DocumentCode
1749200
Title
A new approach of color quantization of image based on neural network
Author
Wu, Yingqian ; Yang, Cuiping ; Wang, Tianzhen
Author_Institution
Inst. of Image Process. & Pattern Recognition, Shanghai Jiaotong Univ., China
Volume
2
fYear
2001
fDate
2001
Firstpage
973
Abstract
In the paper, a new algorithm using a competitive Hopfield neural network for color quantization is proposed, and it completes two tasks of color palette design and pixels color mapping based on the pixel color value distribution. Results of the experiment show that the approach has the advantages of fast convergent speed and high quantization
Keywords
Hopfield neural nets; convergence; image colour analysis; minimisation; quantisation (signal); unsupervised learning; Hopfield neural network; color palette; color quantization; competitive neural network; convergence; minimisation; pixel color value distribution; pixels color mapping; winner takes all learning; Algorithm design and analysis; Color; Hopfield neural networks; Image converters; Image processing; Neural networks; Paper technology; Pattern recognition; Pixel; Quantization;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location
Washington, DC
ISSN
1098-7576
Print_ISBN
0-7803-7044-9
Type
conf
DOI
10.1109/IJCNN.2001.939492
Filename
939492
Link To Document