| Autor: |
Fernandez, Jincy J., P., Nithyanandam |
| Předmět: |
|
| Zdroj: |
Multimedia Tools & Applications; May2024, Vol. 83 Issue 17, p52405-52431, 27p |
| Abstrakt: |
Online image theft is a severe concern faced by many photographers. It occurs when someone uses the photo they took accidentally or deliberately without getting the permission of the owner of the photo. One of the solutions to prevent online image theft is to use biometric watermarking on the photo to be protected. The proposed work integrates multimodal biometric watermarking, Lifting Wavelet Transform (LWT), and score-level fusion using Triangular Norms to achieve better accuracy. Using block-based representatives from LWT coefficients for embedding preserves the visual quality of the watermarked image. By considering the iris and fingerprint images from the multimodal biometric database, SDUMLA-HMT, the proposed approach tests the watermarked images against many attacks and is proven to attack resilience. Moreover, the proposed system tests watermark imperceptibility and are proven not to affect the watermarked image's visual quality. The proposed system has also achieved a better accuracy rate regarding low False Acceptance Rate and False Rejection Rate. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
Full text from SpringerLink