A SIFT-based image fingerprinting approach robust to geometric transformations

摘要

Among approaches in implementing digital rights management, image fingerprinting technique is considered to be one of the most attractive solutions, especially in detecting illegal use of image works. The deficiency of the existing image fingerprinting methods is that they can not deal with geometric transformations, such as aspect ratio changes, rotations, cropping, combining, etc. Aiming at this shortcoming, we propose a SIFT-based image fingerprinting algorithm which is robust to geometric transformations. Firstly, we introduce SIFT-based algorithm to extract features as a unique fingerprint. Secondly, a method based on area ratio invariance of affine transformation is utilized to verify valid matched keypoint pairs between the queried image and the pre-registered image. Finally, by counting the valid matched pairs, we estimate whether the two images are homologous or not. Experimental results demonstrate that the proposed method exhibits an excellent performance when geometric transformation occurs.