Abstract: This paper suggests a removing approach of thick cloud and cloud shadow in remote sensing image based on support vector machine. Firstly, the learning ability of support vector machine is used to detect cloud in remote sensing image, and combining the information of solar angle, cloud shadow area is detected. So the binary images of cloud and its shadow are obtained. Secondly, the remote sensing images are transformed by support vector value contourlet transform. The transforming cofficients are mosaiced using selection matrices produced by the binary images to achieved preliminary removal of cloud and its shadow. The cloud and its shadow which can not be removed by image mosaic are repaired by using the method of statistics. Finally, thick cloud and its shadow are removed by reconstructing image and using median filter. Experiments show that the method proposed in this paper can better recover the ground information covered by cloud and the cloud removal image have better image smoothness and image definition.