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.