Classification Using Nearest Neighbor in Large Databases , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[52]  Richard Szeliski,et al.  Using character recognition and segmentation to tell computer from humans , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[53]  Catherine Blake,et al.  UCI Repository of machine learning databases , 1998 .

[54]  Michio Umeda.  Advances in Recognition Methods for Handwritten Kanji Characters (Special issue on Character Recognition and Document Understanding) , 1996 .

[55]  Bernhard Schölkopf,et al.  Support vector learning , 1997 .

[56]  Patrice Y. Simard,et al.  Best practices for convolutional neural networks applied to visual document analysis , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[57]  Hermann Ney,et al.  Classification of Medical Images using Non-linear Distortion Models , 2004, Bildverarbeitung für die Medizin.