Abstract
Shift and rotation invariant pattern recognition is usually performed by first extracting invariant features from the images and second classifying them. This poses the problem of not only finding suitable features but also a suitable classifier.
Here a class of structured invariant neural network architectures (SINN) is presented that performs adaptive invariant feature extraction and classification simultaneously. The special characteristic of the pyramidal feedforward architecture of the SINN is sparse connectivity and the use of shared weight vectors. This guarantees the invariance of the network output with respect to cyclic shifts and rotations of the input image. In experiments the recognition ability of the SINN is shown on a database of textile images. Without any preprocessing of the images and without the need to choose an appropriate classifier the SINN achieves similar or even better results than standard pattern recognition methods.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
E. Barnard, D. Casasent, Shift Invariance and the Neocognitron, in Neural Networks, Band 3, S. 403–410, Pergamon Press, 1990
K. Fukushima, N. Wake, Handwritten Alphanumeric Character Recognition by the Neocognitron, IEEE Trans. on Neural Networks, Vol. 2, No. 3, May 1991
T. Kanaoka et al., A higher-order neural network for distortion invariant pattern recognition, Pattern Recognition Letters, Vol. 13, pp. 837–841, Dec. 1992
S. Kröner, A Neural Network for Calculating Adaptive Shift and Rotation Invariant Image Features, Proc. of EUSIPCO'96, 8th European Signal Proc. Conf., G. Ramponi et al. (Eds.), Vol. II, pp. 863–866, Trieste, Italy, Sept. 1996
S. Kröner, A Learning Algorithm for Structured Invariant Neural Networks, Technical Report 5/96, Technische Informatik I, TU Hamburg-Harburg, Sept. 1996.
S. Kröner, H. Schulz-Mirbach, Fast adaptive calculation of invariant features, Tagungsband Mustererkennung 1995, (17. DAGM Symposium), Sagerer, G. et al. (Eds.), S. 23–35, Bielefeld, Sept. 1995. Reihe Informatik aktuell, Springer Verlag
C. Li, and C.-H. Wu, Introducing rotation invariance into the Neocognitron model for target recognition, Pattern Recognition Letters, Vol. 14, pp. 985–995, Dec. 1993
Y. le Cun: Generalization and Network Design Strategies, Connectionism in Perspective, R. Pfeiffer, Z. Schreter, F. Fogelman-Soulié, L. Steels (Eds.), Elsevier Science Publishers B.V. 143–155, North-Holland, 1989
D. de Ridder: Shared weight neural networks in image analysis M.Sc. Thesis, TU Delft, March 1996
D. Rumelhart, J. McClelland, (Ed.), Parallel Distributed Processing, Vol. 1, MIT Press, Cambridge, Massachusetts, 1986
H. Schulz-Mirbach, Ein Referenzdatensatz zur Evaluierung von Sichtprüfungsverfahren für Textiloberflächen, Tech. Report 4/96, Tech. Inf. I, TU Hamburg-Harburg, Sept. 1996
H. Schulz-Mirbach, Anwendung von Invarianzprinzipien zur Merkmalgewinnung in der Mustererkennung, VDI-Fortschrittbericht, Reihe 10, Nr. 372, 1995
L. Spirkovska, M.B. Reid, Coarse-Coded Higher-Order Neural Networks for PSRI Object Recognition, IEEE Trans. Neural Networks, Vol. 4, No. 2, 1993
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kröner, S. (1997). A structured neural network invariant to cyclic shifts and rotations. In: Sommer, G., Daniilidis, K., Pauli, J. (eds) Computer Analysis of Images and Patterns. CAIP 1997. Lecture Notes in Computer Science, vol 1296. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63460-6_141
Download citation
DOI: https://doi.org/10.1007/3-540-63460-6_141
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63460-7
Online ISBN: 978-3-540-69556-1
eBook Packages: Springer Book Archive