11,871 Hits in 5.0 sec

Super-resolution reconstruction of a digital elevation model based on a deep residual network

Donglai Jiao, Dajiang Wang, Haiyang Lv, Yang Peng
2020 Open Geosciences  
The results show that DEM super-resolution based on a deep residual network is better than that obtained using a neural network with fewer convolutional layers, and the reconstructed result of the DEM  ...  At present, there is little research on DEM super-resolution based on deep learning, and the results of the reconstructed DEMs obtained by existing methods are inaccurate.  ...  This research was funded by the National Natural Science Foundation of China, grant number 41471329 and 41101358. Author contributions: Donglai Jiao: writingoriginal draft, writingreview and editing.  ... 
doi:10.1515/geo-2020-0207 fatcat:3el2jsdu4veiznw3mhrycmsafa

A Fast Medical Image Super Resolution Method Based on Deep Learning Network

Shengxiang Zhang, Gaobo Liang, Shuwan Pan, Lixin Zheng
2019 IEEE Access  
convolution neural network.  ...  Sub-pixel convolution layer addition and mini-network substitution in the hidden layers are critical for improving the image reconstruction speed.  ...  FAST MEDICAL IMAGE SUPER RESOLUTION BASED ON DEEP LEARNING As showed in Fig.1 , the proposed fast medical image super resolution method is based on a well-designed deep learning network, which comprises  ... 
doi:10.1109/access.2018.2871626 fatcat:k3vvgpstbnghtmvgxjoodixuu4

Human Face Super-Resolution Based on Hybrid Algorithm

Jinfeng Xia, Zhizheng Yang, Fang Li, Yuanda Xu, Nan Ma, Chunxing Wang
2018 Advances in Molecular Imaging  
Aiming at the problems of image super-resolution algorithm with many convolutional neural networks, such as large parameters, large computational complexity and blurred image texture, we propose a new  ...  The classical convolutional neural network is improved, the convolution kernel size is adjusted, and the parameters are reduced; the pooling layer is added to reduce the dimension.  ...  Conclusion In this paper, by analyzing the training process of convolutional neural networks, we have made a series of improvements to the image super-resolution algorithm based on convolutional neural  ... 
doi:10.4236/ami.2018.84004 fatcat:5uvsy7fxr5dejophfyj2lk4a5u

Image Super-resolution Using Mid-level Representations

Li Yang, Yaxing Wang, Xiaomin Mu, Yaping Wang
2016 DEStech Transactions on Engineering and Technology Research  
An end-to-end six layers convolutional neural network(CNNs) structure is proposed to realize single image super-resolution reconstruction.  ...  The input of the network is low-resolution (LR) image, and the output is the superresolution (SR) image. Promising experimental results are obtained with higher precision.  ...  Conclusion In this paper, the image super-resolution reconstruction method based on three layers convolutional neural network is improved.  ... 
doi:10.12783/dtetr/iect2016/3750 fatcat:7aqy4lax5bgj7i5v5b3frv6zsi

Impact of Low Resolution on Image Recognition with Deep Neural Networks: An Experimental Study

Michał Koziarski, Bogusław Cyganek
2018 International Journal of Applied Mathematics and Computer Science  
Furthermore, we examine the possibility of improving neural networks' performance in the task of low resolution image recognition by applying super-resolution prior to classification.  ...  Due to the advances made in recent years, methods based on deep neural networks have been able to achieve a state-of-the-art performance in various computer vision problems.  ...  Since then, numerous variants of convolutional neural networks have been proposed for the image super-resolution task.  ... 
doi:10.2478/amcs-2018-0056 fatcat:56yfhvmthvfwrpy7pqv4bt6gh4

Survey on CNN based super resolution methods

Rafaa Amen Kazem, Jamila H. Suad, Huda Abdulaali Abdulbaqi
2021 Journal La Multiapp  
The study examines super-resolution methods based on a convolutional neural network (CNN) for super-resolution mapping at the sub-pixel level, as well as its primary characteristics and limitations for  ...  Multiple (many input images and one output image) or single (one input and one output) stages are used to convert low-resolution photos to high-resolution photos.  ...  Deep super-resolution (VSDR), deep recursive convolutional network (DRSN), superresolution convolutional neural network (SRCNN), and fast super resolution convolutional neural network are the most recent  ... 
doi:10.37899/journallamultiapp.v2i4.444 fatcat:apjy2pjpfvenno6unrptjqm25e

A Review of Deep Learning Based Image Super-resolution Techniques [article]

Fangyuan Zhu
2022 arXiv   pre-print
in the field of image super-resolution, and reports the latest progress of image super-resolution technology based on depth learning method.  ...  With the development of deep learning, image super-resolution technology based on deep learning method is emerging.  ...  First applied convolutional neural network to the research of image super-resolution in 2014, a large number of new image super-resolution methods based on depth learning have been emerging.  ... 
arXiv:2201.10521v1 fatcat:ul5sxm3ssfagbc6nzpfvgzhowi

Super-Resolution Image Reconstruction Based on Self-Calibrated Convolutional GAN [article]

Yibo Guo, Haidi Wang, Yiming Fan, Shunyao Li, Mingliang Xu
2021 arXiv   pre-print
However, many researches have pointed out that the insufficiency of the neural network extraction on image features may bring the deteriorating of newly reconstructed image.  ...  With the effective application of deep learning in computer vision, breakthroughs have been made in the research of super-resolution images reconstruction.  ...  Super-resolution image reconstruction based on convolutional neural network The method in this paper mainly uses convolutional neural networks, including shallow neural networks and deep neural networks  ... 
arXiv:2106.05545v1 fatcat:pxdvpspvrzcvbdgprxreylff3u

Super Resolution of Videos using SRGAN

Jash Shah
2020 International Journal for Research in Applied Science and Engineering Technology  
Previous techniques of up scaling were based on minimizing the mean squares reconstructed error.  ...  The neural network is successful in recovering the photo realistic textures from downgraded images.  ...  There are different types of CNN based SR such as SRCNN(Super Resolution Convolutional Neural Networks), FSRCNN(Fast Super Resolution Convolutional Network), VDSR(Very Deep Super Resolution Convolutional  ... 
doi:10.22214/ijraset.2020.1058 fatcat:fvjnheoifvbezc7btog4bkxswa

Application of Convolution Network Model Based on Deep Learning in Sports Image Information Detection

Xiaoqiao Zhang, L. Zhang, S. Defilla, W. Chu
2021 E3S Web of Conferences  
In recent years, convolution neural network has achieved great success in single image super-resolution detection.  ...  Aiming at the problems and shortcomings of the existing sports image information detection based on convolution neural network, this paper proposes the application of convolution network model based on  ...  DISCUSSION Validity of MFFRR Reconstruction Model in Sports Image Information Detection In the motion image super-resolution algorithm based on convolution neural network, div2k provided by NTIRE 2017  ... 
doi:10.1051/e3sconf/202123302024 fatcat:zuv7pa2j4ve7bi3qg35rxvtdfm

Improved differentiable neural architecture search for single image super-resolution

Yu Weng, Zehua Chen, Tianbao Zhou
2021 Peer-to-Peer Networking and Applications  
Then we use the improved DARTS to search convolution cells as a nonlinear mapping part of super-resolution network.  ...  AbstractDeep learning has shown prominent superiority over other machine learning algorithms in Single Image Super-Resolution (SISR).  ...  Acknowledgements Thanks to Guosheng Yang for his guidance on this article. At the same time, I would like to thank the students in the laboratory for their suggestions and comments on this article.  ... 
doi:10.1007/s12083-020-01048-4 fatcat:eels5wqcxvattjdkixiynvhqni

A wavelet based deep learning method for underwater image super resolution reconstruction

Yuzhang Chen, Kangli Niu, Zhangfan Zeng, Yongcai Pan
2020 IEEE Access  
In order to further improve the effectiveness and efficiency of deep learning based methods, an improved image super-resolution reconstruction algorithm based on deep convolutional neural network is proposed  ...  INDEX TERMS Convolutional neural network, super-resolution, signal to noise ratio, underwater image.  ...  IMAGE SUPER RESOLUTION RECONSTRUCTION BASED ON WAVELET DEEP CONVOLUTION NEURAL NETWORK The structure of the improved deep intensive convolution neural network designed in this paper is shown in Figure  ... 
doi:10.1109/access.2020.3004141 fatcat:cgojqyczojfxbizlullpwcrfci

Object Detection by a Super-Resolution Method and a Convolutional Neural Networks

Bokyoon Na, Geoffrey C Fox
2018 2018 IEEE International Conference on Big Data (Big Data)  
Recently with many blurless or slightly blurred images, convolutional neural networks classify objects with around 90 percent classification rates, even if there are variable sized images.  ...  However, for smaller region candidates, using our super-resolution preprocessing and region candidates, allows a CNN to outperform conventional methods in the number of detected objects when tested on  ...  Thus, we will introduce our research to improve object classification rates with improvements through superresolution algorithms and convolution neural networks. II.  ... 
doi:10.1109/bigdata.2018.8622135 dblp:conf/bigdataconf/NaF18 fatcat:o723hdnsdvdqpohpsybzxhk2c4

RDA- CNN: Enhanced Super Resolution Method for Rice Plant Disease Classification

K. Sathya, M. Rajalakshmi
2022 Computer systems science and engineering  
We propose a novel Reconstructed Disease Aware-Convolutional Neural Network (RDA-CNN), inspired by recent CNN architectures, that integrates image super resolution and classification into a single model  ...  This network takes low-resolution images of rice crops as input and employs the super resolution layers to transform low-resolution images to super-resolution images to recover appearance such as spots  ...  Although super-resolution is concerned, the early research on the contribution of deep learning is Super-Resolution Convolutional Neural Network (SRCNN).  ... 
doi:10.32604/csse.2022.022206 fatcat:az5m23xt7bc3tm63r6ogq2jxdu

Super Resolution for Noisy Images Using Convolutional Neural Networks

Zaid Bin Mushtaq, Shoaib Mohd Nasti, Chaman Verma, Maria Simona Raboca, Neerendra Kumar, Samiah Jan Nasti
2022 Mathematics  
In this paper, a single-image super-resolution network model based on convolutional neural networks is proposed by combining conventional autoencoder and residual neural network approaches.  ...  A convolutional neural network-based dictionary method is used to train low-resolution input images for high-resolution images.  ...  Acknowledgments: The work of Chaman Verma was supported under "ÚNKP, MIT (Ministry of Innovation and Technology) and National Research, Development and Innovation (NRDI) Fund, Hungarian Government" and  ... 
doi:10.3390/math10050777 fatcat:w24o4fbrhfgw7a7wqryd4gjuda
« Previous Showing results 1 — 15 out of 11,871 results