Copy-Move Forgery Detection by Matching Triangles of Keypoints

— Copy-move forgery is one of the most common types of tampering for digital images. Detection methods generally use block-matching approaches, which first divide the image into overlapping blocks and then extract and compare features to find similar ones, or point-based approaches, in which relevant keypoints are extracted and matched to each other to find similar areas. In this paper we present a very novel hybrid approach, which compares triangles rather than blocks, or single points. Interest points are extracted from the image and objects are modeled as a set of connected triangles built onto these points. Triangles are matched according to their shapes (inner angles), their content (color information), and the local feature vectors extracted onto the vertices of the triangles. Our methods are designed to be robust to geometric transformations. Results are compared with a state-of-the-art block matching method and a point-based method. Furthermore, our dataset is available for use by academic researchers. I. INTRODUCTION AND STATE OF THE ART igital Image Forensics deals with the problem of certifying the authenticity of a picture, or its origin. An image has always implied the truth of what it represents. The advent of digital pictures and relative ease of digital image processing makes today this authenticity uncertain. The same tools, used to crop an image, eliminate " red-eye " or simply improve an image, can also be used to doctor images with despicable intent, creating an image that is not a representation of the reality. Digital images can be manipulated in such a perfect way that the forgery cannot be visually perceived by naked eye. Nowadays, in our society, we can come in contact with a lot of tampered images, in news report, business, law, military affairs, academic research. More particularly, tampered images could be used to distort the truth in news reports, to destroy someone's reputation and privacy, e.g. by changing a face of a person in a