一种新的红外与可见光图像融合算法  

A novel image fusion algorithm for infrared and visible light

作　　者：何国栋[1] 石建平[1] 冯友宏[1] 谢小娟[1] 杨凌云[1] 

机构地区：[1]安徽师范大学物理与电子信息学院,安徽芜湖241000

出　　处：《传感器与微系统》2014年第4期139-141,共3页Transducer and Microsystem Technologies

基　　金：中科院光电技术研究所微细加工光学技术国家重点实验室开放基金资助项目(KFS4);安徽省高校省级自然科学基金资助项目(KJ2011Z138);安徽师范大学校青年基金资助项目(2009XQN64)

摘　　要：提出了一种新的红外与可见光图像融合算法,首先应用非抽样Contourlet变换(NSCT)对图像进行多尺度、多方向变换,对变换的低频子带采用改进的能量加权法融合,带通子带融合采用最大系数与区域方差加权相结合方法,然后对融合的2个子带系数进行NSCT反变换,得到融合图像。对不同算法的融合实验结果进行比较,通过主观和客观评价,该算法融合效果较好。A image novel fusion algorithm for infrared and visible is proposed,firstly,the images are transformed at multi-scales and multi-directions using nonsubsampled contourlet transform （NSCT）,and the transformed low frequency subband is fused by improved energy weighting method,and the bandpass subband coefficients is fused by method combined the maximum coefficients with regional variance weighting,then the fused two subband coefficients is reconstructed by inverse NSCT to get fused image.The fused experimental result of different algorithms are compared,it shows that this algorithm has better fusion effect than other fusion algorithms.

关 键 词：图像融合 非抽样CONTOURLET变换 红外图像 可见光图像 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]