PROJECT TITLE :

A Visual Model-Based Perceptual Image Hash for Content Authentication

ABSTRACT:

Perceptual image hash has been widely investigated in an attempt to unravel the problems of image content authentication and content-based mostly Image Retrieval. In this paper, we combine statistical analysis ways and visual perception theory to develop a true perceptual image hash methodology for content authentication. To realize real perceptual robustness and perceptual sensitivity, the proposed methodology uses Watson’s visual model to extract visually sensitive options that play an vital role in the method of humans perceiving image content. We have a tendency to then generate sturdy perceptual hash code by combining image-block-based mostly options and key-point-based options. The proposed methodology achieves a tradeoff between perceptual robustness to tolerate content-preserving manipulations and a wide selection of geometric distortions and perceptual sensitivity to detect malicious tampering. Furthermore, it has the functionality to detect compromised image regions. Compared with state-of-the-art schemes, the proposed technique obtains a higher comprehensive performance in content-based mostly image tampering detection and localization.