Search Results (6)

This study improves existing protection strategies for image processing models by embedding invisible watermarks into model outputs to verify the sources of images. Most current methods rely on CNN-based architectures, which are limited by their local perception capabilities and struggle to effectively capture global information. To address this, we introduce the Swin-UNet, originally designed for medical image segmentation tasks, into the watermark embedding process. The Swin Transformer’s ability to capture global information enhances the visual quality of the embedded image compared to CNN-based approaches. To defend against surrogate attacks, data augmentation techniques are incorporated into the training process, enhancing the watermark extractor’s robustness specifically against surrogate attacks. Experimental results show that the proposed watermarking approach reduces the impact of watermark embedding on visual quality. On a deraining task with color images, the average PSNR reaches 45.85 dB, while on a denoising task with grayscale images, the average PSNR reaches 56.60 dB. Additionally, watermarks extracted from surrogate attacks closely match those from the original framework, with an accuracy of 99% to 100%. These results confirm the Swin Transformer’s effectiveness in preserving visual quality. Full article

Watermarking is a viable approach for safeguarding the proprietary rights of digital media. This study introduces an innovative fast Fourier transform (FFT)-based phase modulation (PM) scheme that facilitates efficient and effective blind audio watermarking at a remarkable rate of 508.85 numeric values per second while still retaining the original quality. Such a payload capacity makes it possible to embed a full-color image of 64 × 64 pixels within an audio signal of just 24.15 s. To bolster the security of watermark images, we have also implemented the Arnold transform in conjunction with chaotic encryption. Our comprehensive analysis and evaluation confirm that the proposed FFT–PM scheme exhibits exceptional imperceptibility, rendering the hidden watermark virtually undetectable. Additionally, the FFT–PM scheme shows impressive robustness against common signal-processing attacks. To further enhance the visual rendition of the recovered color watermarks, we propose using residual neural networks to perform image denoising and super-resolution reconstruction after retrieving the watermarks. The utilization of the residual networks contributes to noticeable improvements in perceptual quality, resulting in higher levels of zero-normalized cross-correlation in cases where the watermarks are severely damaged. Full article

This paper introduces the Watermark Imaging System (WImSy) which can be used to photograph, document, and study sheets of paper. The WImSy provides surface images, raking light images, and transmitted light images of the paper, all in perfect alignment. We develop algorithms that exploit this alignment by combining several images together in a process that mimics both the “surface image removal” technique and the method of “high dynamic range” photographs. An improved optimization criterion and an automatic parameter selection procedure streamline the process and make it practical for art historians and conservators to extract the relevant information to study watermarks. The effectiveness of the method is demonstrated in several experiments on images taken with the WImSy at the Metropolitan Museum of Art in New York and at the Getty Museum in Los Angeles, and the results are compared with manually optimized images. Full article

Historical documents such as newspapers, invoices, contract papers are often difficult to read due to degraded text quality. These documents may be damaged or degraded due to a variety of factors such as aging, distortion, stamps, watermarks, ink stains, and so on. Text image enhancement is essential for several document recognition and analysis tasks. In this era of technology, it is important to enhance these degraded text documents for proper use. To address these issues, a new bi-cubic interpolation of Lifting Wavelet Transform (LWT) and Stationary Wavelet Transform (SWT) is proposed to enhance image resolution. Then a generative adversarial network (GAN) is used to extract the spectral and spatial features in historical text images. The proposed method consists of two parts. In the first part, the transformation method is used to de-noise and de-blur the images, and to increase the resolution effects, whereas in the second part, the GAN architecture is used to fuse the original and the resulting image obtained from part one in order to improve the spectral and spatial features of a historical text image. Experiment results show that the proposed model outperforms the current deep learning methods. Full article

This paper presents a novel approach for directly hiding the pixel values of a small color watermark in a carrier color image. Watermark embedding is achieved by modulating the gap of paired coefficient magnitudes in the discrete cosine transform domain according to the intended pixel value, and watermark extraction is the process of regaining and regulating the gap distance back to the intensity value. In a comparison study of robustness against commonly encountered attacks, the proposed scheme outperformed seven watermarking schemes in terms of zero-normalized cross-correlation (ZNCC). To render a better visual rendition of the recovered color watermark, a generative adversarial network (GAN) was introduced to perform image denoising and super-resolution reconstruction. Except for JPEG compression attacks, the proposed scheme generally resulted in ZNCCs higher than 0.65. The employed GAN contributed to a noticeable improvement in perceptual quality, which is also manifested as high-level ZNCCs of no less than 0.78. Full article

A non-uniform distribution of diagnostic information in the electrocardiogram (ECG) has been commonly accepted and is the background to several compression, denoising and watermarking methods. Gaze tracking is a widely recognized method for identification of an observer’s preferences and interest areas. The statistics of experts’ scanpaths were found to be a convenient quantitative estimate of medical information density for each particular component (i.e., wave) of the ECG record. In this paper we propose the application of generalized perceptual features to control the adaptive sampling of a digital ECG. Firstly, based on temporal distribution of the information density, local ECG bandwidth is estimated and projected to the actual positions of components in heartbeat representation. Next, the local sampling frequency is calculated pointwise and the ECG is adaptively low-pass filtered in all simultaneous channels. Finally, sample values are interpolated at new time positions forming a non-uniform time series. In evaluation of perceptual sampling, an inverse transform was used for the reconstruction of regularly sampled ECG with a percent root-mean-square difference (PRD) error of 3–5% (for compression ratios 3.0–4.7, respectively). Nevertheless, tests performed with the use of the CSE Database show good reproducibility of ECG diagnostic features, within the IEC 60601-2-25:2015 requirements, thanks to the occurrence of distortions in less relevant parts of the cardiac cycle. Full article