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
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;
Conference_Titel :
Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-5747-7
DOI :
10.1109/ICOSP.2000.893398
