scholarly journals Research on Restoration Algorithm of Tomb Murals Based on Sequential Similarity Detection

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Wang Liu ◽  
Xiao Li ◽  
Fengjiao Wu
Keyword(s):  
Similarity Matching ◽  
Edge Information ◽  
Similarity Detection ◽  
Smooth Edge ◽  
Restoration Algorithm ◽  
Small Cracks ◽  
Matching Degree ◽  
Edge Features ◽  
The Mathematical Model ◽  
Labelling Algorithm

Considering the problems of fuzzy repair and low pixel similarity matching in the repair of existing tomb murals, we propose a novel tomb mural repair algorithm based on sequential similarity detection in this paper. First, we determine the gradient value of tomb mural through second-order Gaussian Laplace operator in LOG edge detection and then reduce the noise in the edge of tomb mural to process a smooth edge of tomb mural. Further, we set the mathematical model to obtain the edge features of tomb murals. To calculate the average gray level of foreground and background under a specific threshold, we use the maximum interclass variance method, which considers the influence of small cracks on the edge of tomb murals and separates the cracks through a connected domain labelling algorithm and open and close operations to complete the edge threshold segmentation. In addition, we use the priority calculation function to determine the damaged tomb mural area, calculate the gradient factor of edge information, obtain the information entropy of different angles, determine the priority of tomb mural image repair, detect the similarity of tomb mural repair pixels with the help of sequential similarity, and complete the tomb mural repair. Experimental results show that our model can effectively repair the edges of the tomb murals and can achieve a high pixel similarity matching degree.

DCNN-based Ship Classification using Enhanced Edge Information and Inception Module

2021 ◽  
Author(s):  
Bo Wang ◽  
Xiaoting Yu ◽  
Chengeng Huang ◽  
Qinghong Sheng ◽  
Yuanyuan Wang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Classification Performance ◽  
Image Features ◽  
Deep Convolutional Neural Networks ◽  
Edge Information ◽  
Average Accuracy ◽  
Ship Classification ◽  
Edge Features ◽  
High Level ◽  
Better Than

The excellent feature extraction ability of deep convolutional neural networks (DCNNs) has been demonstrated in many image processing tasks, by which image classification can achieve high accuracy with only raw input images. However, the specific image features that influence the classification results are not readily determinable and what lies behind the predictions is unclear. This study proposes a method combining the Sobel and Canny operators and an Inception module for ship classification. The Sobel and Canny operators obtain enhanced edge features from the input images. A convolutional layer is replaced with the Inception module, which can automatically select the proper convolution kernel for ship objects in different image regions. The principle is that the high-level features abstracted by the DCNN, and the features obtained by multi-convolution concatenation of the Inception module must ultimately derive from the edge information of the preprocessing input images. This indicates that the classification results are based on the input edge features, which indirectly interpret the classification results to some extent. Experimental results show that the combination of the edge features and the Inception module improves DCNN ship classification performance. The original model with the raw dataset has an average accuracy of 88.72%, while when using enhanced edge features as input, it achieves the best performance of 90.54% among all models. The model that replaces the fifth convolutional layer with the Inception module has the best performance of 89.50%. It performs close to VGG-16 on the raw dataset and is significantly better than other deep neural networks. The results validate the functionality and feasibility of the idea posited.

Image Interpolation Algorithm Based on Edge Features

2011 ◽  
Vol 50-51 ◽  
pp. 564-567
Author(s):  
Yun Feng Yang ◽  
Xiao Guang Wei ◽  
Zhi Xun Su
Keyword(s):  
Interpolation Method ◽  
Spline Interpolation ◽  
Weighted Average ◽  
Image Interpolation ◽  
Interpolation Process ◽  
Edge Information ◽  
B Spline ◽  
Interpolation Methods ◽  
Distance Weighted ◽  
Edge Features

Image interpolation is used widely in the computer vision. Holding edge information is main problem in the image interpolation. By using bilinear and bicubic B-spline interpolation methods, a novel image interpolation approach was proposed in this paper. Firstly, inverse distance weighted average method was used to reduce image’s noise. Secondly, edge detection operator was used to extract image's edges information. It can help us to select different interpolation methods in the image interpolation process. Finally, we selected bilinear interpolation approach at non-edge regions, and bicubic B-spline interpolation method was used near edges regions. Further more, control vertexes were computed from pixels with calculation formula which has been simplified in the B-spline interpolation process. Experiments showed the interpolated image by the proposed method had good vision results for it could hold image's edge information effectively.

scholarly journals Algorithm of web page similarity comparison based on visual block

2019 ◽  
Vol 16 (3) ◽  
pp. 815-830
Author(s):  
Xingchen Li ◽  
Weizhe Zhang ◽  
Desheng Wang ◽  
Bin Zhang ◽  
Hui He
Keyword(s):  
False Alarm ◽  
Web Pages ◽  
Web Page ◽  
Similarity Matching ◽  
Similarity Comparison ◽  
Matching Algorithm ◽  
Similarity Detection ◽  
Structure Similarity ◽  
Relative Similarity ◽  
The Web

Phishing often deceives users due to the relative similarity to the true pages on a layout and leads to considerable losses for the society. Consequently, detecting phishing sites has been an urgent activity. By researching phishing web pages using web page screenshots, we discover that this kind of web pages use numerous web page screenshots to achieve the close similarity to the true page and avoid the text and structure similarity detection. This study introduces a new similarity matching algorithm based on visual blocks. First, the RenderLayer tree of the web page is obtained to extract the visual block. Second, an algorithm that will settle the jumbled visual blocks, including the deletion of the small visual blocks and the emergence of the overlapping visual blocks, is designed. Finally, the similarity between the two web pages is assessed. The proposed algorithm sets different thresholds to achieve the optimal missing and false alarm rates.

An improved PolSAR image speckle reduction algorithm based on LMMSE and RICA

2017 ◽  
Vol 31 (19-21) ◽  
pp. 1740033 ◽  
Author(s):  
Chang Jiang ◽  
Xiufeng He
Keyword(s):  
San Francisco ◽  
Minimum Mean Square Error ◽  
Speckle Reduction ◽  
Edge Weight ◽  
Source Image ◽  
Edge Preservation ◽  
Edge Information ◽  
Polarimetric Synthetic Aperture Radar ◽  
Edge Features ◽  
Reduction Index

Although the linear minimum mean square error (LMMSE) filter removes speckle in polarimetric synthetic aperture radar (PolSAR) images, it has the disadvantage of losing edge detail. In this paper, we propose a new filter based on robust independent component analysis (RICA) and LMMSE. This approach describes edge features in a span image by selecting the adaptive direction window and calculating the edge weight value of the spatial domain, and improves the objective function by using a step polynomial to extract the estimate of the source image with minimum noise. This technique preserves not only the edge information in the images, but also the polarimetric information. Experiments were conducted on the NASA/JPL AIRSAR L-band of the San Francisco area, and evaluated by means of the speckle reduction index and the edge preservation index. The experimental results show that the proposed method effectively reduces speckle, retains edges, and preserves the polarimetric scattering mechanisms.

A Multi-Feature Fusion Method for Forward Vehicle Detection with Single Camera

2013 ◽  
Vol 321-324 ◽  
pp. 998-1004 ◽  
Author(s):  
Xing Li ◽  
Xiao Song Guo ◽  
Jun Bin Guo
Keyword(s):  
Shape Matching ◽  
Feature Fusion ◽  
Detection System ◽  
Vehicle Detection ◽  
Single Camera ◽  
Fusion Method ◽  
Threshold Method ◽  
Feature Based ◽  
Matching Degree ◽  
Edge Features

Vehicle detection is very important for Advanced Driver Assistance System. This paper focused on improving the performance of vehicle detection system with single camera and proposed a multi-feature fusion method for forward vehicle detection. The shadow and edges of the vehicle are the most important features, so they can be utilized to detect vehicle at daytime. The shadow and edge features were segmented accurately by using histogram analysis method and adaptive dual-threshold method respectively. The initial candidates were generated by combining edge and shadow features, and these initial candidates were further verified using an integrated feature based on the fusion of symmetry, texture and shape matching degree features. The weight of each feature was determined by the Fisher criterion, and the non-vehicle initial candidates were rejected by a threshold. The experimental results show that the proposed method could be adapt to different illumination circumstances robustly and improve the accuracy of forward vehicle detection.

Probing the Chemistry and Spectroscopy of Radiation-Sensitive Polymers by Parallel-Detection EELS

1990 ◽  
Vol 48 (2) ◽  
pp. 34-35
Author(s):  
E. G. Rightor ◽  
G. P. Young
Keyword(s):  
Electron Beam ◽  
Bisphenol A ◽  
Energy Loss ◽  
Parallel Detection ◽  
Commercial Grade ◽  
Incident Electron Beam ◽  
Ptfe Sample ◽  
Spectroscopic Information ◽  
Edge Features ◽  
Electron Energy Loss

Investigation of neat polymers by TEM is often thwarted by their sensitivity to the incident electron beam, which also limits the usefulness of chemical and spectroscopic information available by electron energy loss spectroscopy (EELS) for these materials. However, parallel-detection EELS systems allow reduced radiation damage, due to their far greater efficiency, thereby promoting their use to obtain this information for polymers. This is evident in qualitative identification of beam sensitive components in polymer blends and detailed investigations of near-edge features of homopolymers.Spectra were obtained for a poly(bisphenol-A carbonate) (BPAC) blend containing poly(tetrafluoroethylene) (PTFE) using a parallel-EELS and a serial-EELS (Gatan 666, 607) for comparison. A series of homopolymers was also examined using parallel-EELS on a JEOL 2000FX TEM employing a LaB6 filament at 100 kV. Pure homopolymers were obtained from Scientific Polymer Products. The PTFE sample was commercial grade. Polymers were microtomed on a Reichert-Jung Ultracut E and placed on holey carbon grids.

SIMULATION OF ELECTRICAL MONITORING OF DAMS WITH LEAKAGE WITH A TRANSVERSE PLACEMENT OF THE MEASURING INSTALLATION

2020 ◽  
Vol 8 (4) ◽  
pp. 69-82
Author(s):  
D.S. Rakisheva ◽  
◽  
B.G. Mukanova ◽  
I.N. Modin ◽  
◽  
...  
Keyword(s):  
Numerical Modeling ◽  
Water Level ◽  
Electrical Resistivity Tomography ◽  
Resistivity Tomography ◽  
Measuring Installation ◽  
Basic Functions ◽  
Tomography Method ◽  
Dam Monitoring ◽  
The Mathematical Model ◽  
Measurement Line

Numerical modeling of the problem of dam monitoring by the Electrical Resistivity Tomography method is carried out. The mathematical model is based on integral equations with a partial Fourier transform with respect to one spatial variable. It is assumed that the measurement line is located across the dam longitude. To approximate the shape of the dam surface, the Radial Basic Functions method is applied. The influence of locations of the water-dam, dam-basement, basement-leakage boundaries with respect to the sounding installation, which is partially placed under the headwater, is studied. Numerical modeling is carried out for the following varied parameters: 1) water level at the headwater; 2) the height of the leak; 3) the depth of the leak; 4) position of the supply electrode; 5) water level and leaks positions are changing simultaneously. Modeling results are presented in the form of apparent resistivity curves, as it is customary in geophysical practice.

DETERMINATION OF PERFORMANCE INDICATORS OF THE TRUCK KrAZ-6510TE

2020 ◽  
pp. 19-26
Author(s):  
Olexandr Pavlenko ◽  
Serhii Dun ◽  
Maksym Skliar
Keyword(s):  
Mathematical Model ◽  
Surface Friction ◽  
Building Structures ◽  
Maximum Torque ◽  
Military Equipment ◽  
Military Vehicles ◽  
Force Magnitude ◽  
Vehicle Mobility ◽  
The Mathematical Model

In any economy there is a need for the bulky goods transportation which cannot be divided into smaller parts. Such cargoes include building structures, elements of industrial equipment, tracked or wheeled construction and agricultural machinery, heavy armored military vehicles. In any case, tractor-semitrailer should provide fast delivery of goods with minimal fuel consumption. In order to guarantee the goods delivery, tractor-semitrailers must be able to overcome the existing roads broken grade and be capable to tow a semi-trailer in off-road conditions. These properties are especially important for military equipment transportation. The important factor that determines a tractor-semitrailer mobility is its gradeability. The purpose of this work is to improve a tractor-semitrailer mobility with tractor units manufactured at PJSC “AutoKrAZ” by increasing the tractor-semitrailer gradeability. The customer requirements for a new tractor are determined by the maximizing the grade to 18°. The analysis of the characteristics of modern tractor-semitrailers for heavy haulage has shown that the highest rate of this grade is 16.7°. The factors determining the limiting gradeability value were analyzed, based on the tractor-semitrailer with a KrAZ-6510TE tractor and a semi-trailer with a full weight of 80 t. It has been developed a mathematical model to investigate the tractor and semi-trailer axles vertical reactions distribution on the tractor-semitrailer friction performances. The mathematical model has allowed to calculate the gradeability value that the tractor-semitrailer can overcome in case of wheels and road surface friction value and the tractive force magnitude from the engine. The mathematical model adequacy was confirmed by comparing the calculations results with the data of factory tests. The analysis showed that on a dry road the KrAZ-6510TE tractor with a 80 t gross weight semitrailer is capable to climb a gradient of 14,35 ° with its coupling mass full use condition. The engine's maximum torque allows the tractor-semitrailer to overcome a gradient of 10.45° It has been determined the ways to improve the design of the KrAZ-6510TE tractor to increase its gradeability. Keywords: tractor, tractor-semitrailer vehicle mobility, tractor-semitrailer vehicle gradeability.

EXPERIMENTAL STUDIES OF CAR PROPERTIES ON A PHYSICAL MODEL

2019 ◽  
pp. 10-16
Author(s):  
Oleksii Timkov ◽  
Dmytro Yashchenko ◽  
Volodymyr Bosenko
Keyword(s):  
Mathematical Model ◽  
Remote Control ◽  
Physical Model ◽  
Model Experiment ◽  
Experimental Studies ◽  
Electrical Energy ◽  
Short Term ◽  
Motor Current ◽  
Memory Card ◽  
The Mathematical Model

The article deals with the development of a physical model of a car equipped with measuring, recording and remote control equipment for experimental study of car properties. A detailed description of the design of the physical model and of the electronic modules used is given, links to application libraries and the code of the first part of the program for remote control of the model are given. Atmega microcontroller on the Arduino Uno platform was used to manage the model and register the parameters. When moving the car on the memory card saved such parameters as speed, voltage on the motor, current on the motor, the angle of the steered wheel, acceleration along three coordinate axes are recorded. Use of more powerful microcontrollers will allow to expand the list of the registered parameters of movement of the car. It is possible to measure the forces acting on the elements of the car and other parameters. In the future, it is planned to develop a mathematical model of motion of the car and check its adequacy in conducting experimental studies on maneuverability on the physical model. In addition, it is possible to conduct studies of stability and consumption of electrical energy. The physical model allows to quickly change geometric dimensions and mass parameters. In the study of highway trains, this approach will allow to investigate the various layout schemes of highway trains in the short term. It is possible to make two-axle road trains and saddle towed trains, three-way hitched trains of different layout. The results obtained will allow us to improve not only the mathematical model, but also the experimental physical model, and move on to further study the properties of hybrid road trains with an active trailer link. This approach allows to reduce material and time costs when researching the properties of cars and road trains. Keywords: car, physical model, experiment, road trains, sensor, remote control, maneuverability, stability.

Sign in / Sign up

Export Citation Format

Share Document