Detection of duplicated image regions using cellular automata

A common image forgery method is copy-move forgery (CMF), where part of an image is copied and moved to a new location. Identification of CMF can be conducted by detection of duplicated regions in the image. This paper presents a new approach for CMF detection where cellular automata (CA) are used. The main idea is to divide an image into overlapping blocks and use CA to learn a set of rules. Those rules appropriately describe the intensity changes in every block and are used as features for detection of duplicated areas in the image. Use of CA for image processing implies use of pixels' intensities as cell states, leading to a combinatorial explosion in the number of possible rules and subsets of those rules. Therefore, we propose a reduced description based on a proper binary representation using local binary patterns (LBPs). For detection of plain CMF, where no transformation of the copied area is applied, sufficient detection is accomplished by 1D CA. The main issue of the proposed method is its sensitivity to post-processing methods, such as the addition of noise or blurring. Coping with that is possible by pre-processing of the image using an averaging filter.