Abstract: An improved fast method based on fractal theory is presented for small and weak target detection in a single-frame image.The algorithm firstly uses the local entropy information to locate the target coarsely,and then a region of interest(ROI) containing the small target is obtained.Secondly,a fractal dimension image of this region is constructed based on the fractal theory.Finally,self-adaptive threshold segmentation is used for the fractal dimension image to get the exact detection result.Compared with the traditional fractal algorithm,the presented method is divided into two parts: coarse location and accurate location.The region to be processed by the fractal algorithm is reduced to a small range that is estimated by local entropy,thus overcoming the defect of huge computational cost and poor anti-noise capability of traditional fractal methods.The experimental results prove that the proposed method is robust,fast and effective for small and weak target detection.