No way to crop: On robust image crop localization

10/12/2021

∙

by   Qichao Ying, et al.

∙

0

∙

share

Previous image forensics schemes for crop detection are only limited on predicting whether an image has been cropped. This paper presents a novel scheme for image crop localization using robust watermarking. We further extend our scheme to detect tampering attack on the attacked image. We demonstrate that our scheme is the first to provide high-accuracy and robust image crop localization. Besides, the accuracy of tamper detection is comparable to many state-of-the-art methods.