Fragile watermarking for image tamper detection and localization with effective recovery capability using K-means clustering

The continuous development of forgery attacks on critical multimedia applications necessitates having accurate image tamper detection and localization techniques. In this paper, an image authentication approach is designed using a block-based fragile watermarking. Moreover, an effective recovery technique based on unsupervised machine learning is proposed. The authentication data is generated, for each 8 × 8 image block, using the Discrete Cosine Transform. A block dependency is established, for authenticating an image block, through using part of the authentication data of a distant block. Such block-dependency provides more accurate tamper detection and enables precise localization of tampered regions. At the recovery phase, a block is divided into smaller sub-blocks of size 2 × 2, where the recovery data is calculated through the K-means clustering. A fragile watermarking, in the spatial domain, is employed for embedding the watermark that is generated from the authentication and recovery data. We examine the effectiveness of the proposed approach under some of the most common attacks of image tampering, including copy move, constant average, and vector quantization attacks. Our approach is compared with several existing methods. Experimental results show that the proposed technique provides superior tampering detection and localization performance, and is capable of recovering the tampered regions more effectively.