An image storage system using complex-valued associative memories
- 11 November 2002
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (10514651), 626-629 vol.2
- https://doi.org/10.1109/icpr.2000.906153
Abstract
A gray scale image storage system applying a complex-valued associative memory (CAM) combined with a 2-dimensional discrete Fourier transform (2-D DFT) process is proposed. In the proposed system, input images are transformed to a quantized phase matrix through processing including 2-D DFT then provided to CAM. In addition, the elements corresponding to the high frequency, bands in the matrices are omitted in order to reduce the number of neurons of CAM at the degree in which the image degradation is not conspicuous. When a noisy or an imperfect image of a memorised one is input into the system, the corresponding perfect one is output. The image quality memorized into CAM depends on the numbers of both neurons and states of each neuron, respectively. The image quality in changing those numbers and the restoring process of CAM are demonstrated using practical images.Keywords
This publication has 6 references indexed in Scilit:
- Proposal of fully complex-valued neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A multivalued bidirectional associative memory operating on a complex domainNeural Networks, 1998
- Complex-valued multistate neural associative memoryIEEE Transactions on Neural Networks, 1996
- Image restoration using a neural networkIEEE Transactions on Acoustics, Speech, and Signal Processing, 1988
- Neural networks for computation: number representations and programming complexityApplied Optics, 1986
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences of the United States of America, 1982