Copy move forgery detection in digital images has become a very popularresearch topic in the area of image forensics. Due to the availability ofsophisticated image editing tools and ever increasing hardware capabilities, ithas become an easy task to manipulate the digital images. Passive forgerydetection techniques are more relevant as they can be applied without the priorinformation about the image in question. Block based techniques are used todetect copy move forgery, but have limitations of large time complexity andsensitivity against affine operations like rotation and scaling. Keypoint basedapproaches are used to detect forgery in large images where the possibility ofsignificant post processing operations like rotation and scaling is more. Ahybrid approach is proposed using different methods for keypoint detection anddescription. Speeded Up Robust Features (SURF) are used to detect the keypointsin the image and Binary Robust Invariant Scalable Keypoints (BRISK) featuresare used to describe features at these keypoints. The proposed method hasperformed better than the existing forgery detection method using SURFsignificantly in terms of detection speed and is invariant to post processingoperations like rotation and scaling. The proposed method is also invariant toother commonly applied post processing operations like adding Gaussian noiseand JPEG compression
展开▼