基于多尺度积视觉特性的多聚焦图像融合算法  

Multifocus image fusion algorithm based on multiscale products and property of human visual system

作　　者：李华锋[1] 柴毅[1] 张晓阳[1] 

机构地区：[1]重庆大学自动化学院,重庆400044

出　　处：《控制与决策》2012年第3期355-361,共7页Control and Decision

基　　金：国家自然科学基金项目(60974090);教育部博士点基金项目(102063720090013);中央高校基本科研业务费基金项目(CDJXS10172205)

摘　　要：针对传统多尺度图像融合算法不能有效抑制噪声的缺陷,提出一种基于提升静态小波变换(LSWT)多尺度积的多聚焦图像融合算法,并在LSWT域中引入了局部可见度以及局部视觉特性对比度的概念.在融合低频子带系数和各高频子带系数时,分别提出了基于局部可见度和基于多尺度积的局部视觉特性对比度的系数选择方案.实验表明,该算法不仅能有效抑制噪声对融合算法的影响,而且能够得到比传统方法视觉效果更好和更优量化指标的融合图像.In order to overcome the drawbacks of the traditional multiscale transform based image fusion algorithm which cannot restrain the noise influence, a multifocus image fusion method is proposed based on the multiscale products of lifting stationary wavelet transform（LSWT）. At the same time, the local visibility and the local visual properties contrast of the multiscale products are proposed for the fusion of the low frequency subband coefficients and the high frequency subbands coefficients, respectively. Experimental results show that the proposed algorithm not only can restrain the noise influence, but also can provide a better performance in terms of both visual quality and objective evaluation, compared with the traditional fusion methods.

关 键 词：图像融合 提升静态小波变换 局部可见度 视觉特性对比度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]