Image copy-move forgery detection based on polar cosine transform and approximate nearest neighbor searching

• Published in: Forensic science international Vol. 224; no. 1-3; pp. 59 - 67
• Main Author: Li, Yuenan
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ireland Ltd 10.01.2013; Elsevier; Elsevier Limited
• Subjects: Accuracy; Algorithms; Approximation; Authentication; Biological and medical sciences; Copy-move forgery; detection; Duplicated region detection; Forensic medicine; Forensic sciences; Forgery; General aspects; Genital system. Mammary gland; image analysis; Image forensics; Investigative techniques, diagnostic techniques (general aspects); Medical sciences; Missiles; Pathology; Pathology. Cytology. Biochemistry. Spectrometry. Miscellaneous investigative techniques; Post-processing; Principal components analysis; Public health. Hygiene; Public health. Hygiene-occupational medicine; Reproduction; Robustness; Searching; Studies; tampering; Transforms; Duplicated region detection; Image forensics; Authentication; Copy-move forgery; Transformation; Forensic science; Legal medicine; Forensic aspect; Diagnosis; Detection; Image
• ISSN: 0379-0738; 1872-6283; 1872-6283
• DOI: 10.1016/j.forsciint.2012.10.031

Copy-move is one of the most commonly used image tampering operation, where a part of image content is copied and then pasted to another part of the same image. In order to make the forgery visually convincing and conceal its trace, the copied part may subject to post-processing operations such as rotation and blur. In this paper, we propose a polar cosine transform and approximate nearest neighbor searching based copy-move forgery detection algorithm. The algorithm starts by dividing the image into overlapping patches. Robust and compact features are extracted from patches by taking advantage of the rotationally-invariant and orthogonal properties of the polar cosine transform. Potential copy-move pairs are then detected by identifying the patches with similar features, which is formulated as approximate nearest neighbor searching and accomplished by means of locality-sensitive hashing (LSH). Finally, post-verifications are performed on potential pairs to filter out false matches and improve the accuracy of forgery detection. To sum up, the LSH based similar patch identification and the post-verification methods are two major novelties of the proposed work. Experimental results reveal that the proposed work can produce accurate detection results, and it exhibits high robustness to various post-processing operations. In addition, the LSH based similar patch detection scheme is much more effective than the widely used lexicographical sorting.