Low Power Image Acquisition Scheme Using On-Pixel Event Driven Halftoning

Kodge, Sangamesh; Chaudhary, Himanshu; Sharad, Mrigank

doi:10.1109/isvlsi.2017.53

Cited by 6 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The inputs were normalized using the mean and standard deviation of the training dataset. We also consider the nonlinear quantization scheme of halftoning mentioned in [42]. The quantized models are represented by "Q¡bit-width¿", halftone by "HT" and "FP" refers to the full precision network.…”

Section: Quantizationmentioning

confidence: 99%

TREND: Transferability based Robust ENsemble Design

Ravikumar¹,

Kodge²,

Garg³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Deep Learning models hold state-of-the-art performance in many fields, but their vulnerability to adversarial examples poses a threat to their ubiquitous deployment in practical settings. Additionally, adversarial inputs generated on one classifier have been shown to transfer to other classifiers trained on similar data, which makes the attacks possible even if the model parameters are not revealed to the adversary. This property of transferability has not yet been systematically studied, leading to a gap in our understanding of robustness of neural networks to adversarial inputs. In this work, we study the effect of network architecture, initialization, input, weight and activation quantization on transferability. Our experiments reveal that transferability is significantly hampered by input quantization and architectural mismatch between source and target, is unaffected by initialization and is architecture-dependent for both weight and activation quantization. To quantify transferability, we propose a simple metric, which is a function of the attack strength. We demonstrate the utility of the proposed metric in designing a methodology to build ensembles with improved adversarial robustness. Finally, we show that an ensemble consisting of carefully chosen input quantized networks achieves better adversarial robustness than would otherwise be possible with a single network.

show abstract

Section: Quantizationmentioning

confidence: 99%

TREND: Transferability based Robust ENsemble Design

Ravikumar¹,

Kodge²,

Garg³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Common application is for binary output devices such as printers, fax machines, copiers, digital monitors, and so on. Another application is bilevel data compression, such as telemedicine and the Internet of things [1,2]. So far, various digital halftoning technologies have been proposed, such as ordered dithering, error diffusion, dot diffusion, and iterative [3,4].…”

Section: Introductionmentioning

confidence: 99%

An inverse halftoning method based on supervised deep convolutional neural network

Li,

Liu

2023

IET Image Processing

View full text Add to dashboard Cite

Inverse halftoning is a technology that converts a binary image into a continuous tone image. Due to the wide application of inverse halftoning, many scholars have proposed several deep convolutional neural networks (DCNN) to optimize their performance. According to the observation, there is still room for improvement in content generation and detail recovery of the inverse halftone images generated by using the existing methods. Therefore, an inverse halftoning method based on supervised DCNN is proposed in this paper. The method consists of two parts: the multi‐level feature extraction model uses the down‐sampling to extract the features from the halftone image and remove the halftone noise dots on flat areas, which is implemented by four convolutional layers; the image reconstruction model uses up‐sampling to reconstruct image information, which is realized by four convolutional layers and two dense residual blocks. At the same time, in order to further recover the details, the down‐sampling feature maps and up‐sampling feature maps of the same size are concatenated by addition layers. Experimental results show that compared with other methods, the inverse halftone images obtained by the proposed network have better results in both subjective and objective evaluations.

show abstract

“…Different from the general binary image, the halftone image can be perceived as a continuous-tone image when it is viewed from a certain distance because of the low filtering character of the human visual system. Halftone images are widely used in many fields, such as the printing industry [1], telemedicine [2], Internet of Things (IoT) [3], and the textile industry [4]. The common application case of halftone image is for bi-level output devices such as printing press, printers, copiers, fax machines, plasma display panels, and so on.…”

Section: Introductionmentioning

confidence: 99%

“…The common application case of halftone image is for bi-level output devices such as printing press, printers, copiers, fax machines, plasma display panels, and so on. Another application field is in that the halftone image can be used as an image compression mode where there is not enough storage space and ultra-low power image acquisition is needed, such as in telemedicine and IoT [2,3]. Inverse halftoning is an inverse process of halftoning that is used to restore continuous-tone images from their halftone versions.…”

Section: Introductionmentioning

confidence: 99%

Inverse Halftoning Methods Based on Deep Learning and Their Evaluation Metrics: A Review

Zhang

Wang

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

Inverse halftoning is an ill-posed problem that refers to the problem of restoring continuous-tone images from their halftone versions. Although much progress has been achieved over the last decades, the restored images still suffer from detail loss and visual artifacts. Recent studies show that inverse halftoning methods based on deep learning are superior to other traditional methods, and thus this paper aimed to systematically review the inverse halftone methods based on deep learning, so as to provide a reference for the development of inverse halftoning. In this paper, we firstly proposed a classification method for inverse halftoning methods on the basis of the source of halftone images. Then, two types of inverse halftoning methods for digital halftone images and scanned halftone images were investigated in terms of network architecture, loss functions, and training strategies. Furthermore, we studied existing image quality evaluation including subjective and objective evaluation by experiments. The evaluation results demonstrated that methods based on multiple subnetworks and methods based on multi-stage strategies are superior to other methods. In addition, the perceptual loss and the gradient loss are helpful for improving the quality of restored images. Finally, we gave the future research directions by analyzing the shortcomings of existing inverse halftoning methods.

show abstract

Low Power Image Acquisition Scheme Using On-Pixel Event Driven Halftoning

Cited by 6 publications

References 18 publications

TREND: Transferability based Robust ENsemble Design

TREND: Transferability based Robust ENsemble Design

An inverse halftoning method based on supervised deep convolutional neural network

Inverse Halftoning Methods Based on Deep Learning and Their Evaluation Metrics: A Review

Contact Info

Product

Resources

About