scholarly journals Convolutional Neural Network with Spatial-Variant Convolution Kernel

2020 ◽  
Vol 12 (17) ◽  
pp. 2811
Author(s):  
Yongpeng Dai ◽  
Tian Jin ◽  
Yongkun Song ◽  
Shilong Sun ◽  
Chen Wu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Image Enhancement ◽  
Point Spread Function ◽  
Radar Image ◽  
Radar Images ◽  
Point Spread ◽  
Spread Function ◽  
Spatially Variant ◽  
The Impact

Radar images suffer from the impact of sidelobes. Several sidelobe-suppressing methods including the convolutional neural network (CNN)-based one has been proposed. However, the point spread function (PSF) in the radar images is sometimes spatially variant and affects the performance of the CNN. We propose the spatial-variant convolutional neural network (SV-CNN) aimed at this problem. It will also perform well in other conditions when there are spatially variant features. The convolutional kernels of the CNN can detect motifs with some distinctive features and are invariant to the local position of the motifs. This makes the convolutional neural networks widely used in image processing fields such as image recognition, handwriting recognition, image super-resolution, and semantic segmentation. They also perform well in radar image enhancement. However, the local position invariant character might not be good for radar image enhancement, when features of motifs (also known as the point spread function in the radar imaging field) vary with the positions. In this paper, we proposed an SV-CNN with spatial-variant convolution kernels (SV-CK). Its function is illustrated through a special application of enhancing the radar images. After being trained using radar images with position-codings as the samples, the SV-CNN can enhance the radar images. Because the SV-CNN reads information of the local position contained in the position-coding, it performs better than the conventional CNN. The advance of the proposed SV-CNN is tested using both simulated and real radar images.

scholarly journals Estimation of Ultrasound Echogenicity Map from B-Mode Images Using Convolutional Neural Network

Sensors ◽  
2020 ◽  
Vol 20 (17) ◽  
pp. 4931
Author(s):  
Che-Chou Shen ◽  
Jui-En Yang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Imaging System ◽  
Speckle Pattern ◽  
Image Resolution ◽  
Post Processing ◽  
Point Spread ◽  
Spread Function ◽  
In Silico Simulation ◽  
Tissue Structures

In ultrasound B-mode imaging, speckle noises decrease the accuracy of estimation of tissue echogenicity of imaged targets from the amplitude of the echo signals. In addition, since the granular size of the speckle pattern is affected by the point spread function (PSF) of the imaging system, the resolution of B-mode image remains limited, and the boundaries of tissue structures often become blurred. This study proposed a convolutional neural network (CNN) to remove speckle noises together with improvement of image spatial resolution to reconstruct ultrasound tissue echogenicity map. The CNN model is trained using in silico simulation dataset and tested with experimentally acquired images. Results indicate that the proposed CNN method can effectively eliminate the speckle noises in the background of the B-mode images while retaining the contours and edges of the tissue structures. The contrast and the contrast-to-noise ratio of the reconstructed echogenicity map increased from 0.22/2.72 to 0.33/44.14, and the lateral and axial resolutions also improved from 5.9/2.4 to 2.9/2.0, respectively. Compared with other post-processing filtering methods, the proposed CNN method provides better approximation to the original tissue echogenicity by completely removing speckle noises and improving the image resolution together with the capability for real-time implementation.

scholarly journals Recognition of wavefront aberrations types corresponding to single Zernike functions from the pattern of the point spread function in the focal plane using neural networks

2020 ◽  
Vol 44 (6) ◽  
pp. 923-930
Author(s):  
I.A. Rodin ◽  
S.N. Khonina ◽  
P.G. Serafimovich ◽  
S.B. Popov
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Point Spread Function ◽  
Focal Plane ◽  
Prediction Errors ◽  
Intensity Pattern ◽  
Data Set ◽  
Point Spread ◽  
The Neural Network ◽  
Spread Function

In this work, we carried out training and recognition of the types of aberrations corresponding to single Zernike functions, based on the intensity pattern of the point spread function (PSF) using convolutional neural networks. PSF intensity patterns in the focal plane were modeled using a fast Fourier transform algorithm. When training a neural network, the learning coefficient and the number of epochs for a dataset of a given size were selected empirically. The average prediction errors of the neural network for each type of aberration were obtained for a set of 15 Zernike functions from a data set of 15 thousand PSF pictures. As a result of training, for most types of aberrations, averaged absolute errors were obtained in the range of 0.012 – 0.015. However, determining the aberration coefficient (magnitude) requires additional research and data, for example, calculating the PSF in the extrafocal plane.

scholarly journals Euclid: Nonparametric point spread function field recovery through interpolation on a graph Laplacian

2020 ◽  
Vol 636 ◽  
pp. A78 ◽  
Author(s):  
M. A. Schmitz ◽  
J.-L. Starck ◽  
F. Ngole Mboula ◽  
N. Auricchio ◽  
J. Brinchmann ◽  
...  
Keyword(s):  
Point Spread Function ◽  
Super Resolution ◽  
Statistical Error ◽  
Graph Laplacian ◽  
Weak Lensing ◽  
Shape Measurement ◽  
Model Errors ◽  
Point Spread ◽  
Spread Function ◽  
The Impact

Context. Future weak lensing surveys, such as the Euclid mission, will attempt to measure the shapes of billions of galaxies in order to derive cosmological information. These surveys will attain very low levels of statistical error, and systematic errors must be extremely well controlled. In particular, the point spread function (PSF) must be estimated using stars in the field, and recovered with high accuracy. Aims. The aims of this paper are twofold. Firstly, we took steps toward a nonparametric method to address the issue of recovering the PSF field, namely that of finding the correct PSF at the position of any galaxy in the field, applicable to Euclid. Our approach relies solely on the data, as opposed to parametric methods that make use of our knowledge of the instrument. Secondly, we studied the impact of imperfect PSF models on the shape measurement of galaxies themselves, and whether common assumptions about this impact hold true in an Euclid scenario. Methods. We extended the recently proposed resolved components analysis approach, which performs super-resolution on a field of under-sampled observations of a spatially varying, image-valued function. We added a spatial interpolation component to the method, making it a true 2-dimensional PSF model. We compared our approach to PSFEx, then quantified the impact of PSF recovery errors on galaxy shape measurements through image simulations. Results. Our approach yields an improvement over PSFEx in terms of the PSF model and on observed galaxy shape errors, though it is at present far from reaching the required Euclid accuracy. We also find that the usual formalism used for the propagation of PSF model errors to weak lensing quantities no longer holds in the case of an Euclid-like PSF. In particular, different shape measurement approaches can react differently to the same PSF modeling errors.

scholarly journals Neural networks application to determine the types and magnitude of aberrations from the pattern of the point spread function out of the focal plane

2021 ◽  
Vol 2086 (1) ◽  
pp. 012148
Author(s):  
P A Khorin ◽  
A P Dzyuba ◽  
P G Serafimovich ◽  
S N Khonina
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Point Spread Function ◽  
Focal Plane ◽  
Prediction Errors ◽  
Point Spread ◽  
The Neural Network ◽  
Spread Function ◽  
The Mean

Abstract Recognition of the types of aberrations corresponding to individual Zernike functions were carried out from the pattern of the intensity of the point spread function (PSF) outside the focal plane using convolutional neural networks. The PSF intensity patterns outside the focal plane are more informative in comparison with the focal plane even for small values/magnitudes of aberrations. The mean prediction errors of the neural network for each type of aberration were obtained for a set of 8 Zernike functions from a dataset of 2 thousand pictures of out-of-focal PSFs. As a result of training, for the considered types of aberrations, the obtained averaged absolute errors do not exceed 0.0053, which corresponds to an almost threefold decrease in the error in comparison with the same result for focal PSFs.

Sign in / Sign up

Export Citation Format

Share Document