Instantiating Deformable Models with a Neural Net

Deformable models are an attractive approach to recognizing objects which have considerable within-class variability such as handwritten characters. However, there are severe search problems associated with fitting the models to data which could be reduced if a better starting point for the search were available. We show that by training a neural network to predict how a deformable model should be instantiated from an input image, such improved starting points can be obtained. This method has been implemented for a system that recognizes handwritten digits using deformable models, and the results show that the search time can be significantly reduced without compromising recognition performance. © 1997 Academic Press.

[1]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[2]  David G. Lowe,et al.  Learning indexing functions for 3-D model-based object recognition , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[3]  David G. Lowe,et al.  Perceptual Organization and Visual Recognition , 2012 .

[4]  John Scott Bridle,et al.  Probabilistic Interpretation of Feedforward Classification Network Outputs, with Relationships to Statistical Pattern Recognition , 1989, NATO Neurocomputing.

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

[6]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[7]  Geoffrey E. Hinton,et al.  Combining two methods of recognizing hand-printed digits , 1992 .

[8]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[9]  Geoffrey E. Hinton,et al.  TRAFFIC: Recognizing Objects Using Hierarchical Reference Frame Transformations , 1989, NIPS.

[10]  Ulf Grenander,et al.  Hands: A Pattern Theoretic Study of Biological Shapes , 1990 .

[11]  Richard S. Stephens,et al.  Probabilistic approach to the Hough transform , 1991, Image Vis. Comput..

[12]  Yehezkel Lamdan,et al.  Geometric Hashing: A General And Efficient Model-based Recognition Scheme , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[13]  R. Bajcsy,et al.  A computerized system for the elastic matching of deformed radiographic images to idealized atlas images. , 1983, Journal of computer assisted tomography.

[14]  A. Yuille.  Deformable Templates for Face Recognition , 1991, Journal of Cognitive Neuroscience.

[15]  Loren W. Nolte,et al.  Performance of the hough transform and its relationship to statistical signal detection theory , 1988, Comput. Vis. Graph. Image Process..

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

[17]  Y. J. Tejwani,et al.  Robot vision , 1989, IEEE International Symposium on Circuits and Systems,.

[18]  Timothy F. Cootes,et al.  A Generic System For Classifying Variable Objects Using Flexible Template Matching , 1993, BMVC.

[19]  Alexander J. Smola,et al.  Neural Information Processing Systems , 1997, NIPS 1997.

[20]  J. G. Taylor,et al.  ARTIFICIAL NEURAL NETWORKS, 2 , 1992 .

[21]  Martin A. Fischler,et al.  The Representation and Matching of Pictorial Structures , 1973, IEEE Transactions on Computers.

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

[23]  Geoffrey E. Hinton,et al.  Using Generative Models for Handwritten Digit Recognition , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  David S. Broomhead,et al.  Multivariable Functional Interpolation and Adaptive Networks , 1988, Complex Syst..

[25]  Tomaso Poggio,et al.  Example Based Image Analysis and Synthesis , 1993 .

[26]  Bernard Widrow,et al.  The "Rubber-Mask" Technique I. Pattern Measurement and Analysis , 1973 .

[27]  Geoffrey E. Hinton,et al.  To appear in : Advances in Neural Information Processing Systems , 2007 .

[28]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[29]  Geoffrey E. Hinton,et al.  Discovering Viewpoint-Invariant Relationships That Characterize Objects , 1990, NIPS.

[30]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[31]  Geoffrey E. Hinton,et al.  Combining deformable models and neural networks for handprinted digit recognition , 1994 .