Tools
Tools
Tidke, Aishwarya (2023) Image Ownership Protection Through Hybrid Approach. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (1MB) | Preview |
Abstract
Protecting images from cyber attacks on social media has become a challenge as technology evolves. The growing concerns over preserving the ownership of digital photos uploaded online are addressed by this research. The study presents a novel and hybrid approach that includes techniques for frequency domain digital watermarking, such as RDWT (Redundant Discreet Wavelet Transform) and SVD (Singular Value Decomposition), as well as other techniques like XChaCha20- Poly1305 that have never been used before in relation to digital watermarking, chaotic logistic mapping, and Huffman coding that securely conceals ownership information in images, making it difficult for others to alter or steal them, especially on social media. The research embeds watermarks resistant to common modifications such as noise and compression. Experiments show that this hybrid strategy is effective at preserving image quality while also ensuring robust security, with evaluation metrics such as a Peak signal-to-noise ratio (PSNR) of 46 dB, a Structural Similarity Index (SSIM) of around 1, and resistance to noise, filtering, and JPEG compression attacks when compared to existing approaches. Overall, this research outlines improved imperceptibility and robustness by providing a scalable method of managing digital rights, stimulating additional developments in the domain of image ownership protection. The paper also notes its limitations in terms of countering increasingly sophisticated attacks and makes it suitable for a wider range of media such as video and audio.
Actions (login required)
 |
View Item |