轮廓波和方向小波变换方法的性能比较

摘要

The efficiency of the two-dimensional separable wavelet transform is limited by the spatial isotropy of its basis functions built in the horizontal and vertical directions .The contourlet and directional-wavelet transform are two different multi-scale geometric analysis methods,which can efficiently capture the geometrical structures in images,and are efficient for sparse image representation .The theories of contourlet and directional-wavelet transform are introduced,and their performance are analyzed and compared with each other by their applications in image fusion .%　　轮廓波和方向小波是两种不同的多尺度几何分析方法，弥补了小波方向性的缺失和基的各向同性的缺点，能够更有效地捕捉图像中的几何结构，是有效的图像稀疏表示方法。介绍了轮廓波和方向小波的基本理论，并通过它们在图像融合中的应用来比较它们的性能。