【摘 要】
：
There is a Poisson inverse problem in biomedical imaging,fluorescence microscopy and so on.Since the observed measurements are damaged by a linear operator and further destroyed by Poisson noise,recovering the approximate original image is difficult.Motiv
【机 构】
：
School of Electronic Information Engineering,Nanchang University,Nanchang 330031,China
论文部分内容阅读
There is a Poisson inverse problem in biomedical imaging,fluorescence microscopy and so on.Since the observed measurements are damaged by a linear operator and further destroyed by Poisson noise,recovering the approximate original image is difficult.Motivated by the decouple scheme and the variance-stabilizing trans-formation (VST) strategy,we propose a method of transformed convolutional neural network (CNN) to restore the observed image.In the network,the Conv-layers play the role of a linear inverse filter and the distribution transformation simultaneously.Furthermore,there is no batch normalization (BN) layer in the residual block of the network,which is devoted to tackling with the non-Gaussian recovery procedure.The proposed method is compared with state-of-the-art Poisson deblurring algorithms,and the experimental results show the effectiveness of the method.
其他文献
This work presents a nonlinear finite element method to simulate the macroscopic mechanical re-sponses and the effects of martensite plasticity in a shape memory alloy (SMA) structure.A linear relationship formulation is adopted to express the influence o
Owing to the remarkable advantages in mechanical behavior,cast steel nodes have been widely used in static structures.Nowadays,cast steel nodes also gain increasing popularity due to the superior fatigue per-formance in dynamic structures,but they are not
The acceleration saltation of the traditional S-type acceleration model in the speed planning of the NURBS curve will result in the vibration and flexible impact of the machine tool.It will affect the surface quality of the components.The high speed smoot
Additional hysteretic experiments for corroded rectangular reinforced concrete (RC) columns with an axial load ratio of 0.27 were implemented.A quasi-static cyclic lateral loading with constant axial force was subjected to tests.Herein,a modified ductilit
Combined with fiber Bragg grating (FBG) sensing technology,four glass fiber reinforced polymer(GFRP) anti-floating anchors and four steel anti-floating anchors were tested for on-site destructive failure to investigate the anchoring performance and the bo
Considering the situation that fatigue life prediction of notched component is an indispensable part in the process of design in engineering,it is necessary to find some ways to solve such problems effectively.The stress and strain state of notched specim
A high-power marine controlled-source electromagnetic transmitter (HP-MCSET) transmits a high-frequency conversion current on the sea floor.Some problems exist when the direct-current to alternating-current(DC-AC) launch bridge (LB) is used in the marine
With rigorous dynamic performance of mechanical products,it is important to identify dynamic parameters exactly.In this paper,a response surface plotting method is proposed and it can be applied to identify the dynamic parameters of some nonlinear systems
This paper studies practical control design for a novel automatic shell magazine (ASM) with a new fast smooth second-order sliding mode (FSSOSM) control based on disturbance observer.The dynamic model of the ASM with parameter perturbations and nonlinear
The computational speed in the feature selection of Mahalanobis-Taguchi system (MTS) using standard binary particle swarm optimization (BPSO) is slow and it is easy to fall into the locally optimal solution.This paper proposes an MTS variable optimization