A Hybrid Multi-Frame Super-Resolution Algorithm Using Multi-Channel Memristive Pulse Coupled Neural Network and Sparse Coding

@article{Dong2019AHM,
  title={A Hybrid Multi-Frame Super-Resolution Algorithm Using Multi-Channel Memristive Pulse Coupled Neural Network and Sparse Coding},
  author={Zhekang Dong and Songjie Zhang and Bihuan Ma and Donglian Qi and Li Luo and Mengzhe Zhou},
  journal={2019 7th International Conference on Information, Communication and Networks (ICICN)},
  year={2019},
  pages={185-190},
  url={https://api.semanticscholar.org/CorpusID:202560753}
}
  • Zhekang DongSongjie Zhang Mengzhe Zhou
  • Published in 7th International Conference… 1 April 2019
  • Computer Science, Engineering
  • 2019 7th International Conference on Information, Communication and Networks (ICICN)
This method combines the concepts of both multi-frame and single-frame SR to generate a high-resolution (HR) image and a series of contrast experiments and the relevant subjective/objective analysis jointly illustrate the effectiveness and superiority of the entire scheme.
View on IEEE
doi.org
2 Citations
Background Citations
1

Figures from this paper

2 Citations

Convolution Kernel Operations on a Two-Dimensional Spin Memristor Cross Array

A circuit based on spin memristor cross array is proposed, which realizes the multiplication and addition operation in the convolution operation and significantly alleviates the computational memory bottleneck.

SRPeek: Super Resolution Enabled Screen Peeking via COTS Smartphone

An end-to-end system deployed on commercial smartphones, including an innovative deep neural network architecture, StARe, for efficient multi-image SR attack method using smartphones, calling for the vigilance of the Quietly growing shoulder surfing threat.

16 References

A general memristor-based pulse coupled neural network with variable linking coefficient for multi-focus image fusion

Single Image Super-Resolution via the Implementation of the Hardware-Friendly Sparse Coding

A Memristor crossbar array synthesized by a threshold-type memristor model is constructed for the implementation of a hardware-friendly sparse coding method, i.e., the Locally Competitive Algorithm (LCA).

Multi-frame image super-resolution reconstruction using sparse co-occurrence prior and sub-pixel registration

Fifth-Level Second-Generation Wavelet-Based Image Fusion Algorithm for Visual Quality Enhancement of Digital Image Data

The proposed technique involves the use of lifting wavelet transform technique at fifth level of decomposition and 9 different max–min–mean fusion rule combinations to achieve image fusion.

Learning a Deep Convolutional Network for Image Super-Resolution

This work proposes a deep learning method for single image super-resolution (SR) that directly learns an end-to-end mapping between the low/high-resolution images and shows that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network.

Fast and Accurate Single Image Super-Resolution via Information Distillation Network

This work proposes a deep but compact convolutional network to directly reconstruct the high resolution image from the original low resolution image and demonstrates that the proposed method is superior to the state-of-the-art methods, especially in terms of time performance.

Super-resolution image reconstruction: a technical overview

The goal of this article is to introduce the concept of SR algorithms to readers who are unfamiliar with this area and to provide a review for experts to present the technical review of various existing SR methodologies which are often employed.

Subpixel registration for a high resolution imaging scheme using multiple imagers

In the present work, the authors discuss an image registration scheme that exploits camera projection parameters so that the precision is substantially improved and the computational complexity is reduced.

Fast Generalized Motion Estimation and

A fast image registration and reconstruction algorithm is proposed which obtains a high-resolution (HR) frame using a number of adjacent low- resolution (LR) frames and is robust against high noise level in video frames.

Remote Sensing Image Fusion Method Based on PCA and Curvelet Transform

The experimental results illustrate that the proposed fusion algorithm outperforms Curvelet transform and other traditional fusion algorithms in whole both in visual effect and objective evaluation indexes.