The development of an algorithm to automatically detect ship wakes in digital synthetic aperture radar(SAR)images of the ocean surface is described．Firstly，this algorithm performs a logarithmic transform to convert the multiplicative speckle noise into additive noise，and then performed the nonsubsampled contourlet transform．The coefficients are classified to two types according to the mean value．and then modified to get rid of the noise and check the contours of the ship wakes．The second key element of this technique is a localization of the Radon transform，whereby the intensity integration is performed over short line segments rather than across the entire image．Lastly，the algorithm applies the dilation and erosion mathematical morphology of binary images to the image obtained in order to connect the adjacent line segments．This algorithm is tested by actual SAR images of ship wakes．The resultsdemonstrate that this algorithm's robustness in the presence of noise．as well as its ability to detect and localize linear features that are somewhat not so straight．作者简介：孙继银(1952-),男,山东单县人,教授,博士生导师,研究方向为图像处理、导弹制导.Email:grass2009@163.com