Research on Dynamic Subspace Divided BP Neural Network Identification Method of Color Space Transform Model

Article Preview

Abstract:

In order to improve the precision for BP neural network model color space conversion, this paper takes RGB color space and CIE L*a*b* color space as an example. Based on the input value, the color space is dynamically divided into many subspaces. To adopt the BP neural network in the subspace can effectively avoiding the local optimum of BP neural network in the whole color space and greatly improving the color space conversion precision.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

97-100

Citation:

Online since:

December 2010

Export:

Price:

[1] Liu Haoxu, Yuan Yuxia: Journal of Beijing Institute of Printing Vol. 7 (1999), p.19.

Google Scholar

[2] Huang Qing-mei, Zhao Da-zun and Guo Jing: Optical Technique Vol. 31 (2005), p.244.

Google Scholar

[3] LOU Wen-gao and KUANG Luo-ping: Opto-Electronic Engineering Vol. 33 (2006), p.118.

Google Scholar

[4] Zhi Chuan and Zhou Shi-Sheng: 2008 International Conference on Computer Science and Software Engineering (2008), p.306.

Google Scholar

[5] Li Xinwu: Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing ( 2007), p.70.

DOI: 10.1109/snpd.2007.9

Google Scholar