Generalized Benford's Law for Blind Detection of Morphed Face Images

摘要: A morphed face image in a photo ID is serious threat to image-based user verification enabling that multiple persons could be matched with the same document. The application of machine-readable travel documents (MRTD) at automated border control (ABC) gates an example scenario very sensitive this kind fraud. Detection images prior matching is, therefore, indispensable for effective security. We introduce morphing detection approach based on fitting logarithmic curve nine Benford features extracted from quantized DCT coefficients JPEG compressed original and images. separately study parameters background regions establish traces imposed by process. evaluation results show single parameter may sufficient clearly separate