scholarly journals Low-Light-Level Image Super-Resolution Reconstruction Based on a Multi-Scale Features Extraction Network

Photonics ◽  
2021 ◽  
Vol 8 (8) ◽  
pp. 321
Author(s):  
Bowen Wang ◽  
Yan Zou ◽  
Linfei Zhang ◽  
Yan Hu ◽  
Hao Yan ◽  
...  
Keyword(s):  
High Frequency ◽  
Signal To Noise Ratio ◽  
Super Resolution ◽  
Light Level ◽  
Superior Performance ◽  
Wide Field ◽  
Low Light ◽  
Color Mapping ◽  
Multi Scale ◽  
Imaging Sensors

Wide field-of-view (FOV) and high-resolution (HR) imaging are essential to many applications where high-content image acquisition is necessary. However, due to the insufficient spatial sampling of the image detector and the trade-off between pixel size and photosensitivity, the ability of current imaging sensors to obtain high spatial resolution is limited, especially under low-light-level (LLL) imaging conditions. To solve these problems, we propose a multi-scale feature extraction (MSFE) network to realize pixel-super-resolved LLL imaging. In order to perform data fusion and information extraction for low resolution (LR) images, the network extracts high-frequency detail information from different dimensions by combining the channel attention mechanism module and skip connection module. In this way, the calculation of the high-frequency components can receive greater attention. Compared with other networks, the peak signal-to-noise ratio of the reconstructed image was increased by 1.67 dB. Extensions of the MSFE network are investigated for scene-based color mapping of the gray image. Most of the color information could be recovered, and the similarity with the real image reached 0.728. The qualitative and quantitative experimental results show that the proposed method achieved superior performance in image fidelity and detail enhancement over the state-of-the-art.

Low-light-level image pixel super-resolution reconstruction method

2021 ◽  
Author(s):  
Bowen Wang ◽  
Ju Zhang ◽  
Ziheng Jin ◽  
Haojie Gu ◽  
Yan Zou ◽  
...  
Keyword(s):  
Super Resolution ◽  
Light Level ◽  
Reconstruction Method ◽  
Low Light

scholarly journals Structure based analysis of protein cluster size for super-resolution microscopy in the nervous system

2019 ◽  
Author(s):  
Chia-En Wong ◽  
Cheng-Che Lee ◽  
Kuen-Jer Tsai
Keyword(s):  
Super Resolution ◽  
Superior Performance ◽  
Structural Function ◽  
Wide Field ◽  
Localization Algorithm ◽  
Novel Structure ◽  
Localization Algorithms ◽  
Optical Reconstruction ◽  
Microscopy Data ◽  
Maximum Parameters

AbstractTo overcome the diffraction limit and resolve target structures in greater detail, far-field super-resolution techniques such as stochastic optical reconstruction microscopy (STORM) have been developed, and different STORM algorithms have been developed to deal with the various problems that arise. In particular, the effect of local structure is an important issue. For objects with closely correlated distributions, simple Gaussian-based localization algorithms often used in STORM imaging misinterpret overlapping point spread functions (PSFs) as one and this limits the ability of super-resolution imaging to resolve nanoscale local structures and leading to inaccurate length measurements. In the present study, we proposed a novel, structure-based, super-resolution image analysis method: structure-based analysis (SBA), which combines a structural function and a super-resolution localization algorithm. Using SBA, we estimated the size of fluorescent beads, inclusion proteins, and subtle synaptic structures in both wide-field and STORM images. The results showed that SBA has comparable and often superior performance to commonly used full-width-at-half-maximum parameters. We also demonstrated that SBA provides size estimations that corroborate previously published electron microscopy data.

scholarly journals End-to-End Super-Resolution for Remote-Sensing Images Using an Improved Multi-Scale Residual Network

2021 ◽  
Vol 13 (4) ◽  
pp. 666
Author(s):  
Hai Huan ◽  
Pengcheng Li ◽  
Nan Zou ◽  
Chao Wang ◽  
Yaqin Xie ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Feature Fusion ◽  
Signal To Noise Ratio ◽  
Model Performance ◽  
Super Resolution ◽  
Structural Similarity ◽  
Remote Sensing Images ◽  
Residual Network ◽  
Multi Scale ◽  
Information Image

Remote-sensing images constitute an important means of obtaining geographic information. Image super-resolution reconstruction techniques are effective methods of improving the spatial resolution of remote-sensing images. Super-resolution reconstruction networks mainly improve the model performance by increasing the network depth. However, blindly increasing the network depth can easily lead to gradient disappearance or gradient explosion, increasing the difficulty of training. This report proposes a new pyramidal multi-scale residual network (PMSRN) that uses hierarchical residual-like connections and dilation convolution to form a multi-scale dilation residual block (MSDRB). The MSDRB enhances the ability to detect context information and fuses hierarchical features through the hierarchical feature fusion structure. Finally, a complementary block of global and local features is added to the reconstruction structure to alleviate the problem that useful original information is ignored. The experimental results showed that, compared with a basic multi-scale residual network, the PMSRN increased the peak signal-to-noise ratio by up to 0.44 dB and the structural similarity to 0.9776.

Sign in / Sign up

Export Citation Format

Share Document