scholarly journals Shade recognition of the color label based on the fuzzy clustering

2021 ◽  
Vol 20 (2) ◽  
pp. 407-434
Author(s):  
Maxim Bobyr ◽  
Alexander Arkhipov ◽  
Aleksey Yakushev
Keyword(s):  
Fuzzy Clustering ◽  
Color Image ◽  
Vision System ◽  
Video Recording ◽  
Experimental Studies ◽  
Area Ratio ◽  
Center Of Gravity ◽  
Clustering Model ◽  
Technical Vision ◽  
Fuzzy Clustering Method

In this article the task of determining the current position of pneumatic actuators is considered. The solution to the given task is achieved by using a technical vision system that allows to apply the fuzzy clustering method to determine in real time the center coordinates and the displacement position of a color label located on the mechatronic complex actuators. The objective of this work is to improve the accuracy of the moving actuator’s of mechatronic complex by improving the accuracy of the color label recognition. The intellectualization of process of the color shade recognition is based on fuzzy clustering. First, a fuzzy model is built, that allows depending on the input parameters of the color intensity for each of the RGB channels and the color tone component, to select a certain color in the image. After that, the color image is binarized and noise is suppressed. The authors used two defuzzification models during simulation a fuzzy system: one is based on the center of gravity method (CoG) and the other is based on the method of area ratio (MAR). The model is implemented based on the method of area ratio and allows to remove the dead zones that are present in the center of gravity model. The method of area ratio determines the location of the color label in the image frame. Subsequently, when the actuator is moved longitudinally, the vision system determines the location of the color label in the new frame. The color label position offset between the source and target images allows to determine the moved distance of the color label. In order to study  how noise affects recognition accuracy, the following digital filters were used: median, Gaussian, matrix and binomial. Analysis of the accuracy of these filters showed that the best result was obtained when using a Gaussian filter. The estimation was based on the signal-to-noise coefficient. The mathematical models of fuzzy clustering of color label recognition were simulated in the Matlab/Simulink environment. Experimental studies of technical vision system performance with the proposed fuzzy clustering model were carried out on a pneumatic mechatronic complex that performs processing, moving and storing of details. During the experiments, a color label was placed on the cylinder, after which the cylinder moved along the guides in the longitudinal direction. During the movement, video recording and image recognition were performed. To determine the accuracy of color label recognition, the PSNR and RMSE coefficients were calculated which were equal 38.21 and 3.14, respectively. The accuracy of determining the displacement based on the developed model for recognizing color labels was equal 99.7%. The defuzzifier speed has increased to 590 ns.

Grid Resources’ Fuzzy Clustering Based on Mobile Agent

2011 ◽  
Vol 467-469 ◽  
pp. 1038-1043
Author(s):  
Dong Guo ◽  
Qiang Li ◽  
Meng Zhang ◽  
Bing Xin Guo ◽  
Liang Hu
Keyword(s):  
Fuzzy Clustering ◽  
Mobile Agent ◽  
Mobile Agents ◽  
Grid Resource ◽  
Simulation Experiments ◽  
Clustering Model ◽  
Fuzzy Clustering Method ◽  
Speed Up ◽  
Grid Nodes ◽  
Grid Resources

To speed up grid resources’ clustering, this paper presents a grid resource fuzzy clustering model based on mobile agent. A fuzzy clustering task is decomposed into some parallel subtasks which then are distributed to some grid nodes for parallel processing by using mobile agents through B-shift algorithm so as to improve clustering efficiency. This paper implements grid resources’ fuzzy clustering based on mobile agent with Aglet platform, and evaluates the performances through simulation experiments. The experiments show that the clustering time of this method is shorter than that of center fuzzy clustering method.

scholarly journals Use of Variable Fuzzy Clustering to Quantify the Vulnerability of a Power Grid to Earthquake Damage

2019 ◽  
Vol 11 (20) ◽  
pp. 5633
Author(s):  
Tianhua Li ◽  
Yanchao Du ◽  
Yongbo Yuan
Keyword(s):  
Fuzzy Clustering ◽  
Power Grid ◽  
Well Being ◽  
Earthquake Damage ◽  
Hierarchical Level ◽  
Critical Threshold ◽  
Network Vulnerability ◽  
Clustering Model ◽  
Fuzzy Clustering Method ◽  
New Perspective

The power grid is a critical component of city infrastructure. If it is damaged by an earthquake, there can be a huge impact on the safety and well-being of society and individuals. Identifying nodes in the grid that are highly vulnerable to earthquake damage is significant for effective pre-earthquake damage prevention, emergency response, and post-earthquake relief. Three indicators, the probability of node disconnection, the node hierarchical level, and the node critical threshold, were chosen, and their combined ability to represent node vulnerability to damage from an earthquake event was analyzed. A variable fuzzy clustering model was used to classify and order the nodes in the grid. The 20-node power grid of a city was used as an example to show how highly vulnerable nodes were identified, and how the reasons for the high vulnerability of these nodes were drawn out of the analysis. Countermeasures were given to reduce network vulnerability. The variable fuzzy clustering method used in this paper offers a new perspective on network vulnerability, and it quantifies the vulnerability of grid nodes more comprehensively than existing methods of assessing grid vulnerability. This research is significant as a baseline reference for future studies of grid vulnerability.

Semantic Color Retrieval of Color Image Based on Fuzzy Clustering

2013 ◽  
Vol 380-384 ◽  
pp. 3469-3473
Author(s):  
Xiao Feng Wang ◽  
Jian Hua Li
Keyword(s):  
Image Segmentation ◽  
Fuzzy Clustering ◽  
Clustering Algorithm ◽  
Color Image ◽  
Color Image Segmentation ◽  
Fuzzy Clustering Method ◽  
Retrieval Mechanism ◽  
Previous Algorithm ◽  
Physical Features ◽  
Initial Focus

As next generation of the web, the semantic web aims at a more intelligent web severing machines as well as people, based on radical notions of information sharing and acquisition. For color image segmentation, semantic color is our focus. One method of color partition is fuzzy clustering which has been widely used in image segmentation. However, the fuzzy clustering algorithm is parameter sensitive, and lack of availability because of its initial focus on physical features. To improve the above problems, a novel fuzzy clustering method based on semantic color retrieval for image segmentation is proposed in this paper. The method is realized by modifying the membership function in the conventional clustering algorithm and by constructing the semantic color retrieval mechanism to achieve the semantic color extraction, which take human visual subjectivity into account in semantics. Experimental results show that the presented method performs more effectively than the previous algorithm.

scholarly journals Filtering a Signal in a Fuzzy Filter Based on the Area Ratio Method

2020 ◽  
Vol 24 (3) ◽  
pp. 183-195
Author(s):  
M. V. Bobyr ◽  
M. Yu. Luneva
Keyword(s):  
Kalman Filter ◽  
Digital Filter ◽  
Experimental Studies ◽  
Area Ratio ◽  
Center Of Gravity ◽  
Ratio Method ◽  
Fuzzy Filter ◽  
Signal Filtering ◽  
Gravity Method ◽  
Control Coefficients

Purpose of reseach. Digital signal filtering allows real-time noise reduction in electronic devices. Currently, there are many different digital filters, differing in speed, computing power, algorithms and restrictions on the conditions of use. One of these filters is the Kalman filter, but adjusting the gains of this filter is very complicated by the process of additional experiments and collection of statistical information. Therefore, in this paper, the authors consider a simplified algorithm for finding the control coefficients of a fuzzy digital filter with defuzzifier based on the area ratio method and investigate the influence of the area ratio method parameters on signal filtering, thereby achieving the goal of improving the accuracy of the fuzzy digital filter. Methods. For the algorithm for finding the control coefficients of the digital filter, a fuzzy logic apparatus was used. The control factors are determined using a defuzzifier based on the area ratio method. Results. In the course of experimental studies, the mean square error RMSE was calculated for a fuzzy digital filter using the area ratio method, the center of gravity method and the Kalman filter. Based on the results obtained, it was concluded that the fuzzy filter based on the area ratio RMSE method is 5.43 times less than for the Kalman filter and 2.77 times less than for the defuzzifier based on the center of gravity method. The results obtained prove the effectiveness of using a fuzzy digital filter with the area ratio method. Conclusion: This article considers an algorithm for the operation of a fuzzy digital filter, simulates a fuzzy digital filter and a Kalman filter in the Simulink system and calculates the RMSE values for a fuzzy digital filter with the area ratio method and the center of gravity method, as well as the Kalman filter.

scholarly journals Television images identification in the vision system basis on the mathematical apparatus of cubic normalized B-splines

2017 ◽  
Vol 14 (3) ◽  
pp. 387-399 ◽  
Author(s):  
Vladimir Krutov ◽  
Dmitriy Bezuglov ◽  
Viacheslav Voronin
Keyword(s):  
Background Noise ◽  
Autonomous Robots ◽  
Vision System ◽  
Experimental Studies ◽  
Numerical Differentiation ◽  
Mathematical Apparatus ◽  
B Splines ◽  
Technical Vision ◽  
Priori Information ◽  
Selection Operator

The solution the task of television image identification is used in industry when creating autonomous robots and systems of technical vision. A similar problem also arises in the development of image analysis systems to function under the influence of various interfering factors in complex observation conditions complicated the registration process and existing when priori information is absent, in background noise type. One of the most important operators is the contour selection operator. Methods and algorithms of processing information from image sensors must take into account the different character of noise associated with images and signals registration. The solution of the task of isolating contours, and in fact of digital differentiation of two-dimensional signals registered against a different character of background noise, is far from trivial. This is due to the fact that such task is incorrect. In modern information systems, methods of numerical differentiation or masks are usually used to solve the task of isolating contours. The paper considers a new method of differentiating measurement results against a noise background using the modern mathematical apparatus of cubic smoothing B-splines. The new high-precision method of digital differentiation of signals using splines is proposed for the first time, without using standard numerical differentiation procedures, to calculate the values of the derivatives with high accuracy. In fact, a method has been developed for calculating the image gradient module using spline differentiation. The method, as proved by experimental studies, and computational experiments has higher noise immunity than algorithms based on standard differentiation procedures using masks.

Sign in / Sign up

Export Citation Format

Share Document