Dual Image Watermarking Based On Human Visual Characteristics For Authentication And Copyright Protection

Wong, Shu Jie (2023) Dual Image Watermarking Based On Human Visual Characteristics For Authentication And Copyright Protection. Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah.

[img]
Preview
Pdf
CD20137.pdf - Accepted Version

Download (3MB) | Preview

Abstract

Nowadays, multimedia content like images are easily to be distributed globally because of the widespread usage of information and communication technologies. Digital watermarking is an approach to prevent attacks or modification on images that might lead to serious problems like spreading of fake news, image piracy and illegal distribution of images. This research presents a novel Dual Image Watermarking scheme based on human visual characteristics for authentication and copyright protection. The objective of this proposed scheme is to develop an enhanced watermarking algorithm that achieves high imperceptibility and robustness by leveraging the principles of human visual system characteristics. The scheme aims to embed two watermarks into an image with minimal distortion, rendering them imperceptible to the human eye. Furthermore, the watermarks can be extracted accurately even after image processing attacks such as Gaussian noise or salt and pepper noise. Additionally, the scheme demonstrates efficient tamper localization, enabling the detection of modifications made to the original image with high accuracy, precision, and F1-score. Experimental results validate the effectiveness of the proposed scheme, showcasing superior performance in terms of imperceptibility, robustness, and tamper localization compared to existing watermarking schemes subjected to the same attacks. The scheme's ability to embed undetectable watermarks ensures copyright protection and authenticity verification, while its robustness against various image processing attacks enhances its practicality in real-world scenarios. In conclusion, the proposed Dual Image Watermarking scheme based on human visual characteristics provides an effective solution for authentication and copyright protection. By ensuring imperceptibility, robustness, and tamper localization, the scheme offers a reliable approach for securing digital multimedia content in the era of widespread information distribution and technological advancements.

Item Type: Undergraduates Project Papers
Additional Information: SV: Prof. Madya Ts. Dr. Ferda Ernawan
Uncontrolled Keywords: Digital watermarking
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Faculty/Division: Faculty of Computing
Depositing User: Mr. Nik Ahmad Nasyrun Nik Abd Malik
Date Deposited: 18 Mar 2024 04:22
Last Modified: 18 Mar 2024 04:22
URI: http://umpir.ump.edu.my/id/eprint/40697
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item