一类二维小波构造及在图像融合中的应用  

Construction of a Class of Two-dimensional Wavelets and its Application in Image Fusion

作　　者：刘斌[1,2] 彭嘉雄[2] 王时绘[2] 

机构地区：[1]湖北大学数学与计算机科学学院,武汉430062 [2]华中科技大学图像识别与人工智能研究所,武汉430074

出　　处：《计算机工程与应用》2005年第13期10-13,共4页Computer Engineering and Applications

基　　金：国家自然科学基金(编号:60085002);国家部委科技重点实验室基金;湖北省教育厅重点项目基金(编号:D200510004)

摘　　要：论文提出了一类新的小波-具有紧支撑、线性相位和正交性、伸缩矩阵为200的非张量积小波的一种构造方法,并把此类小波应用于多聚焦图像融合中。首先根据非张量积小波理论,提出了一种设计4通道6×6对称的非张量积小波滤波器组的方法,并用此方法设计出多组具有紧支撑、线性相位和正交性的非张量积小波6×6滤波器组,利用此类滤波器组对参加融合的图像进行滤波;然后利用基于张量积小波的图像融合常用的三种融合规则对图像进行融合。通过研究发现:无论利用三种规则的哪一种对多聚焦图像进行融合,基于该文构造的非张量积小波的融合方法都可得到较好的融合效果。作为例子选用对低频部分和高频部分均采用基于局部窗口激活度量取大的融合算法对分解后的系数图像进行融合;最后重构。并采用熵、均方根误差等指标对融合结果图像进行了评价,实验结果表明,该方法对多聚焦图像的融合有较好的融合效果。其融合性能好于采用相同融合算法的基于张量积Haar小波的融合方法和基于不对称的非张量积小波融合方法。In this paper,a construction method of a new class of wavelets-non-separable wavelet with compactly supported,linear phase,orthogonal and dilation matrix and its application in the fusion of multi-focus images are presented.We first have presented a method constructing a class of 4 channels 6×6 filter bank.Using this class filter bank,We have decomposed the image into low-frequency sub-image and high-frequency sub-images.Then we have fused the multi-focus images using the three fusion rules used in the fusion method of separable wavelets by a lot of experiments,we have found that whichever rule we used,the fusion performance is good.As an example,we use the rule selecting the center pixel value of the local area window which the activity measurement is bigger for the three high-frequency parts of each level.Then new fused image is reconstructed.The performance of the method is evaluated using the Entropy,Error of mean square root.The experiment results show that the method is an effective method.The performance is better than the fusion method based on Haar separable wavelet and the fusion method based on dissymmetrical nonseparable wavelets.

关 键 词：非张量积小波 图像融合 激活度量 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]