| | This Article | |
| |
| |
| | Share | |
| |
| |
| | Bibliographic References | |
| |
| |
| | Add to: | |
| |
 Digg
 Furl
 Spurl
 Blink
 Simpy
 Google
 Del.icio.us
 Y!MyWeb
| |
| | Search | |
| |
| |
| | |
Pattern Recognition Properties of Various Feature Spaces for Higher Order Neural Networks
August 1993 (vol. 15 no. 8)
pp. 795-801
The authors explore alternatives that reduce the number of network weights while maintaining geometric invariant properties for recognizing patterns in real-time processing applications. This study is limited to translation and rotation invariance. The primary interest is in examining the properties of various feature spaces for higher-order neural networks (HONNs), in correlated and uncorrelated noise, such as the effect of various types of input features, feature size and number of feature pixels, and effect of scene size. The robustness of HONN training is considered in terms of target detectability. The experimental setup consists of a 15*20 pixel scene possibly containing a 3*10 target. Each trial used 500 training scenes plus 500 testing scenes. Results indicate that HONNs yield similar geometric invariant target recognition properties to classical template matching. However, the HONNs require an order of magnitude less computer processing time compared with template matching. Results also indicate that HONNs could be considered for real-time target recognition applications.
[1] 795D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning internal representation by error propagation,"Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vols. 1 and 2. Cambridge, MA: MIT Press, 1986.[2] C. L. Giles and T. Maxwell, "Learning invariance and generalization in higher-order neural networks,"Applied Opt., vol. 26, pp. 2972-2978. 1987.[3] D. F. Specht, "Generation of polynomial discriminant functions for pattern recognition,"IEEE Trans. Electron. Comput., vol. EC-16, no. 3, pp. 308-319, June 1967.[4] B. Widrow, R. G. Winter, and R. A. Baxter, "Learning phenomena in layered neural networks," inProc. IEEE First Int. Conf. Neural Networks(San Diego, CA), June 21-24, 1987, pp. 411-429, vol. 2[5] M. K. Hu, "Visual pattern recognition by moment invariants,"IRE Trans. Inform. Theory, pp. 179-187, 1962.[6] M. B. Reid, L. Spirkovska, and E. Ochoa, "Rapid training of higher-order neural networks for invariant pattern recognition," inProc. Int. Joint Conf. Neural Networks(Washington DC), June 18-22, 1989, pp. 1-689-1-692.[7] L. Spirkovska and M. B. Reid, "Connectivity strategies for higher-order neural networks applied to pattern recognition," inProc. Int. Joint Conf. Neural Networks(Washington DC), Feb. 2-5, 1990, pp. 1-21-1-26.[8] R. O. Duda and P. E. Hart,Pattern Classification and Scene Analysis. New York, Wiley, 1973, pp. 276-284.
Index Terms:
geometric variance; translation variance; pattern recognition; feature spaces; higher order neural networks; rotation invariance; feature pixels; template matching; real-time target recognition; feature extraction; invariance; neural nets
Citation:
W.A.C. Schmidt, J.P. Davis, "Pattern Recognition Properties of Various Feature Spaces for Higher Order Neural Networks," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 8, pp. 795-801, Aug. 1993, doi:10.1109/34.236250
