自动化学报2007，Vol.33Issue(2)：132-137,6.
基于主观对比度的变分图像融合方法
Perceptual Contrast-Based Image Fusion: A Variational Approach
摘要
Abstract
Local contrast, or variation, plays an important role in image fusion which is mainly to preserve the important information from the source images to the fusion result. Weber's law tells us that the same variation under different backgrounds will cause different perceptual feelings, thus an ideal image processor has to take into account the effects of vision psychology and psychophysics. This paper considers the property of human visual system (HVS) and transfers the quantitative perceptual variations from each source image to the result. Using just-noticeable-difference (JND) as measurement, the multiband image's perceptual contrast is obtained as a target. We construct a functional extremum problem to find a single band image, or fusion result, which has the closest perceptual contrast to the target one. Via the variational approach, the Euler-Lagrange equation is derived, and a gradient descent iteration is employed. Experimental results show that this method is perceptually good.关键词
Image fusion/variational approach/perceptual contrast/Weber's law/human visual system (HVS)/partial differential equations (PDEs)Key words
Image fusion/variational approach/perceptual contrast/Weber's law/human visual system (HVS)/partial differential equations (PDEs)分类
信息技术与安全科学引用本文复制引用
王超,叶中付..基于主观对比度的变分图像融合方法[J].自动化学报,2007,33(2):132-137,6.基金项目
Supported by the Graduates Innovation Fund of University of Science and Technology of China (KD2005043). （KD2005043）
