A Flexible Deep CNN Framework for Image Restoration

Jin, Zhi; Iqbal, Muhammad; Bobkov, Dmytro; Zou, Wenbin; Li, Xia; Steinbach, Eckehard

doi:10.1109/tmm.2019.2938340

Cited by 87 publications

(27 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most denoisers are designed for a given primary noise. The most addressed distribution is Additive White Gaussian Noise (AWGN) [14], [17], [18]. To challenge denoisers and approach real-world cases, different types of mixture noises have been proposed in the literature.…”

Section: Related Workmentioning

confidence: 99%

NoiseBreaker: Gradual Image Denoising Guided by Noise Analysis

Lemarchand

Findeli

Nogues

et al. 2020

2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)

View full text Add to dashboard Cite

Fully supervised deep-learning based denoisers are currently the most performing image denoising solutions. However, they require clean reference images. When the target noise is complex, e.g. composed of an unknown mixture of primary noises with unknown intensity, fully supervised solutions are hindered by the difficulty to build a suited training set for the problem.This paper proposes a gradual denoising strategy called NoiseBreaker that iteratively detects the dominating noise in an image, and removes it using a tailored denoiser. The method is shown to strongly outperform state of the art blind denoisers on mixture noises. Moreover, noise analysis is demonstrated to guide denoisers efficiently not only on noise type, but also on noise intensity. NoiseBreaker provides an insight on the nature of the encountered noise, and it makes it possible to update an existing denoiser with novel noise profiles. This feature makes the method adaptive to varied denoising cases.

show abstract

Section: Related Workmentioning

confidence: 99%

NoiseBreaker: Gradual Image Denoising Guided by Noise Analysis

Lemarchand

Findeli

Nogues

et al. 2020

2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)

View full text Add to dashboard Cite

show abstract

“…The aforementioned observation was proven by several researchers [3][4][5][6][7][8][9][10][11][12][13][14]. DL is beneficial in other fields, including target recognition [15], speech recognition [16,17], image recognition [18][19][20], image restoration [21][22][23], audio classification [24,25], object detection [26][27][28][29][30], scene recognition [31], etc., but it has been considered "bad news" in text-based CAPTCHAs, by penetrating their security and making them vulnerable.…”

Section: Introductionmentioning

confidence: 98%

Securing IoT Devices: A Robust and Efficient Deep Learning with a Mixed Batch Adversarial Generation Process for CAPTCHA Security Verification

Dankwa

Yang

2021

Electronics

View full text Add to dashboard Cite

The Internet of Things environment (e.g., smart phones, smart televisions, and smart watches) ensures that the end user experience is easy, by connecting lives on web services via the internet. Integrating Internet of Things devices poses ethical risks related to data security, privacy, reliability and management, data mining, and knowledge exchange. An adversarial machine learning attack is a good practice to adopt, to strengthen the security of text-based CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart), to withstand against malicious attacks from computer hackers, to protect Internet of Things devices and the end user’s privacy. The goal of this current study is to perform security vulnerability verification on adversarial text-based CAPTCHA, based on attacker–defender scenarios. Therefore, this study proposed computation-efficient deep learning with a mixed batch adversarial generation process model, which attempted to break the transferability attack, and mitigate the problem of catastrophic forgetting in the context of adversarial attack defense. After performing K-fold cross-validation, experimental results showed that the proposed defense model achieved mean accuracies in the range of 82–84% among three gradient-based adversarial attack datasets.

show abstract

“…Recently, deep learning, which is a subfield in machine learning [6], is one of the demanded areas in artificial intelligence research. Deep learning has achieved good performance and great success in many applications such as scene recognition [7], image recognition [8], object detection [9][10][11][12][13], and image restoration [14][15][16]. In contrast to the traditional pattern recognition technique, the huge advantage of deep learning is its effectiveness in learning features actively without artificial design [2].…”

Section: Introductionmentioning

confidence: 99%

An Efficient and Accurate Depth-Wise Separable Convolutional Neural Network for Cybersecurity Vulnerability Assessment Based on CAPTCHA Breaking

Dankwa

Yang

2021

Electronics

View full text Add to dashboard Cite

Cybersecurity practitioners generate a Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHAs) as a form of security mechanism in website applications, in order to differentiate between human end-users and machine bots. They tend to use standard security to implement CAPTCHAs in order to prevent hackers from writing malicious automated programs to make false website registrations and to restrict them from stealing end-users’ private information. Among the categories of CAPTCHAs, the text-based CAPTCHA is the most widely used. However, with the evolution of deep learning, it has been so dramatic that tasks previously thought not easily addressable by computers and used as CAPTCHA to prevent spam are now possible to break. The workflow of CAPTCHA breaking is a combination of efforts, approaches, and the development of the computation-efficient Convolutional Neural Network (CNN) model that attempts to increase accuracy. In this study, in contrast to breaking the whole CAPTCHA images simultaneously, this study split four-character CAPTCHA images for the individual characters with a 2-pixel margin around the edges of a new training dataset, and then proposed an efficient and accurate Depth-wise Separable Convolutional Neural Network for breaking text-based CAPTCHAs. Most importantly, to the best of our knowledge, this is the first CAPTCHA breaking study to use the Depth-wise Separable Convolution layer to build an efficient CNN model to break text-based CAPTCHAs. We have evaluated and compared the performance of our proposed model to that of fine-tuning other popular CNN image recognition architectures on the generated CAPTCHA image dataset. In real-time, our proposed model used less time to break the text-based CAPTCHAs with an accuracy of more than 99% on the testing dataset. We observed that our proposed CNN model has efficiently improved the CAPTCHA breaking accuracy and streamlined the structure of the CAPTCHA breaking network as compared to other CAPTCHA breaking techniques.

show abstract

A Flexible Deep CNN Framework for Image Restoration

Cited by 87 publications

References 56 publications

NoiseBreaker: Gradual Image Denoising Guided by Noise Analysis

NoiseBreaker: Gradual Image Denoising Guided by Noise Analysis

Securing IoT Devices: A Robust and Efficient Deep Learning with a Mixed Batch Adversarial Generation Process for CAPTCHA Security Verification

An Efficient and Accurate Depth-Wise Separable Convolutional Neural Network for Cybersecurity Vulnerability Assessment Based on CAPTCHA Breaking

Contact Info

Product

Resources

About