Abstract—BP neural network not only has the ability of strong nonlinear information processing, but also has the advantage of transform quickly. Because the process of different color space conversion shows high nonlinear, it is reasonable to research color space conversion model by BP neural network. But the color space conversion is complicated, adding that it is easy for BP neural model to appear local optimum phenomenon during the transformation process, so it affects the model transformation precision. 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.
Index Terms—Dynamic space divided; BP neural network; transition of color space; color error
C. Zhi is a Ph.D candidate with the Xi’an University of Technology, Xi’an, 710048, China, and at the same time he is a lecturer of Shaanxi university of science and technology, Xi’an, 710021, China(Email:firstname.lastname@example.org).
S. S. Zhou is a Ph.D. supervisor with the Xi’an University of Technology. He is now the dean of the Faculty of Printing and Packaging Engineering, Xi’an University of Technology, Xi’an, 710048, China.
Y. Shi is a Ph.D. and general manager of Shaanxi Hwatop Science & Technology Co. Ltd, Xi’an, 710043, China
Cite: Zhi Chuan, Zhou Shi-Sheng and Shi Yi, "The Research on Color Space Transfer Model Based on Dynamic Subspace Divided BP Neural Network," International Journal of Engineering and Technology vol. 2, no. 5, pp. 447-452, 2010.