Robust contrast-transfer-function phase retrieval via flexible deep learning networks

2019 ◽  
Vol 44 (21) ◽  
pp. 5141 ◽  
Author(s):  
Chen Bai ◽  
Meiling Zhou ◽  
Junwei Min ◽  
Shipei Dang ◽  
Xianghua Yu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Transfer Function ◽  
Phase Retrieval ◽  
Learning Networks ◽  
Contrast Transfer Function

Robust contrast-transfer-function phase retrieval via flexible deep learning networks: publisher’s note

2019 ◽  
Vol 44 (22) ◽  
pp. 5561
Author(s):  
Chen Bai ◽  
Meiling Zhou ◽  
Junwei Min ◽  
Shipei Dang ◽  
Xianghua Yu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Transfer Function ◽  
Phase Retrieval ◽  
Learning Networks ◽  
Contrast Transfer Function

A variable-wavelength-based approach of phase retrieval for contrast transfer function based methods

2010 ◽  
Vol 17 (6) ◽  
pp. 799-803 ◽  
Author(s):  
Yogesh S. Kashyap ◽  
Ashish Agrawal ◽  
P. S. Sarkar ◽  
Mayank Shukla ◽  
Tushar Roy ◽  
...  
Keyword(s):  
Transfer Function ◽  
Phase Retrieval ◽  
Contrast Transfer Function

Contrast-transfer-function phase retrieval based on compressed sensing

2017 ◽  
Vol 42 (6) ◽  
pp. 1133 ◽  
Author(s):  
Pablo Villanueva-Perez ◽  
Filippo Arcadu ◽  
Peter Cloetens ◽  
Marco Stampanoni
Keyword(s):  
Transfer Function ◽  
Compressed Sensing ◽  
Phase Retrieval ◽  
Contrast Transfer Function

Radiation Damage of Support Films

1981 ◽  
Vol 39 ◽  
pp. 28-29
Author(s):  
H.A. Cohen ◽  
W. Chiu
Keyword(s):  
Transfer Function ◽  
Low Temperatures ◽  
Carbon Support ◽  
Contrast Transfer Function ◽  
Electron Dose ◽  
Imaging Parameters ◽  
Negative Stain ◽  
Phase Corrections ◽  
Two Parameters ◽  
Medium Dose

The goal of imaging the finest detail possible in biological specimens leads to contradictory requirements for the choice of an electron dose. The dose should be as low as possible to minimize object damage, yet as high as possible to optimize image statistics. For specimens that are protected by low temperatures or for which the low resolution associated with negative stain is acceptable, the first condition may be partially relaxed, allowing the use of (for example) 6 to 10 e/Å2. However, this medium dose is marginal for obtaining the contrast transfer function (CTF) of the microscope, which is necessary to allow phase corrections to the image. We have explored two parameters that affect the CTF under medium dose conditions.Figure 1 displays the CTF for carbon (C, row 1) and triafol plus carbon (T+C, row 2). For any column, the images to which the CTF correspond were from a carbon covered hole (C) and the adjacent triafol plus carbon support film (T+C), both recorded on the same micrograph; therefore the imaging parameters of defocus, illumination angle, and electron statistics were identical.

Evaluation method for imaging plate resolution by means of phase contrast transfer function

1995 ◽  
Vol 53 ◽  
pp. 662-663 ◽  
Author(s):  
T. Oikawa ◽  
H. Kosugi ◽  
F. Hosokawa ◽  
D. Shindo ◽  
M. Kersker
Keyword(s):  
Transfer Function ◽  
Phase Contrast ◽  
Evaluation Method ◽  
Amorphous Film ◽  
Imaging Plate ◽  
X Rays ◽  
Special Shape ◽  
Contrast Transfer Function ◽  
Contrast Image ◽  
Specimen Shape

Evaluation of the resolution of the Imaging Plate (IP) has been attempted by some methods. An evaluation method for IP resolution, which is not influenced by hard X-rays at higher accelerating voltages, was proposed previously by the present authors. This method, however, requires truoblesome experimental preperations partly because specially synthesized hematite was used as a specimen, and partly because a special shape of the specimen was used as a standard image. In this paper, a convenient evaluation method which is not infuenced by the specimen shape and image direction, is newly proposed. In this method, phase contrast images of thin amorphous film are used.Several diffraction rings are obtained by the Fourier transformation of a phase contrast image of thin amorphous film, taken at a large under focus. The rings show the spatial-frequency spectrum corresponding to the phase contrast transfer function (PCTF). The envelope function is obtained by connecting the peak intensities of the rings. The evelope function is offten used for evaluation of the instrument, because the function shows the performance of the electron microscope (EM).

Density-based discrimination of protein and RNA in the ribosome

1992 ◽  
Vol 50 (1) ◽  
pp. 464-465
Author(s):  
Joachim Frank
Keyword(s):  
Transfer Function ◽  
Spatial Frequency ◽  
Three Dimensional ◽  
Wiener Filter ◽  
Dark Field Image ◽  
Dark Field ◽  
Frequency Range ◽  
Bright Field ◽  
Contrast Transfer Function ◽  
Pass Filter

Cryo-electron microscopy combined with single-particle reconstruction techniques has allowed us to form a three-dimensional image of the Escherichia coli ribosome.In the interior, we observe strong density variations which may be attributed to the difference in scattering density between ribosomal RNA (rRNA) and protein. This identification can only be tentative, and lacks quantitation at this stage, because of the nature of image formation by bright field phase contrast. Apart from limiting the resolution, the contrast transfer function acts as a high-pass filter which produces edge enhancement effects that can explain at least part of the observed variations. As a step toward a more quantitative analysis, it is necessary to correct the transfer function in the low-spatial-frequency range. Unfortunately, it is in that range where Fourier components unrelated to elastic bright-field imaging are found, and a Wiener-filter type restoration would lead to incorrect results. Depending upon the thickness of the ice layer, a varying contribution to the Fourier components in the low-spatial-frequency range originates from an “inelastic dark field” image. The only prospect to obtain quantitatively interpretable images (i.e., which would allow discrimination between rRNA and protein by application of a density threshold set to the average RNA scattering density may therefore lie in the use of energy-filtering microscopes.

Correction of the contrast transfer function to determine the radial density distribution of frozen-hydrated tobacco mosaic virus

1992 ◽  
Vol 50 (1) ◽  
pp. 536-537
Author(s):  
Michael F. Smith ◽  
John P. Langmore
Keyword(s):  
Transfer Function ◽  
Phase Contrast ◽  
Heavy Atom ◽  
Biological Molecules ◽  
Frequency Compensation ◽  
Contrast Transfer Function ◽  
High Background ◽  
Low Contrast ◽  
Radial Density Distribution ◽  
Excellent Preservation

The purpose of image reconstruction is to determine the mass densities within molecules by analysis of the intensities within images. Cryo-EM offers this possibility by virtue of the excellent preservation of internal structure without heavy atom staining. Cryo-EM images, however, have low contrast because of the similarity between the density of biological material and the density of vitreous ice. The images also contain a high background of inelastic scattering. To overcome the low signal and high background, cryo-images are typically recorded 1-3 μm underfocus to maximize phase contrast. Under those conditions the image intensities bear little resemblance to the object, due to the dependence of the contrast transfer function (CTF) upon spatial frequency. Compensation (i.e., correction) for the CTF is theoretically possible, but implementation has been rare. Despite numerous studies of molecules in ice, there has never been a quantitative evaluation of compensated images of biological molecules of known structure.

scholarly journals UAVs in rail damage image diagnostics supported by deep-learning networks

2021 ◽  
Vol 11 (1) ◽  
pp. 339-348
Author(s):  
Piotr Bojarczak ◽  
Piotr Lesiak
Keyword(s):  
Deep Learning ◽  
Head Width ◽  
Learning Networks ◽  
Image Brightness ◽  
Learning Network ◽  
Rail Head ◽  
Image Recording ◽  
Python Language ◽  
Deep Learning Network ◽  
Efficiency Rate

Abstract The article uses images from Unmanned Aerial Vehicles (UAVs) for rail diagnostics. The main advantage of such a solution compared to traditional surveys performed with measuring vehicles is the elimination of decreased train traffic. The authors, in the study, limited themselves to the diagnosis of hazardous split defects in rails. An algorithm has been proposed to detect them with an efficiency rate of about 81% for defects not less than 6.9% of the rail head width. It uses the FCN-8 deep-learning network, implemented in the Tensorflow environment, to extract the rail head by image segmentation. Using this type of network for segmentation increases the resistance of the algorithm to changes in the recorded rail image brightness. This is of fundamental importance in the case of variable conditions for image recording by UAVs. The detection of these defects in the rail head is performed using an algorithm in the Python language and the OpenCV library. To locate the defect, it uses the contour of a separate rail head together with a rectangle circumscribed around it. The use of UAVs together with artificial intelligence to detect split defects is an important element of novelty presented in this work.

Sign in / Sign up

Export Citation Format

Share Document