Aiming at the characteristics of side-scan sonar image，such as serious noise interference，low resolution and fuzzy target contour，a detection algorithm of underwater small target in side-scan sonar image based on LOG operator is proposed. Firstly，according to the imaging characteristics of the underwater small target in the side-scan sonar image，the sonar image is filtered and segmented by clustering，which greatly reduce the noise in the images. Secondly，the suspected target area in the side-scan sonar image is extracted by using the speckle detection idea. Finally，the sonar image is segmented based on the automatic threshold segmentation algorithm to obtain the binary image of the target area，and then the false targets is eliminated though estimating the target scale by using the second-order moment. Finally the accurate detection of underwater small targets is achieved. The experimental results show that the method has fast calculation speed and high detection success rate，with good detection effect on underwater small targets in side-scan sonar image.