论文信息 - Invariant Object Recognition Using Higher-Order Neural Networks, Line-Segment Spectra and Multi-Resolution Training

Invariant Object Recognition Using Higher-Order Neural Networks, Line-Segment Spectra and Multi-Resolution Training

A second-order neural network architecture is introduced that achieves invariant recognition with respect to an object's position and orientation in an image. This network does not show the combinatorial growth in network size as image size is increased, which is commonly observed in higher-order architectures. A new concept called an object's line-segment spectrum is introduced. It is argued that the weights of the second-order architecture are determined by these line-segments. Training time then becomes a function of object size rather than image size. The network is tested on the 26 capital letters of the alphabet. It is shown that in this application a multi-resolution training approach leads to reduced training time and improved performance.

Marijke F. Augusteijn | Michael C. Winterbottom

[1] Lilly Spirkovska,et al. Connectivity strategies for higher-order neural networks applied to pattern recognition , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[2] L. Spirkovska,et al. Rapid training of higher-order neural networks for invariant pattern recognition , 1989, International 1989 Joint Conference on Neural Networks.

[3] Takayuki Ito,et al. Neocognitron: A neural network model for a mechanism of visual pattern recognition , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[4] Heeyeung Hwang,et al. Reduced shift invariant second order neural networks using principal component analysis and pixel combinations , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[5] Soheil Shams. Multiple elastic modules for visual pattern recognition , 1995, Neural Networks.

[6] Lilly Spirkovska,et al. Coarse-coded higher-order neural networks for PSRI object recognition , 1993, IEEE Trans. Neural Networks.

[7] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[8] Paulo J. G. Lisboa,et al. Translation, rotation, and scale invariant pattern recognition by high-order neural networks and moment classifiers , 1992, IEEE Trans. Neural Networks.