In this paper, an Adaptive Polar based Filtering Method is proposed for image copy-move forgery detection. In order to improve the performance of detection method, the post-processing of the matching results is worth being focused on. To filter out the redundant pixels from the initially matched pixels, two pixels sets-Symmetrical Matched Pixels set and Unsymmetrical Matched Pixels set, are extracted from the matched pixel pairs, furthermore, the polar distributions of the two sets are calculated respectively. Then, the filtering thresholds can be adaptively calculated according to the polar distribution, thus the redundant pixels can be filtered out accordingly. Finally, some morphological operations are applied to the remained pixels to generate the detected forged regions. Experimental results show that the proposed scheme can achieve much better detection results compared with the existing state-of-the-art copy-move forgery detection methods.