Abstract: Copy-move forgery is one of the most important types of image tampering. But the algorithms in previous study are less robust to rotation, scaling and additive Gaussian noise. In this study, a new approach was purposed for detecting copy-move forgery in digital images which based on the normalized histogram multi-feature vectors. In order to improve the poor robust in detecting the duplicated image regions, the use of the normalized histogram multi-feature vectors of image was proposed to construct feature matrix which is a common component of most proposed copy-move forgery detection schemes. It is proved by experiments that the algorithm can reduce the operand and is provided with the good robust in rotation, scaling and additive Gaussian noise.