Abstract
The higher order neural network(HONN) was proved to be able to realize invariant object recognition. By taking the relationship between input units into account, HONN's are superior to other neural models in invariant pattern recognition. However, there are two main problems preventing HONN's from practical applications. One is the combinatorial increase of weight number, that is, as input size increases, the number of weights in a HONN increases exponentially. The other problem is sensitivity to distortion and noise. In this paper, we described a method, in which by modifying the constraints imposed on the weights in HONN's, the performance of a HONN with respect to distortion can be improved considerably.
Similar content being viewed by others
References
Mundy, J. L. and Zissorman, A.: Geometric Invariant in Computer Vision, MIT Press, Cambridge, 1992.
Wood, J.: Invariant pattern recognition - a review, Pattern Recognition 29(1) (1996), 1–17.
Giles, C. L. and Maxwell, T.: Learning, invariance and generalization in high-order neural networks, Applied Optics 26(23) (1987), 4972–4978.
Giles, C. L., Griffin, R. D. and Maxwell, T.: Encoding geometric invariant in higher-order neural networks, In: D. Z. Anderson (ed.), Neural Information Processing Systems, Proc. of American Institute of Physics Conference, 1988, pp. 301–309.
Spirkovsks, L. and Reid, M. B.: Connectivity strategies for higher-order neural networks applied to pattern recognition, Proc. Joint Int. Conf. Neural Networks, San Diego, 1990, pp. 121–126.
Spirkovsks, L. and Reid, M. B.: Coarse-coded higher-oder neural networks for PSRI object recognition, IEEE Trans. Neural Networks 4(2) (1993), 276–283.
Perantonis, S. J. and Lisba, P. J. G.: Translation, rotation and scale invariant pattern recognition by higher-order neural networks and moment classifiers, IEEE Trans. Neural Networks 3(2) (1992), 241–256.
Kanaoka, T., Chellappa, R., Yoshitaka, M. and Tomita, S.: A higher-order neural network for distortion invariant pattern recognition, Pattern Recognition Letter 13(12) (1992), 837–841.
Takano, M., Kanaoka, T., Skrzypek, J. and Tomita, S.: A note on a higher-order neural network for distortion invariant pattern recognition, Pattern Recognition Letter 15(6) (1994), 631–635.
Amit, Y. and Geman, D.: Shape quantization and recognition with randomized trees, Neural Computation 9(7) (1997), 1545–1588.
Bishop, C. M.: Neural Networks for Pattern Recognition, Clarendon Press, Oxford, 1995.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
He, Z., Siyal, M.Y. Improvement on Higher-Order Neural Networks for Invariant Object Recognition. Neural Processing Letters 10, 49–55 (1999). https://doi.org/10.1023/A:1018610829733
Issue Date:
DOI: https://doi.org/10.1023/A:1018610829733