Detecting Composite JPEG Images in Transform Domain

Compositing is one of the most common forms of digital image tampering. In this paper, we present a passive approach to detect composite JPEG images by measuring inconsistencies of blocking artifacts. Firstly, double-compression detection is performed to estimate the primary quality factor. Secondly, the blocking artifacts ratio mapping is extracted in the DCT domain via computing the blocking artifacts with different block-dividing manners at primary quality factor. Finally, automatic tampering detection and location of tampered region are fulfilled by image segmentation. Experimental results indicate the proposed algorithm is effective to images of various qualities and small tampered regions. With the false positive rate of 1%, the detection accuracy for composite images is above 93% for differences of quality factors before/after tampering larger than 15 and for tampered regions with size 64×64. Furthermore, owing to the elimination of decompression/ compression conversion, the proposed method has advantage of low computational complexity.