非子采样变换域的方向向量约束图像融合算法  

Direction vector constraints image fusion algorithm based on NSCT

作　　者：柳翠寅[1,2] 雷欢[2] 王翠伟[3] 

机构地区：[1]攀枝花学院计算机学院,四川攀枝花617000 [2]四川大学计算机学院,成都610065 [3]昆明理工大学计算中心,昆明650500

出　　处：《计算机应用研究》2013年第10期3172-3174,3177,共4页Application Research of Computers

基　　金：国家自然科学基金资助项目(60736046);国家"973"计划资助项目(2009CB320803)

摘　　要：针对存在的频谱混叠及图像细节信息丢失问题,研究已有基于多尺度分解的多分辨率图像融合方法,提出采用具有移不变性的非子采样轮廓变换对图像进行多尺度、多方向分解,更完整地表征图像的几何结构,同时对滤波器组进行上采样消除频谱混叠。研究已有的子带系数的融合规则,提出了基于方向向量约束对比度的高频系数融合规则,以及基于局部多向方差能量的选择与平均的低频系数融合规则。经多组实验结果表明,该融合方法在视觉上和评价测度指标上都优于已有基于多分辨率图像融合方法。This paper investigated the existence problems of spectrum aliasing and detail lost and proposed a new novel fusion method based on the nonsubsmapled eontourlet transform（NSCT）. It adopted the new decomposition of NSCT, which built up- on nonsubsampled pyramids and nonsubsampled directional filter banks for extracting the geometric information of images. It proposed the high-frequency coefficient fusion rules by combination of direction vector and contrast, and proposed the low-fre- quency fusion rule based on the local energy of multi-direction variance. Experimental results show that the proposed method achieves better fusion results than wavelet-based and CT-based fusion method.

关 键 词：融合 非子采样 方向向量 

分 类 号：TP317.4[自动化与计算机技术—计算机软件与理论]