中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
A Multi-scale Adaptive Grey World Algorithm

文献类型:期刊论文

作者Li B(李兵)
刊名IEICE Trans. On Inf. & Sys.
出版日期2007
卷号E91-D期号:7页码:1121-1124
关键词Color Constancy
英文摘要Grey world algorithm is a well-known color constancy algorithm. It based on the Grey-World assumption i.e., the average reflectance of surfaces in the world is achromatic. This algorithm is simple and has low computational costs. However, for the few color images, the light source color could not be estimated correctly using the Grey World algorithm. In this paper, we propose a multi-scale adaptive grey world algorithm (MAGW). First,  multi-scale images are obtained based on wavelet transformation and the illumination color is estimated from different scales images. Then according to the estimated illumination color, the original image is mapped into under a canonical illumination with supervision of an adaptive reliability function, which is based on the image entropy. The experimental results show that our algorithm is effective and also has low computational costs.
源URL[http://ir.ia.ac.cn/handle/173211/20381]  
专题自动化研究所_09年以前成果
作者单位Beijing Jiaotong University
推荐引用方式
GB/T 7714
Li B. A Multi-scale Adaptive Grey World Algorithm[J]. IEICE Trans. On Inf. & Sys.,2007,E91-D(7):1121-1124.
APA Li B.(2007).A Multi-scale Adaptive Grey World Algorithm.IEICE Trans. On Inf. & Sys.,E91-D(7),1121-1124.
MLA Li B."A Multi-scale Adaptive Grey World Algorithm".IEICE Trans. On Inf. & Sys. E91-D.7(2007):1121-1124.

入库方式: OAI收割

来源:自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。