Learning topological image transforms using cellular simultaneous recurrent networks
Authors:
- 1 August 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21614393,p. 1-9
Abstract
In this work, we investigate cellular simultaneous recurrent networks (CSRNs) to learn topological image mappings, particularly those of the affine transformations. While affine image transformation in conventional image processing is a relatively simple task, learning these transformations is an important part of having neural networks (NNs) function as generalized image processors. We introduce the CSRN and discuss its adaptation for image processing tasks. We report results for translation, rotation and scaling of both binary and grey-scale images. Our results suggest that the CSRN is capable of learning and performing these basic topological transformations.Keywords
This publication has 14 references indexed in Scilit:
- Large-scale pose-invariant face recognition using cellular simultaneous recurrent networkApplied Optics, 2010
- Binary image registration using cellular simultaneous recurrent networks2009
- Beyond Feedforward Models Trained by Backpropagation: A Practical Training Tool for a More Efficient Universal ApproximatorIEEE Transactions on Neural Networks, 2008
- Image registration methods: a surveyImage and Vision Computing, 2003
- Kalman Filtering and Neural Networks2001
- Learning affine transformationsPattern Recognition, 1999
- Parameter optimization in models of the olfactory neural systemNeural Networks, 1996
- Supervised Learning: Can it Escape its Local Minimum?1994
- A neural cocktail-party processorBiological Cybernetics, 1986
- Comparison of Interpolating Methods for Image ResamplingIEEE Transactions on Medical Imaging, 1983