As the advent and growing popularity of image editing software, digital images can be manipulated easily without leaving obvious visual clues. If the tampered images are abused, it may lead to potential social, legal or private consequences. To this end, it’s very necessary and also challenging to find effective methods to detect digital image forgeries. In this paper, a fast method to detect image copy-move forgery is proposed based on the SURF (Speed up Robust Features) descriptors, which are invariant to rotation, scaling etc. Results of experiments indicate that the proposed method is valid in detecting the image region duplication and quite robust to additive noise and blurring.