A fuzzy c-means clustering-based fragile watermarking scheme for image authentication

  • Authors:
  • Wei-Che Chen;Ming-Shi Wang

  • Affiliations:
  • Department of Engineering Science, National Cheng Kung University, Tainan 701, Taiwan;Department of Engineering Science, National Cheng Kung University, Tainan 701, Taiwan

  • Venue:
  • Expert Systems with Applications: An International Journal
  • Year:
  • 2009

Quantified Score

Hi-index 12.05

Visualization

Abstract

In recent years, various fragile watermarking schemes have been proposed for image authentication and integrity verification. In this paper, a novel block-based fragile watermarking scheme for image authentication and tamper proofing is proposed. Realizing that block-wise dependency is a basic requirement for fragile watermarking schemes to withstand counterfeiting attacks, the proposed scheme uses the fuzzy c-means (FCM) clustering technique to create the relationship between image blocks. The effectiveness of the proposed scheme is demonstrated through a series of attack simulations. Experimental results show that the proposed scheme not only provides satisfactory imperceptibility, but also achieves superior tamper detection and localization accuracy under different attacks, such as the cut-and-paste attack and the vector quantization (VQ) attack.