Abstract
This paper discusses the application of a class of feed-forward Artificial Neural Networks (ANNs) known as Multi-Layer Perceptrons(MLPs) to two vision problems: recognition and pose estimation of 3D objects from a single 2D perspective view; and handwritten digit recognition. In both cases, a multi-MLP classification scheme is developed that combines the decisions of several classifiers. These classifiers operate on the same feature set for the 3D recognition problem whereas different feature types are used for the handwritten digit recognition. The backpropagationlearning rule is used to train the MLPs. Application of the MLP architecture to other vision problems is also briefly discussed.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Hansen LK, Salamon P. Neural Network Ensembles. IEEE Trans PAMI 1990; 12(10): 993–1002.
Xu L, Krzyzak A, Suen CY. Methods of Combining Multiple Classifiers and Their Applications to Handwriting Recognition. IEEE Trans SMC 1992; 22(3): 418–435.
Ho TK, Hull JJ, Srihari SN. Decision Combination in Multiple Classifier Systems. IEEE Trans PAMI 1994; 16(1): 66–75.
Khotanzad A, Chung C. Handwritten Digit Recognition Using BKS Combination of Neural Network Classifiers. Proc IEEE SW Symp on Image Analysis and Interpretation, Dallas, TX 1994; 94–99.
Huang YS, Suen CY. A Method of Combining Multiple Experts for the Recognition of Unconstrained Handwritten Numerals. IEEE Trans PAMI 1995; 17(1): 90–94.
Khotanzad A, Liou J. Recognition and Pose Estimation of Unoccluded Three-Dimensional Objects from a Two-Dimensional Perspective View by Banks of Neural Networks. IEEE Trans NN 1996; 7(4): 907–918.
Woods K, Kegelmeyer WP, Bowyer K. Combination of Multiple Classifiers Using Local Accuracy Estimates. IEEE Trans PAMI 1997; 19(4): 405–410.
Rumelhart DE, McClelland JL. Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1: Foundations. Cambridge, MA: MIT Press.
Teh CH, Chin RT. On Image Analysis by the Methods of Moments. IEEE Trans PAMI 1988; 10(4): 496–514.
Bailey R, Srinath M. Orthogonal Moment Features for Use with Parametric and Non-Parametric Classifiers. IEEE Trans PAMI 1996; 18(4): 389–399.
Pratt WK. Digital Image Processing. Chichester: Wiley, 1991; 449–485.
Burr DJ. Experiments on Neural Net Recognition of Spoken and Written Text. IEEE Trans ASSP 1988; 36(7): 1162–1168.
Wilkinson RA. et al. The First Census Optical Character Recognition System Conference. Gaithersburg, MD: The US, Bureau of Census and the National Institute of Standards and Technology, Technical Report No. NISTIR 4912, August 1992.
Ha TM, Bunke H. Off-line Handwritten Numeral Recognition by Perturbation Method. IEEE Trans PAMI 1997; 19(5): 535–539.
Khotanzad A, Lu JH. Shape and Texture Recognition by a Neural Network. In: Artificial Neural Networks and Statistical Pattern Recognition: Old and New Connections, IK Sethi and AK Jain (editors), Elsevier, 1991, pp. 109–133.
Cottrell G, Munro P, Zipser D. Image Compression by Backpropagation: an example of Extensional Programming. ICS Report 8702, University of California, San Diego, CA, 1987.
Qiu G, Varley M, Terrel T. Image Compression by Edge Pattern Learning Using Multilayer Perceptrons. Electron Lett 1993; 29: 601–602.
Khotanzad A, Bokil A, Lee YW. Stereopsis by Constraint Learning Feed-Forward Neural Networks. IEEE Trans NN 1993; 4(2): 332–342.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Khotanzad, A., Chung, C. Application of multi-layer perceptron neural networks to vision problems. Neural Comput & Applic 7, 249–259 (1998). https://doi.org/10.1007/BF01414886
Issue Date:
DOI: https://doi.org/10.1007/BF01414886