With the maturity of image editing software, image content has been forged frequently, posing potential threats to many critical fields. To detect forgery images effectively, this paper proposes an image copy-move forgery detection (CMFD) method based on speeded-up robust feature (SURF) and polar complex exponential transform (PCET). Firstly, image is divided into non-overlapping irregular image blocks by superpixel segmentation. Then, these image blocks are separated into two categories: smooth regions and texture regions. Secondly, after finding the keypoints by SURF, the PCET coefficients are extracted and utilized for searching similar features by feature matching algorithm. Thirdly, a strategy is used to eliminate false matched points and find the regions with dense matched points. It combines the random sample consensus (RANSAC) algorithm and a filtering scheme. Finally, mathematical morphology and an iterative strategy are adopted to refine the tampered regions. Compared with other CMFD methods, the proposed method can detect the forgery which occurs in high-brightness smooth regions or forgery images involving similar but genuine regions. Experimental results also indicate the proposed method can resist different distortions by various attacks, including rotation, scaling, blurring, joint photographic expert group (JPEG) compression, and noise addition.INDEX TERMS Image forensics, image copy-move forgery detection (CMFD), speeded-up robust feature (SURF), polar complex exponential transform (PCET), superpixel segmentation.

With the increasing importance of image information, image forgery seriously threatens the security of image content. Copy-move forgery detection (CMFD) is a greater challenge because its abnormality is smaller than other forgeries. To solve the problem that the detection results of the most image CMFD based on convolutional neural networks (CNN) have relatively low accuracy, an image copy-move forgery detection and localization based on super boundary-to-pixel direction (super-BPD) segmentation and deep CNN (DCNN) is proposed: SD-Net. Firstly, the segmentation technology is used to enhance the connection between the same or similar image blocks, improving the detection accuracy. Secondly, DCNN is used to extract image features, replacing conventional hand-crafted features with automatic learning features. The feature pyramid is used to improve the robustness to the scaling attack. Thirdly, the image BPD information is used to optimize the edges of rough detected image and obtain final detected image. The experiments proved that the SD-Net could detect and locate multiple, rotated, and scaling forgery well, especially large-level scaling forgery. Compared with other methods, the SD-Net is more accurately located and robust to various post-processing operations: brightness change, contrast adjustments, color reduction, image blurring, JPEG compression, and noise adding.