DocumentCode :
1635433
Title :
Applying neural networks to colour image data compression
Author :
Godfrey, Keith R L ; Attikiouzel, Yiannis
Author_Institution :
Dept. of Electr. & Electron. Eng., Western Australia Univ., Nedlands, WA, Australia
fYear :
1992
Firstpage :
545
Abstract :
A self-organizing neural network is used to achieve color image segmentation and image data compression, with an adaptive codebook for faster training. Neural network architectures are well-suited to high speed processing because they are massively parallel. By adding an external threshold decision, a compression network can build its codebook adaptively and therefore speed the compression process. A 24-bit color image is compressed to 6.39 bit with virtually no visual degradation
Keywords :
data compression; image coding; image segmentation; self-organising feature maps; adaptive codebook; color image segmentation; colour image data compression; external threshold decision; high speed processing; self-organizing neural network; Color; Data compression; Image coding; Image segmentation; Information processing; Intelligent systems; Neural networks; Pixel; Quantization; Slabs;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
TENCON '92. ''Technology Enabling Tomorrow : Computers, Communications and Automation towards the 21st Century.' 1992 IEEE Region 10 International Conference.
Conference_Location :
Melbourne, Vic.
Print_ISBN :
0-7803-0849-2
Type :
conf
DOI :
10.1109/TENCON.1992.272008
Filename :
272008
Link To Document :
بازگشت