Name
Abstract | ||
|---|---|---|
In the past few years, various fragile watermarking systems have been proposed for image authentication and tamper detection. In this paper, we propose a rough k-means (RKM) fragile watermarking approach with a block-wise dependency mechanism which can detect any alterations made to the protected image. Initially, the input image is divided into blocks with equal size in order to improve image tamper localization precision. By combining image local properties with human visual system, authentication data are acquired. By computing the class membership degree of each image block property, data are generated by applying rough k-means clustering to create the relationship between all image blocks and cluster all of them. The embed watermark is carried by least significant bits (LSBs) of each pixel within each block. The effectiveness of the proposed approach is demonstrated through a series simulations and experiments. Experimental results show that the proposed approach can embed watermark without causing noticeable visual artifacts, and does not only achieve superior tamper detection in images accurately, it also recovers tampered regions effectively. In addition, the results show that the proposed approach can effectively thwart different attacks, such as the cut-and paste attack and collage attack, while sustaining superior tamper detection and localization accuracy. Furthermore, the results show that the proposed approach can embed watermark without causing noticeable visual artifacts. |
Year | Venue | Keywords |
|---|---|---|
2011 | Computer Science and Information Systems | image watermarking,pattern clustering,rough set theory,block-wise dependency mechanism,class membership degree,collage attack,cut-and paste attack,human visual system,image authentication,image local properties,image tamper localization precision,least significant bits,rough k-means clustering,rough k-means fragile watermarking approach,tamper detection |
Field | DocType | ISBN |
Data mining,k-means clustering,Computer vision,Visual artifact,Digital watermarking,Authentication,Human visual system model,Computer science,Watermark,Pixel,Artificial intelligence,Cluster analysis | Conference | 978-83-60810-35-4 |
Citations | PageRank | References |
2 | 0.37 | 4 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Lamiaa M. El Bakrawy | 1 | 2 | 0.37 |
| Neveen I. Ghali | 2 | 2 | 0.37 |
| ella Hassanien, A. | 3 | 36 | 4.57 |
| Tai-hoon Kim | 4 | 2 | 0.37 |