These findings demonstrate that the hybrid DWT – SVD method is effective for ensuring the authenticity of AI-generated content without compromising visual quality, while offering novelty through its integration into the generative pipeline and its support for local language inputs.
Rapid increase in the number of digital multimedia sharing has generated the need for advanced methods for protecting the ownership of images to prevent their reproduction. For this purpose, in this paper, we suggest a hybrid method for digital image watermarking using Discrete Wavelet Transform (DWT) and Singular Value Decomposition (SVD). The watermark is inserted in the LL sub-band in order to find a proper balance between visual transparency and robustness against image manipulations. The suggested method has been implemented in MATLAB R2023b on a set of standard color benchmark images. The performance of this technique has been evaluated using MSE, PSNR, SSIM, NC, and BER metrics. Experimental results show that the watermarking scheme causes only minor image degradation with good image fidelity with the values of PSNR from 38 dB to 51 dB and values of SSIM close to one. Moreover, robustness has been investigated against different image manipulation procedures such as additive Gaussian noise, salt-and-pepper noise, speckle noise, JPEG compression, rotation, and cropping of images. The achieved results show that the suggested hybrid DWT-SVD watermarking scheme can be considered an effective solution for copyright protection of digital images.
Rasha Awad Abtan· International Journal of Adv...· 0 citations
With the innovation, development, and widespread use of today's communication technology, multimedia information such as images can be easily transmitted. Digital image watermarking is a technology that can prevent serious problems such as illegal image editing, fake news, and illegal image distribution. This research will introduce a new dual image watermarking strategy that uses human visual features to ensure image integrity, authorization, and protection. By using human perception features and adjusting the U coefficient in DCT-SVD, the proposed method further improves the existing watermarking process. It aims to generate strong, accurate tampering localization while embedding both watermarked images and proof files into the host image. According to the test results, the proposed scheme shows better performance in generating high uncertainty, robustness, and exposure identification ability compared to other methods when encountering similar images. In addition, the new dual image watermarking strategy provides a good solution for image authentication as it achieves an average sensitivity of 0.9837 and an accuracy of about 0.9836. The watermark quality of this solution reaches a PSNR of 48.41 and an SSIM of 0.9905. In addition, the proposed strategy has achieved strong positive results against various attacks. This solution provides a reliable way to protect digital images with the legal protection and integrity of the original images.
F. Ernawan, M. Hafidz, S. A. Bakar et al.· JOIV: International Journal...· 0 citations
The widespread circulation and reuse of digital images makes it increasingly important to verify whether a given image is still consistent with its original content or has undergone substantial modification. Instead of embedding an explicit ownership identifier, this work introduces a blind, imperceptible digital image watermarking scheme that derives a contentdependent perceptual signature directly from the image itself. The watermark is generated from local luminance statistics and embedded into the singular values of block-wise Singular Value Decomposition (SVD) of the RGB channels using quantization. At verification time, the same procedure is applied to a received image, and the extracted watermark is compared to the freshly regenerated one. Consistency between both indicates that the image has not been drastically altered, while significant discrepancies are expected to reveal strong local modifications or severe processing. Unlike traditional ownership watermarking, our scheme acts as a content-bound, signature-like mechanism: a reproducible, image-internal token derived from local block statistics and re-embodied via quantized SVD coefficients. Experimental results show that the proposed scheme maintains high visual quality and can still detect substantial changes under common signal-processing operations, making it suitable as a baseline for semi-fragile, content-bound perceptual signature mechanisms.
Mareike Meyer, Shashank Shekher Tripathi, Sascha Kaven et al.· International Conference on...· 0 citations
A blind digital watermarking framework based on Discrete Wavelet Transform (DWT) is proposed for secure image authentication and copyright protection. A binary watermark is embedded within the LH subband, and a chaotic map is used to select embedding positions, ensuring high randomness and security. During the extraction, a convolutional neural network (CNN) is applied to the embedded subband and combined with an error correction code to improve recovery performance under attacks. Experimental results on 200 COCO test images demonstrate that, with a magnitude factor of 0.35, the proposed method achieves an average Peak Signal-to-Noise Ratio (PSNR) of 29.46 dB and an SSIM of 0.9189 on 200 COCO test images. The results indicate that the framework achieves stable watermark recovery under blur, Gaussian noise, JPEG compression, and scaling, with high perceptual image quality.
J. Panyavaraporn, Paramate Horkaew· Asia-Pacific Journal of Scie...· 0 citations
In the contemporary digital era, image watermarking is essential for protecting intellectual property due to the widespread unauthorized distribution of digital content. In this work, a robust and efficient image watermarking scheme for copyright protection is proposed. The method integrates wavelet packet decomposition (WPD) with an ensemble of bagged tree classifiers, forming the BT-WPD framework. In the proposed approach, wavelet packet coefficients extracted from each color channel are reorganized into structured batches that capture spatial frequency characteristics, enabling effective watermark embedding in the WPD domain guided by the bagged tree ensemble model. Experimental results demonstrate that the proposed method achieves high imperceptibility, with a peak signal-to-noise ratio (PSNR) exceeding 60 dB, while maintaining strong robustness against various image processing attacks. The method also exhibits low computational complexity during watermark extraction, making it suitable for practical applications. Furthermore, the framework is extended to support Quick Response (QR) code watermark embedding, demonstrating enhanced robustness and versatility for copyright protection in digital media systems.
Current optical image watermarking methods are mostly robust techniques aimed at image copyright protection, and the few existing optical fragile watermarking methods for image tamper detection are almost exclusively designed for natural images. To address these issues, this paper proposes an optical fragile zero-watermarking (ZW) method specifically for medical image tamper detection. In the proposed method, the two-dimensional discrete wavelet transform is first utilized to extract the high-frequency polarity features of the medical host image, which are then combined with the SHA-256 hash algorithm to generate chaotic initial state values. Secondly, these initial values are used to dynamically initialize a novel three-dimensional chaotic system (3D-CCSLM) to generate a chaotic sequence, realizing a ‘one-image-one-key’ security mechanism. Subsequently, a cascaded dual-phase mask architecture is introduced during the watermark’s optical encryption stage, where the original watermark sequentially undergoes double Fresnel diffraction and phase truncation operations to form an optical ciphertext; this ciphertext is then diffused by the chaotic sequence and XORed with the host features to generate a ZW certificate to be stored in the database. Extensive experimental results demonstrate that the proposed scheme achieves complete recovery of the copyright watermark under ideal, attack-free conditions and possesses high algorithmic execution efficiency. By integrating the hash avalanche effect with a cascaded optical encryption architecture, the scheme achieves acute fragility against localized tampering, enabling highly sensitive integrity alarms. Furthermore, the noise-like distribution of the generated ZW effectively neutralizes statistical attacks. Ultimately, this zero-distortion approach provides a highly secure and reliable solution for the authentication and integrity verification of sensitive medical imagery.
