基于Contourlet变换的偏振图像融合

提出一种基于Contourlet变换的偏振图像融合算法。Contourlet变换是一种具有几何信息的灵活多尺度、多方向和平移不变性的图像分解变换，与小波变换相比，对图像分析很重要的沿曲面任意方向反映的细节更容易调整。采用Contourlet变换对三个555波段不同方向的偏振图像进行分解，对于高频和低频系数分别采用不同的窗函数计算区域能量，最后加权实现偏振图像的融合处理。实验结果表明，该算法与小波分解法相比在保留原始图像边缘和纹理信息同时，可以体现偏振图像的特点，取得较好的融合视觉效果。

Fusion of polarimetric image based on Contourlet transform

A fusion method for polarimetric image based on Contourlet transform is proposed. Owing to the geometric information, Contourlet transform is a flexible multi-scale, multi-direction and shift-invariant image decomposition. It is easily adjustable for detecting fine details in any orientation along curvatures, which results in more potential for effective analysis of images compared with wavelet transform. The three polarimtric images in 555 nm band are decomposed using Contourlet transform. Low-pass coefficients and the directional high-frequency coefficients, which were calculated with the energy of the corresponding neighbor region, are used to select the better coefficients by weighted sum of algorithm for fusion. Experimental results show that the algorithm can get better visual effect and achieve the virtue of polarimetric image effectively and preserve image details, and the significant information of original image like textures and contour details is well maintained compared with the wavelet transform algorithm.