中文摘要：

小或光滑的克隆的区域是困难的在图象拷贝行动被检测伪造品(CMF ) 察觉。瞄准这个问题，一个有效方法基于图象分割和群聪明(SI ) 算法被建议。这个方法分割图象进小 nonoverlapping 块。光滑的度的计算为每块被给。测试图象根据光滑的度被分割进独立的层。SI 算法在为每层发现最佳的察觉参数被使用。这些参数被用来由不变的特征转变的规模检测每层(筛) 基于计划，它能定位 keypoints 的一个团。试验性的结果证明建议方法的好性能，它是有效的与小或光滑的克隆的区域识别 CMF 图象。

英文摘要：

Small or smooth cloned regions are difficult to be detected in image copy-move forgery （CMF） detection. Aiming at this problem, an effective method based on image segmentation and swarm intelligent （SI） algorithm is proposed. This method segments image into small nonoverlapping blocks. A calculation of smooth degree is given for each block. Test image is segmented into independent layers according to the smooth degree. SI algorithm is applied in finding the optimal detection parameters for each layer. These parameters are used to detect each layer by scale invariant features transform （SIFT）-based scheme, which can locate a mass of keypoints. The experimental results prove the good performance of the proposed method, which is effective to identify the CMF image with small or smooth cloned region.