DocumentCode
2748726
Title
An new approach of color quantization of image based on neural network
Author
Wu, Yingqian ; Yang, Cuiping ; Wang, Tianzhen
Author_Institution
Inst. of Image Process., Wuhan Automobile Polytech. Univ., China
Volume
3
fYear
2000
fDate
2000
Firstpage
1563
Abstract
In the paper, a new algorithm using a competitive Hopfield neural network (CHNN) is proposed for color quantization, and it completes two tasks of color palette design and pixel color mapping based on pixel color value distribution. Experiment results show that the approach has the advantages of fast convergent speed the high quantization quality, etc
Keywords
Hopfield neural nets; convergence; image colour analysis; quantisation (signal); unsupervised learning; CHNN; color palette design; competitive Hopfield neural network; fast convergence; image color quantization; pixel color mapping; pixel color value distribution; quantization quality; Algorithm design and analysis; Automobiles; Hopfield neural networks; Image color analysis; Image converters; Image processing; Neural networks; Pixel; Printing; Quantization;
fLanguage
English
Publisher
ieee
Conference_Titel
Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on
Conference_Location
Beijing
Print_ISBN
0-7803-5747-7
Type
conf
DOI
10.1109/ICOSP.2000.893398
Filename
893398
Link To Document