郑州轻工业学院学报（自然科学版）2012，Vol.27Issue(3)：53-57,5.
一种基于像素清晰度的NSCT域多聚焦图像融合方法
A method for multifocus image fusion in NSCT domain based on pixel clarity
摘要
Abstract
Considering the problem that NSCT-based multiresolution fusion methods may change the reliable information during the process of decomposition and reconstruction, a multifocus image fusion method based on a new pixel clarity measure and NSCT in spatial domain was proposed. According to the characteristics of the human visual system ( HVS) of frequency and direction selectivity, and the distribution difference between the image' s salient features and the noise in NSCT domain, the conception of local directional contrast and directional vector is introduced in the measurement of pixel clarity. Finally based on pixel clarity of the corresponding pixels of the source images, a selection principle is put forward for fusion. Experimental results demonstrated that the proposed method could not only extract more important visual information from source images, but also effectively avoid the introduction of artificial information. It significantly outperforms the traditional image fusion methods.关键词
多聚焦图像融合/像素清晰度/非下采样contourlet变换/局部方向对比度/方向向量Key words
multifocus image fusion/pixel clarity/NSCT/local directional contrast/directional vector分类
信息技术与安全科学引用本文复制引用
时海亮,黄海洋,李刚..一种基于像素清晰度的NSCT域多聚焦图像融合方法[J].郑州轻工业学院学报（自然科学版）,2012,27(3):53-57,5.基金项目
河南省基础与前沿技术研究计划项目(102300410112):河南省教育厅自然科学研究计划项目(2010A520045) （102300410112）
