scholarly journals Are Classification Deep Neural Networks Good for Blind Image Watermarking?

Entropy ◽  
2020 ◽  
Vol 22 (2) ◽  
pp. 198 ◽  
Author(s):  
Vedran Vukotić ◽  
Vivien Chappelier ◽  
Teddy Furon
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Deep Neural Networks ◽  
Feature Vector ◽  
Image Watermarking ◽  
Discrete Wavelet ◽  
New Family ◽  
Classical Image ◽  
Blind Image

Image watermarking is usually decomposed into three steps: (i) a feature vector is extracted from an image; (ii) it is modified to embed the watermark; (iii) and it is projected back into the image space while avoiding the creation of visual artefacts. This feature extraction is usually based on a classical image representation given by the Discrete Wavelet Transform or the Discrete Cosine Transform for instance. These transformations require very accurate synchronisation between the embedding and the detection and usually rely on various registration mechanisms for that purpose. This paper investigates a new family of transformation based on Deep Neural Networks trained with supervision for a classification task. Motivations come from the Computer Vision literature, which has demonstrated the robustness of these features against light geometric distortions. Also, adversarial sample literature provides means to implement the inverse transform needed in the third step above mentioned. As far as zero-bit watermarking is concerned, this paper shows that this approach is feasible as it yields a good quality of the watermarked images and an intrinsic robustness. We also tests more advanced tools from Computer Vision such as aggregation schemes with weak geometry and retraining with a dataset augmented with classical image processing attacks.

scholarly journals Off-the-shelf deep learning is not enough, and requires parsimony, Bayesianity, and causality

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Rama K. Vasudevan ◽  
Maxim Ziatdinov ◽  
Lukas Vlcek ◽  
Sergei V. Kalinin
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Bayesian Methods ◽  
Deep Neural Networks ◽  
Applied Research ◽  
Modern Science ◽  
Generative Models ◽  
Knowledge Development ◽  
Physical Constraints

AbstractDeep neural networks (‘deep learning’) have emerged as a technology of choice to tackle problems in speech recognition, computer vision, finance, etc. However, adoption of deep learning in physical domains brings substantial challenges stemming from the correlative nature of deep learning methods compared to the causal, hypothesis driven nature of modern science. We argue that the broad adoption of Bayesian methods incorporating prior knowledge, development of solutions with incorporated physical constraints and parsimonious structural descriptors and generative models, and ultimately adoption of causal models, offers a path forward for fundamental and applied research.

scholarly journals Encryption Based Image Watermarking Algorithm in 2DWT-DCT Domains

Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5540
Author(s):  
Nayeem Hasan ◽  
Md Saiful Islam ◽  
Wenyu Chen ◽  
Muhammad Ashad Kabir ◽  
Saad Al-Ahmadi
Keyword(s):  
Signal To Noise Ratio ◽  
Image Watermarking ◽  
Similarity Index ◽  
Structural Similarity ◽  
Reconstructed Image ◽  
Discrete Wavelet ◽  
Signal To Noise ◽  
Noise Ratio ◽  
Watermarking Scheme

This paper proposes an encryption-based image watermarking scheme using a combination of second-level discrete wavelet transform (2DWT) and discrete cosine transform (DCT) with an auto extraction feature. The 2DWT has been selected based on the analysis of the trade-off between imperceptibility of the watermark and embedding capacity at various levels of decomposition. DCT operation is applied to the selected area to gather the image coefficients into a single vector using a zig-zig operation. We have utilized the same random bit sequence as the watermark and seed for the embedding zone coefficient. The quality of the reconstructed image was measured according to bit correction rate, peak signal-to-noise ratio (PSNR), and similarity index. Experimental results demonstrated that the proposed scheme is highly robust under different types of image-processing attacks. Several image attacks, e.g., JPEG compression, filtering, noise addition, cropping, sharpening, and bit-plane removal, were examined on watermarked images, and the results of our proposed method outstripped existing methods, especially in terms of the bit correction ratio (100%), which is a measure of bit restoration. The results were also highly satisfactory in terms of the quality of the reconstructed image, which demonstrated high imperceptibility in terms of peak signal-to-noise ratio (PSNR ≥ 40 dB) and structural similarity (SSIM ≥ 0.9) under different image attacks.

scholarly journals A Fuzzy Controlled Image Watermarking Based on a Dual Transform Technique

2016 ◽  
Vol 5 (1) ◽  
pp. 83-92
Author(s):  
Bander Albarakati, Abdullah Basuhail, Gibrael Abo Samra Bander Albarakati, Abdullah Basuhail, Gibrael Abo Samra
Keyword(s):  
Fuzzy Logic ◽  
Spread Spectrum ◽  
Image Watermarking ◽  
Error Correcting Code ◽  
Recovery Process ◽  
Discrete Wavelet ◽  
Hybrid Watermarking ◽  
High Level ◽  
Code Division Multiple

This paper presents a new watermarking technique using hybrid image transforms that aims to be very robust against attacks. It also aims to reduce the amount of distortion created from embedding the watermark as much as possible, and have good capacity. The proposed system uses a hybrid watermarking technique that is based on Non-Subsampled Contourlet Transform and Discrete Wavelet Transform. In addition, the proposed system makes use of the fuzzy logic to automatically choose the strength of the embedded watermark. Furthermore, the system uses Spread Spectrum Code Division Multiple Access to embed and recover the watermark after transforming the image. To enhance recoverability of the watermarks, the system uses a high level of redundancy in the embedding process, which allows a powerful Error Correcting Code to be used in the recovery process. The fuzzy logic is used to help the system in producing watermarked images that reserve their quality and not be heavily altered after embedding the watermark. Experiments were performed to measure the quality of the proposed system using JPEG compression attacks. The results showed that the proposed system is robust and has good capacity and imperceptibly although it suffers from being computationally complex.

scholarly journals Label Distribution for Learning with Noisy Labels

2020 ◽  
Author(s):  
Yun-Peng Liu ◽  
Ning Xu ◽  
Yu Zhang ◽  
Xin Geng
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Confidence Estimation ◽  
Novel Method ◽  
Real World Datasets ◽  
Label Distribution ◽  
Noisy Labels

The performances of deep neural networks (DNNs) crucially rely on the quality of labeling. In some situations, labels are easily corrupted, and therefore some labels become noisy labels. Thus, designing algorithms that deal with noisy labels is of great importance for learning robust DNNs. However, it is difficult to distinguish between clean labels and noisy labels, which becomes the bottleneck of many methods. To address the problem, this paper proposes a novel method named Label Distribution based Confidence Estimation (LDCE). LDCE estimates the confidence of the observed labels based on label distribution. Then, the boundary between clean labels and noisy labels becomes clear according to confidence scores. To verify the effectiveness of the method, LDCE is combined with the existing learning algorithm to train robust DNNs. Experiments on both synthetic and real-world datasets substantiate the superiority of the proposed algorithm against state-of-the-art methods.

Survey on Energy-Efficient Deep Neural Networks for Computer Vision

2022 ◽  
pp. 25-52
Author(s):  
Abhinav Goel ◽  
Caleb Tung ◽  
Xiao Hu ◽  
Haobo Wang ◽  
Yung-Hsiang Lu ◽  
...  
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Energy Efficient ◽  
Deep Neural Networks
Sign in / Sign up

Export Citation Format

Share Document