Abstract
Convolutional neural networks (CNNs) represent an interesting method for adaptive image processing, and form a link between general feed-forward neural networks and adaptive filters. Two dimensional CNNs are formed by one or more layers of two dimensional filters, with possible non-linear activation functions and/or down-sampling. CNNs possess key properties of translation invariance and spatially local connections (receptive fields). We present a description of the convolutional network architecture, and an application to practical image processing on a mobile robot. A CNN is used to detect and characterize cracks on an autonomous sewer inspection robot. The filter sizes used in all cases were 4x4, with non-linear activations between each layer. The number of feature maps used in the three hidden layers was, from input to output, 4, 4, 4. The network was trained using a dataset of 48x48 sub-regions drawn from 30 still image 320x240 pixel frames sampled from a pre-recorded sewer pipe inspection video. 15 frames were used for training and 15 for validation of network performance. Although development of a CNN system for civil use is on-going, the results support the notion that data-based adaptive image processing methods such as CNNs are useful for image processing, or other applications where the input arrays are large, and spatially / temporally distributed. Further refinements of the CNN architecture, such as the implementation of separable filters, or extensions to three dimensional (ie. video) processing, are suggested.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representation by error propagation. In: Rumelhart, D.E., McClelland, J.L. (eds.) Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1, pp. 318–362. MIT Press, Cambridge (1986)
Le Cun, Y.B., Boser, J.S., Denker, D., Henderson, R.E., Howard, W., Hubbard, W., Jackel, L.D.: Backpropagation applied to handwritten zip code recognition. Neural Computation 4(1), 541–551 (1988)
Lang, K.J., Hinton, G.E.: Dimensionality reduction and prior knowledge in e-set recognition. In: Touretzky, D.S. (ed.) Advances in Neural Information Processing Systems, pp. 178–185. Morgan Kauffman, San Marteo (1990)
Fukushima, K., Miyake, S., Ito, T.: Neocognitron: a neural model for a mechanism of visual pattern recognition. IEEE Transactions on Systems, Man, and Cybernetics 13, 826–834 (1983)
Fukushima, K.: Neocognitron: A hierachical neural network capable of visual pattern recognition. Neural Networks 1(2), 119–130 (1988)
Le Cun, Y., Bengio, Y.: Convolutional networks for images, speech, and time series. In: Arbib, M.A. (ed.) The Handbook of Brain Theory and Neural Networks, pp. 255–258. MIT Press, Cambridge (1995)
Lawrence, S., Lee Giles, C., Tsoi, A.C., Back, A.D.: Face recognition: A convolutional neural network approach. IEEE Transactions on Neural Networks 8(1), 98–113 (1997)
Fasel, B.: Robust face analysis using convolutional neural networks. In: Proceedings of the International Conference on Pattern Recognition (ICPR 2002), Quebec, Canada (2002)
Sackinger, E., Boser, B., Bromley, J., LeCun, Y.: Application of the anna neural network chip to high-speed character recognition. IEEE Transactions on Neural Networks 3, 498–505 (1992)
Le Cun, Y.: Generalization and network design strategies,” Tech. Rep. CRGTR- 89-4, Department of Computer Science, University of Toronto (1989)
Bengio, Y., Le Cun, Y., Henderson, D.: Globally trained handwritten word recognizer using spatial representation, convolutional neural networks, and Hidden MarkovModels. In: Cowan, J.D., Tesauro, G., Alspector, J. (eds.) Advances in Neural Information Processing Systems, vol. 6, pp. 937–944. Morgan Kaufmann Publishers, Inc., San Francisco (1994)
Fasel, B.: Facial expression analysis using shape and motion information extracted by convolutional neural networks. In: Proceedings of the International IEEE Workshop on Neural Networks for Signal Processing (NNSP 2002), Martigny, Switzerland (2002)
Kirchner, F., Hertzberg, J.: A prototype study of an autonomous robot platform for sewerage system maintenance. Autonomous Robots 4(4), 319–331 (1997)
Browne, M., Dorn, M., Ouellette, R., Shiry, S.: Wavelet entropy-based feature extraction for crack detection in sewer pipes. In: 6th International Conference on Mechatronics Technology, Kitakyushu, Japan (2002)
Browne, M., Shiry, S., Dorn, M., Ouellette, R.: Visual feature extraction via pca-based parameterization of wavelet density functions. In: International Symposium on Robots and Automation, Toluca, Mexico (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Browne, M., Ghidary, S.S. (2003). Convolutional Neural Networks for Image Processing: An Application in Robot Vision. In: Gedeon, T.(.D., Fung, L.C.C. (eds) AI 2003: Advances in Artificial Intelligence. AI 2003. Lecture Notes in Computer Science(), vol 2903. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24581-0_55
Download citation
DOI: https://doi.org/10.1007/978-3-540-24581-0_55
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20646-0
Online ISBN: 978-3-540-24581-0
eBook Packages: Springer Book Archive