CMF-iteMS: An automatic threshold selection for detection of copy-move forgery.

•Performances copy–move forgery (CMF) detection methods against image quality, sizes and attacks in images are studied.•A method is proposed to deal with diverse input of CMF images comprising the variety of image quality, sizes and attacks.•CMF-iteMS introduced automatic threshold selection based on iterative means of regions size as the filtering process.•CMF-iteMS is evaluated on three CMF datasets and compared with four state-of-the-art methods.•The method is able to maintain the highest performance even if the images in the datasets are resized to 0.25 parameter.