Improving Low-Resolution Image Classification by Super-Resolution with Enhancing High-Frequency Content

2021 ◽  
Author(s):  
Liguo Zhou ◽  
Guang Chen ◽  
Mingyue Feng ◽  
Alois Knoll
Keyword(s):  
Image Classification ◽  
High Frequency ◽  
Super Resolution ◽  
Frequency Content ◽  
Low Resolution ◽  
Resolution Image ◽  
High Frequency Content

scholarly journals SR-Inpaint: A General Deep Learning Framework for High Resolution Image Inpainting

Algorithms ◽  
2021 ◽  
Vol 14 (8) ◽  
pp. 236
Author(s):  
Haoran Xu ◽  
Xinya Li ◽  
Kaiyi Zhang ◽  
Yanbai He ◽  
Haoran Fan ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
High Frequency ◽  
Image Inpainting ◽  
Super Resolution ◽  
Low Resolution ◽  
Resolution Image ◽  
Learning Framework ◽  
High Resolution Image ◽  
High Resolution Images

Recently, deep learning has enabled a huge leap forward in image inpainting. However, due to the memory and computational limitation, most existing methods are able to handle only low-resolution inputs, typically less than 1 K. With the improvement of Internet transmission capacity and mobile device cameras, the resolution of image and video sources available to users via the cloud or locally is increasing. For high-resolution images, the common inpainting methods simply upsample the inpainted result of the shrinked image to yield a blurry result. In recent years, there is an urgent need to reconstruct the missing high-frequency information in high-resolution images and generate sharp texture details. Hence, we propose a general deep learning framework for high-resolution image inpainting, which first hallucinates a semantically continuous blurred result using low-resolution inpainting and suppresses computational overhead. Then the sharp high-frequency details with original resolution are reconstructed using super-resolution refinement. Experimentally, our method achieves inspiring inpainting quality on 2K and 4K resolution images, ahead of the state-of-the-art high-resolution inpainting technique. This framework is expected to be popularized for high-resolution image editing tasks on personal computers and mobile devices in the future.

scholarly journals Fast Target Localization Method for FMCW MIMO Radar via VDSR Neural Network

2021 ◽  
Vol 13 (10) ◽  
pp. 1956
Author(s):  
Jingyu Cong ◽  
Xianpeng Wang ◽  
Xiang Lan ◽  
Mengxing Huang ◽  
Liangtian Wan
Keyword(s):  
Neural Network ◽  
Continuous Wave ◽  
Super Resolution ◽  
Mimo Radar ◽  
Target Localization ◽  
Estimation Accuracy ◽  
Low Resolution ◽  
Range Estimation ◽  
Resolution Image ◽  
Resolution Imaging

The traditional frequency-modulated continuous wave (FMCW) multiple-input multiple-output (MIMO) radar two-dimensional (2D) super-resolution (SR) estimation algorithm for target localization has high computational complexity, which runs counter to the increasing demand for real-time radar imaging. In this paper, a fast joint direction-of-arrival (DOA) and range estimation framework for target localization is proposed; it utilizes a very deep super-resolution (VDSR) neural network (NN) framework to accelerate the imaging process while ensuring estimation accuracy. Firstly, we propose a fast low-resolution imaging algorithm based on the Nystrom method. The approximate signal subspace matrix is obtained from partial data, and low-resolution imaging is performed on a low-density grid. Then, the bicubic interpolation algorithm is used to expand the low-resolution image to the desired dimensions. Next, the deep SR network is used to obtain the high-resolution image, and the final joint DOA and range estimation is achieved based on the reconstructed image. Simulations and experiments were carried out to validate the computational efficiency and effectiveness of the proposed framework.

Comparison of wavelet continuous transform and signal averaged ECG for high frequency content and late potential detection in healthy individuals

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
D Garcia Iglesias ◽  
J.M Rubin Lopez ◽  
D Perez Diez ◽  
C Moris De La Tassa ◽  
F.J De Cos Juez ◽  
...  
Keyword(s):  
High Frequency ◽  
Classical Method ◽  
Total Power ◽  
Frequency Content ◽  
Healthy Individuals ◽  
Time Frequency ◽  
Qt Intervals ◽  
Long Time ◽  
Power Content ◽  
High Frequency Content

Abstract Introduction The Signal Averaged ECG (SAECG) is a classical method forSudden Cardiac Death (SCD) risk assessment, by means of Late Potentials (LP) in the filtered QRS (fQRS)[1]. But it is highly dependent on noise and require long time records, which make it tedious to use. Wavelet Continuous Transform (WCT) meanwhile is easier to use, and may let us to measure the High Frequency Content (HFC) of the QRS and QT intervals, which also correlates with the risk of SCD [2,3]. Whether the HFC of the QRS and QT measured with the WCT is a possible subrogate of LP, has never been demonstrated. Objective To demonstrate if there is any relationship between the HFC measured with the WCT and the LP analyzed with the SAECG. Methods Data from 50 consecutive healthy individuals. The standard ECG was digitally collected for 3 consecutive minutes. For the WCT Analysis 8 consecutive QT complexes were used and for the SAECG Analysis all available QRS were used. The time-frequency data of each QT complex were collected using the WCT as previously described [3] and the Total, QRS and QT power were obtained from each patient. For the SAECG, bipolar X, Y and Z leads were used with a bidirectional filter at 40 to 250 Hz [1]. LP were defined as less than 0.05 z in the terminal part of the filtered QRS and the duration (SAECG LP duration) and root mean square (SAECG LP Content) of this LP were calculated. Pearson's test was used to correlate the Power content with WCT analysis and the LP in the SAECG. Results There is a strong correlation between Total Power and the SAECG LP content (r=0.621, p<0.001). Both ST Power (r=0.567, p<0.001) and QRS Power (r=0.404, p=0.004) are related with the SAECG LP content. No correlation were found between the Power content (Total, QRS or ST Power) and the SAECG LP duration. Also no correlation was found between de SAECG LP content and duration. Conclusions Total, QRS and ST Power measured with the WCT are good surrogates of SAECG LP content. No correlation were found between WCT analysis and the SAECG LP duration. Also no correlation was found between the SAECG LP content and duration. This can be of high interest, since WCT is an easier technique, not needing long recordings and being less affected by noise. Funding Acknowledgement Type of funding source: None

scholarly journals Super Resolution Digital Image Correlation (SR-DIC): an Alternative to Image Stitching at High Magnifications

2021 ◽  
Author(s):  
R. S. Hansen ◽  
D. W. Waldram ◽  
T. Q. Thai ◽  
R. B. Berke
Keyword(s):  
High Resolution ◽  
Digital Image Correlation ◽  
Spatial Resolution ◽  
Digital Image ◽  
Super Resolution ◽  
Image Correlation ◽  
Low Resolution ◽  
Strain Measurements ◽  
Resolution Image ◽  
High Resolution Image

Abstract Background High-resolution Digital Image Correlation (DIC) measurements have previously been produced by stitching of neighboring images, which often requires short working distances. Separately, the image processing community has developed super resolution (SR) imaging techniques, which improve resolution by combining multiple overlapping images. Objective This work investigates the novel pairing of super resolution with digital image correlation, as an alternative method to produce high-resolution full-field strain measurements. Methods First, an image reconstruction test is performed, comparing the ability of three previously published SR algorithms to replicate a high-resolution image. Second, an applied translation is compared against DIC measurement using both low- and super-resolution images. Third, a ring sample is mechanically deformed and DIC strain measurements from low- and super-resolution images are compared. Results SR measurements show improvements compared to low-resolution images, although they do not perfectly replicate the high-resolution image. SR-DIC demonstrates reduced error and improved confidence in measuring rigid body translation when compared to low resolution alternatives, and it also shows improvement in spatial resolution for strain measurements of ring deformation. Conclusions Super resolution imaging can be effectively paired with Digital Image Correlation, offering improved spatial resolution, reduced error, and increased measurement confidence.

A Video Super Resolution Algorithm Based on Wavelet Coefficient

2014 ◽  
Vol 610 ◽  
pp. 425-428
Author(s):  
Wei Jian Liu ◽  
Si Da Xiao ◽  
Ruo He Yao
Keyword(s):  
High Frequency ◽  
Wavelet Coefficient ◽  
Three Dimensional ◽  
Super Resolution ◽  
Structural Similarity ◽  
Image Sequences ◽  
Discrete Wavelet ◽  
Resolution Image ◽  
Resolution Algorithm ◽  
Visual Results

In this paper, we propose a new super-resolution algorithm based on wavelet coefficient. The proposed algorithm uses discrete wavelet transform (DWT) to decompose the input low-resolution image sequences into four subband images, including LL, LH, HL, HH. Then the input images have been processed by the 3DSKR (Three Dimensional Steering Kernel Regression) super resolution (SR) algorithm, and the result replaces the LL subband image, while the three high-frequency subband images have been interpolated. Finally, combining all these images to generate a new high-resolution image by using inverse DWT. Proposed method has been verified on Calendar and Foliage by Matlab software platform. The peak signal-to-noise (PSNR), structural similarity (SSIM) and visual results are compared, and show that the computational complexity of the proposed algorithm decline by 30 percent compared with the existing algorithm to obtain the approximate results.

scholarly journals Region Filling with Super Resolution Algorithm

2021 ◽  
Vol 9 (VI) ◽  
pp. 3557-3564
Author(s):  
Darakhshan R. Khan
Keyword(s):  
Patch Size ◽  
Research Work ◽  
Super Resolution ◽  
Input Image ◽  
Computational Time ◽  
Low Resolution ◽  
Resolution Image ◽  
Resolution Algorithm ◽  
Region Filling

Region filling which has another name inpainting, is an approach to find the values of missing pixels from data available in the remaining portion of the image. The missing information must be recalculated in a distinctly convincing manner, such that, image look seamless. This research work has built a methodology for completely automating patch priority based region filling process. To reduce the computational time, low resolution image is constructed from input image. Based on texel of an image, patch size is determined. Several low resolution image with missing region filled is generated using region filling algorithm. Pixel information from these low resolution images is consolidated to produce single low resolution region filled image. Finally, super resolution algorithm is applied to enhance the quality of image and regain all specifics of image. This methodology of identifying patch size based on input fed has an advantage over filling algorithms which in true sense automate the process of region filling, to deal with sensitivity in region filling, algorithm different parameter settings are used and functioning with coarse version of image will notably reduce the computational time.

Sign in / Sign up

Export Citation Format

Share Document