Search Swinburne Research Bank
Please use this identifier to cite or link to this item: http://hdl.handle.net/1959.3/44314
|Download PDF (Published version) (Adobe Acrobat PDF, 552 KB)|
- New adaptive image sequence coding scheme using Kohonen's SOFM
- Andrew, Lachlan L. H.; Palaniswami, Marimuthu
- This paper presents a novel adaptive vector quantization scheme based on the SOFM neural network. All adaptation is performed directly from the quantized image with no explicit adaptation information transmitted or stored. Thus the network learns an input distribution it has never actually seen. Training sets are generated from the received image by scaling the image to approximate the statistics of the original image and selecting blocks in such a way as to capture edges and other image features. This data is fed to a SOFM neural network to update the codebook. A new method is also presented for ensuring that all neurons are well used, by estimating directly from the quantized image how much distortion each neuron introduces. The ability of this scheme to adapt successfully is verified by simulation.
- Publication type
- Conference paper
- Proceedings of the 1995 IEEE International Conference on Neural Networks, Perth, Western Australia, Australia, 27 November-01 December 1995, Vol. 4, pp. 2071-2076
- Publication year
- Computer simulation; Image coding; Image quality; Neural networks; Self organizing feature map; SOFM; Vector quantisation
- 9780780327689, 0780327683
- Publisher URL
- Copyright © 1995 IEEE. Paper reproduced here in accordance with the copyright policy of the publisher.
- Full text
- Peer reviewed