Multi-Scale Image Hashing Using Adaptive Local Feature Extraction For Robust Tampering Detection

The main problem addressed in this paper is the robust tampering detection of the image received in a transmission under various content-preserving attacks. To this aim the multi-scale image hashing method is proposed by using the location-context information of the features generated by adaptive and local feature extraction techniques. The generated hash is attached to the image before transmission and analyzed at destination to filter out the geometric transformations occurred in the received image by image restoration firstly. Based on the restored image, the image authentication using the global and color hash component is performed to determine whether the received image has the same contents as the trusted one or has been maliciously tampered, or just different. After regarding the received image as being tampered, the tampered regions will be localized through the multi-scale hash component. Lots of experiments are conducted to indicate that our tampering detection scheme outperforms the existing state-of-the-art methods and is very robust against the content-preserving attacks, including both common signal processing and geometric distortions. (C) 2015 Elsevier B.V. All rights reserved.