Image extraction using convolution kernal

This paper discusses about the noise reduction of images using the convolution matrix. The convolution kernel matrix filters generate new features of the input images with good quality.The noise reduction methods based on convolution kernel is achieved by deep learning theory along with the difference equations. The random variation of the colour and brightness are taken as authenticated coefficients of the images. Convolution techniques along withrecurrent neuralnetwork are applied into theinput image. This input image is divided into the matrix of pixel values. The optimal enhanced image is arrived through convolution kernel using computational learning of autonomous difference equations.

Download Full-text

Finiteness Properties of Affine Difference Algebraic Groups

International Mathematics Research Notices ◽

10.1093/imrn/rnaa177 ◽

2020 ◽

Cited By ~ 1

Author(s):

Michael Wibmer

Keyword(s):

Differential Equation ◽

Linear Differential Equation ◽

Difference Equations ◽

General Linear Group ◽

Algebraic Groups ◽

The Matrix ◽

Algebraic Difference ◽

The Difference ◽

Linear Differential ◽

Finiteness Properties

Abstract We establish several finiteness properties of groups defined by algebraic difference equations. One of our main results is that a subgroup of the general linear group defined by possibly infinitely many algebraic difference equations in the matrix entries can indeed be defined by finitely many such equations. As an application, we show that the difference ideal of all difference algebraic relations among the solutions of a linear differential equation is finitely generated.

Download Full-text

Effect of acoustic Doppler velocimeter sampling volume size on measurements of turbulence

Journal of Atmospheric and Oceanic Technology ◽

10.1175/jtech-d-20-0174.1 ◽

2020 ◽

Author(s):

Mohammad Kazemi ◽

Babak Khorsandi ◽

Laurent Mydlarski

Keyword(s):

Noise Reduction ◽

Radial Profile ◽

Velocity Shear ◽

Mean Velocity ◽

Reduction Methods ◽

Sampling Volume ◽

The Difference ◽

Highly Correlated ◽

Velocity Variances ◽

Volume Size

AbstractThe relatively large sampling volume of acoustic Doppler velocimeters (ADVs) is expected to influence their measurement of turbulence. To study this effect, a series of experiments using different sampling volume sizes was conducted in an axisymmetric turbulent jet. The results show that the mean velocities are not significantly affected by the size of the sampling volume. On the other hand, reducing the sampling volume size results in an increase in the variances of the u and v velocities, while its effect on the variance of the w-velocity is negligible. Application of a noise reduction method to the data renders the velocity variances nearly independent of sampling volume size, suggesting that the difference was mainly due to Doppler noise. The principal conclusion of this work is therefore that – as long as the characteristic length of sampling volume is much smaller than the integral length scale of flow – increasing the sampling volume size (i.e., increasing spatial averaging over highly correlated scatterers) can reduce Doppler noise and result in more accurate measurements of the velocity variances. Application of noise reduction methods to the data is found to be especially important when the sampling volume size is reduced to capture smaller scales, or for near-boundary measurements. Furthermore, noise due to mean velocity shear, even at the largest velocity gradient along the jet radial profile, is found to be negligible in the present work.

Download Full-text

Tem analysis of multiple-energy arsenic implanted and Rta'd silicon

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100126135 ◽

1987 ◽

Vol 45 ◽

pp. 246-247

Author(s):

R.A. Herring

Keyword(s):

Device Fabrication ◽

High Concentration ◽

Tem Analysis ◽

Defect Clusters ◽

High Fluences ◽

Small Defect ◽

Before And After ◽

The Matrix ◽

The Difference ◽

Factor Type

Rapid thermal annealing (RTA) of ion-implanted Si is important for device fabrication. The defect structures of 2.5, 4.0, and 6.0 MeV As-implanted silicon irradiated to fluences of 2E14, 4E14, and 6E14, respectively, have been analyzed by electron diffraction both before and after RTA at 1100°C for 10 seconds. At such high fluences and energies the implanted As ions change the Si from crystalline to amorphous. Three distinct amorphous regions emerge due to the three implantation energies used (Fig. 1). The amorphous regions are separated from each other by crystalline Si (marked L1, L2, and L3 in Fig. 1) which contains a high concentration of small defect clusters. The small defect clusters were similar to what had been determined earlier as being amorphous zones since their contrast was principally of the structure-factor type that arises due to the difference in extinction distance between the matrix and damage regions.

Download Full-text

Development of Prolonged Delivery of Tramadol and Dissolution Translation by Statistical Data Treatment

International Journal of Pharmaceutical Sciences and Nanotechnology ◽

10.37285/ijpsn.2011.4.1.5 ◽

2011 ◽

Vol 4 (1) ◽

pp. 1331-1337

Author(s):

P B Parejiya ◽

B S Barot ◽

P K Shelat

Keyword(s):

Drug Release ◽

Study Data ◽

Stability Study ◽

Dissolution Time ◽

Matrix Tablet ◽

Burst Effect ◽

The Matrix ◽

The Mean ◽

The Difference ◽

Dissolution Efficiency

The present study was carried out to fabricate a prolonged design for tramadol using Kollidon SR (Polyvinyl acetate and povidone based matrix retarding polymer). Matrix tablet formulations were prepared by direct compression of Kollidon SR of a varying proportion with a fixed percentage of tramadol. Tablets containing a 1:0.5 (Drug: Kollidon SR) ratio exhibited a rapid rate of drug release with an initial burst effect. Incorporation of more Kollidon SR in the matrix tablet extended the release of drug with subsequent minimization of the burst effect as confirmed by the mean dissolution time, dissolution efficiency and f2 value. Among the formulation batches, a direct relationship was obtained between release rate and the percentage of Kollidon SR used. The formulation showed close resemblance to the commercial product Contramal and compliance with USP specification. The results were explored and explained by the difference of micromeritic characteristics of the polymers and blend of drug with excipients. Insignificant effects of various factors, e.g. pH of dissolution media, ionic strength, speed of paddle were found on the drug release from Kollidon-SR matrix. The formulation followed the Higuchi kinetic model of drug release. Stability study data indicated stable character of Batch T6 after short-term stability study.

Download Full-text

Analyzing the difference between deep learning and machine learning features of EEG signal using clustering techniques

2019 IEEE Region 10 Symposium (TENSYMP) ◽

10.1109/tensymp46218.2019.8971358 ◽

2019 ◽

Author(s):

Anushri Saha ◽

Sachin Singh Rathore ◽

Shivam Sharma ◽

Debasis Samanta

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Eeg Signal ◽

Clustering Techniques ◽

The Difference

Download Full-text

A Stochastic Model for Block Segmentation of Images Based on the Quadtree and the Bayes Code for It

Entropy ◽

10.3390/e23080991 ◽

2021 ◽

Vol 23 (8) ◽

pp. 991

Author(s):

Yuta Nakahara ◽

Toshiyasu Matsushima

Keyword(s):

Computational Cost ◽

Block Size ◽

Input Image ◽

Generative Model ◽

Image Size ◽

Variable Block ◽

General Data ◽

The Difference ◽

Segmentation Of Images ◽

Target Data

In information theory, lossless compression of general data is based on an explicit assumption of a stochastic generative model on target data. However, in lossless image compression, researchers have mainly focused on the coding procedure that outputs the coded sequence from the input image, and the assumption of the stochastic generative model is implicit. In these studies, there is a difficulty in discussing the difference between the expected code length and the entropy of the stochastic generative model. We solve this difficulty for a class of images, in which they have non-stationarity among segments. In this paper, we propose a novel stochastic generative model of images by redefining the implicit stochastic generative model in a previous coding procedure. Our model is based on the quadtree so that it effectively represents the variable block size segmentation of images. Then, we construct the Bayes code optimal for the proposed stochastic generative model. It requires the summation of all possible quadtrees weighted by their posterior. In general, its computational cost increases exponentially for the image size. However, we introduce an efficient algorithm to calculate it in the polynomial order of the image size without loss of optimality. As a result, the derived algorithm has a better average coding rate than that of JBIG.

Download Full-text

Deep Learning-Based Congestion Detection at Urban Intersections

Sensors ◽

10.3390/s21062052 ◽

2021 ◽

Vol 21 (6) ◽

pp. 2052

Author(s):

Xinghai Yang ◽

Fengjiao Wang ◽

Zhiquan Bai ◽

Feifei Xun ◽

Yulin Zhang ◽

...

Keyword(s):

Deep Learning ◽

Optical Flow ◽

Traffic Congestion ◽

Detection Algorithm ◽

Input Image ◽

Vehicle Speed ◽

Position Information ◽

Traffic State ◽

State Discrimination ◽

Discrimination Method

In this paper, a deep learning-based traffic state discrimination method is proposed to detect traffic congestion at urban intersections. The detection algorithm includes two parts, global speed detection and a traffic state discrimination algorithm. Firstly, the region of interest (ROI) is selected as the road intersection from the input image of the You Only Look Once (YOLO) v3 object detection algorithm for vehicle target detection. The Lucas-Kanade (LK) optical flow method is employed to calculate the vehicle speed. Then, the corresponding intersection state can be obtained based on the vehicle speed and the discrimination algorithm. The detection of the vehicle takes the position information obtained by YOLOv3 as the input of the LK optical flow algorithm and forms an optical flow vector to complete the vehicle speed detection. Experimental results show that the detection algorithm can detect the vehicle speed and traffic state discrimination method can judge the traffic state accurately, which has a strong anti-interference ability and meets the practical application requirements.

Download Full-text

Deep learning-based framework for the distinction of membranous nephropathy: a new approach through hyperspectral imagery

BMC Nephrology ◽

10.1186/s12882-021-02421-y ◽

2021 ◽

Vol 22 (1) ◽

Author(s):

Tianqi Tu ◽

Xueling Wei ◽

Yue Yang ◽

Nianrong Zhang ◽

Wei Li ◽

...

Keyword(s):

Deep Learning ◽

Renal Biopsy ◽

Membranous Nephropathy ◽

Learning Algorithm ◽

Hyperspectral Imagery ◽

Chinese Patients ◽

Support Vector ◽

Deep Learning Algorithm ◽

The Difference ◽

Complex Deposition

Abstract Background Common subtypes seen in Chinese patients with membranous nephropathy (MN) include idiopathic membranous nephropathy (IMN) and hepatitis B virus-related membranous nephropathy (HBV-MN). However, the morphologic differences are not visible under the light microscope in certain renal biopsy tissues. Methods We propose here a deep learning-based framework for processing hyperspectral images of renal biopsy tissue to define the difference between IMN and HBV-MN based on the component of their immune complex deposition. Results The proposed framework can achieve an overall accuracy of 95.04% in classification, which also leads to better performance than support vector machine (SVM)-based algorithms. Conclusion IMN and HBV-MN can be correctly separated via the deep learning framework using hyperspectral imagery. Our results suggest the potential of the deep learning algorithm as a new method to aid in the diagnosis of MN.

Download Full-text

Image-based textile decoding

Integrated Computer-Aided Engineering ◽

10.3233/ica-200647 ◽

2020 ◽

pp. 1-14

Author(s):

Siqiang Chen ◽

Masahiro Toyoura ◽

Takamasa Terada ◽

Xiaoyang Mao ◽

Gang Xu

Keyword(s):

Deep Learning ◽

Grid Point ◽

Intermediate Representation ◽

Training Set ◽

Binary Matrix ◽

The Matrix ◽

Correct Pattern ◽

Grid Points ◽

Textile Fabric ◽

Direct Correspondence

A textile fabric consists of countless parallel vertical yarns (warps) and horizontal yarns (wefts). While common looms can weave repetitive patterns, Jacquard looms can weave the patterns without repetition restrictions. A pattern in which the warps and wefts cross on a grid is defined in a binary matrix. The binary matrix can define which warp and weft is on top at each grid point of the Jacquard fabric. The process can be regarded as encoding from pattern to textile. In this work, we propose a decoding method that generates a binary pattern from a textile fabric that has been already woven. We could not use a deep neural network to learn the process based solely on the training set of patterns and observed fabric images. The crossing points in the observed image were not completely located on the grid points, so it was difficult to take a direct correspondence between the fabric images and the pattern represented by the matrix in the framework of deep learning. Therefore, we propose a method that can apply the framework of deep learning viau the intermediate representation of patterns and images. We show how to convert a pattern into an intermediate representation and how to reconvert the output into a pattern and confirm its effectiveness. In this experiment, we confirmed that 93% of correct pattern was obtained by decoding the pattern from the actual fabric images and weaving them again.

Download Full-text