A method for detecting watermarks in print using smart phone

Yamada, Takeshi; Kamitani, Motoki

doi:10.1145/2457413.2457425

Cited by 12 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The challenges in this use-case arise because watermark extraction needs to handle multiple combinations of the distortions, such as optical tilt, quality degradation, compression, lens distortions, and lighting variation. Most existing approaches [29], [30], [31], [32] focus on the resamples of printed marked-images, not on phone resamples of a computer monitor screen. This usecase typically involves additional distortions, such as the Moiré pattern (i.e., the RGB ripple), the refresh rate of the screen, and the spatial resolution of a monitor (some examples are mentioned in Fig.…”

Section: E a Case Study: Feasibility Test On Watermark Extraction Frmentioning

confidence: 99%

An Automated and Robust Image Watermarking Scheme Based on Deep Neural Networks

Zhong

Huang

Mastorakis

et al. 2021

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Digital image watermarking is the process of embedding and extracting a watermark covertly on a cover-image. To dynamically adapt image watermarking algorithms, deep learning-based image watermarking schemes have attracted increased attention during recent years. However, existing deep learning-based watermarking methods neither fully apply the fitting ability to learn and automate the embedding and extracting algorithms, nor achieve the properties of robustness and blindness simultaneously. In this paper, a robust and blind image watermarking scheme based on deep learning neural networks is proposed. To minimize the requirement of domain knowledge, the fitting ability of deep neural networks is exploited to learn and generalize an automated image watermarking algorithm. A deep learning architecture is specially designed for image watermarking tasks, which will be trained in an unsupervised manner to avoid human intervention and annotation. To facilitate flexible applications, the robustness of the proposed scheme is achieved without requiring any prior knowledge or adversarial examples of possible attacks. A challenging case of watermark extraction from phone camera-captured images demonstrates the robustness and practicality of the proposal. The experiments, evaluation, and application cases confirm the superiority of the proposed scheme.

show abstract

Section: E a Case Study: Feasibility Test On Watermark Extraction Frmentioning

confidence: 99%

An Automated and Robust Image Watermarking Scheme Based on Deep Neural Networks

Zhong

Huang

Mastorakis

et al. 2021

IEEE Trans. Multimedia

View full text Add to dashboard Cite

show abstract

“…Yamada et al [28] divided the image into regions and embedded the message into these regions with spread spectrum techniques. The locations of the watermark were then detected and the message was extracted only in case of positive detection.…”

Section: Related Workmentioning

confidence: 99%

“…The aim of this research is to focus on one aspect of print-cam robustness inherent to any kind of camera application, namely focusing. Until now, print-cam robust watermarking research has been based on the assumption that the picture is taken as perpendicularly as possible to the watermarked image and that autofocus handles focusing [15,28,7]. This is not the case in general when people take images from papers laying on desks or from the side while standing by their friends.…”

mentioning

confidence: 99%

Extracting watermarks from printouts captured with wide angles using computational photography

Pramila

Keskinarkaus

Takala

et al. 2016

Multimed Tools Appl

View full text Add to dashboard Cite

Thus far the research of print-cam robust watermarking methods has focused on finding new methods for embedding and extracting the watermark. However, the capturing process itself, has been neglected in scientific research. In this paper, we propose a solution for the situation when the watermarked image has been captured in a wide angle and the depth of focus of the camera is not deep enough to capture the whole scene in-focus resulting in unfocused areas. The solution proposed here relies on a subfield of computational photography, namely all-in-focus imaging. All-in-focus images are generated by fusing multiple images from the same scene with different focus distances together, so that the object being photographed is fully in focus. Traditionally, the images to be fused are selected by hand from the focal stack or the whole stack is used for building the all-in-focus image. In mobile phone applications, computational resources are limited and using the full focal stack would result in long processing times and the manual selection of images would not be practical. In addition, we propose a method for optimizing the size of the focal stack and automatically selecting appropriate images for fusion. It is shown here that a watermark can still be recovered from the reconstructed all-in-focus image accurately.

show abstract

“…However, this ink requires special hardware, i.e., blacklight cameras, and can only be applied to analogue print media. The system presented by Yamada and Kamitani [35] can also be used without special hardware. In comparison to the proposed system in Section 3, however, it is restricted to small payloads (64 bits) and short distances between the camera and the image.…”

Section: Visual Data Transfermentioning

confidence: 99%

Using mobile devices to enable visual multiplexing on public displays

Ostkamp

Hülsermann

Kray

et al. 2013

Proceedings of the 12th International Conference on Mobile and Ubiquitous Multimedia

View full text Add to dashboard Cite

Public displays have become ubiquitous in many places regularly visited by large numbers of people (e.g., traffic hubs or malls). In addition to advertising they often provide information related to the location (e.g., time tables). However, individuals can have difficulties to find information relevant to them -either due to information overload or lack of personalization. Multiplexing, as defined in information theory, can help to address this issue by increasing the number of available channels. We propose three methods for visual multiplexing, and report on a controlled lab-based comparison study. Our results indicate that visual multiplexing via mobile devices can be a feasible solution to provide personalized multimedia content on public displays, and that the three methods tested differ in terms of performance. We found that the content type shown has an impact on which method works best, and that self-reported workload differed according to content type and multiplexing method.

show abstract

A method for detecting watermarks in print using smart phone

Cited by 12 publications

References 12 publications

An Automated and Robust Image Watermarking Scheme Based on Deep Neural Networks

An Automated and Robust Image Watermarking Scheme Based on Deep Neural Networks

Extracting watermarks from printouts captured with wide angles using computational photography

Using mobile devices to enable visual multiplexing on public displays

Contact Info

Product

Resources

About