Automated vision system for quality inspection of slate slabs

Iglesias, Carla; Martínez, Javier Martínez; Taboada, J.

doi:10.1016/j.compind.2018.03.030

Cited by 59 publications

(33 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the number of neurons in the hidden layer is finally set to the type of rising firstly and then horizontal values, which is used for reliability analysis of power distribution network. The data samples used in this research were collected using the Canadian power system's CYME software [38].The sample has 209 input features in total, so the number of neurons in the input layer is 209. The four indexes of the reliability analysis of the power distribution network are used as the output indexes of the network, so the number of neurons in the output layer is set to 4.…”

Section: Tableⅱ Influence Of the Number Of Nodes In The Hidden Layermentioning

confidence: 99%

Reliability Analysis of Power Distribution Network Based on PSO-DBN

et al. 2020

View full text Add to dashboard Cite

The main problem dealt with in this paper is to find a method to improve the performance of the reliability analysis of power distribution networks. With the help of deep learning, which has the characteristics of large-scale parallel processing and self-learning, a deep belief network (DBN) simulation model for power distribution network reliability analysis is established. After training RBM layer by layer and extracting feature information from complex data, DBN model parameters are adaptively adjusted by particle swarm optimization (PSO) algorithm. The results of power distribution network reliability analysis based on PSO-DBN model is compared with those of Monte Carlo model. In order to evaluate the performance of the proposed model, the coefficient R 2 , the mean absolute error and the root mean square error are used to evaluate the model. The results show that the reliability analysis model based on PSO-DBN is more accurate, and the reliability analysis efficiency of the trained PSO-DBN model is higher, which to some extent proves the superiority of applying deep neural network to the reliability analysis of distribution network.

show abstract

Section: Tableⅱ Influence Of the Number Of Nodes In The Hidden Layermentioning

confidence: 99%

Reliability Analysis of Power Distribution Network Based on PSO-DBN

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The paper describes defects in roofing slates, parameters describing their quality and method of those parameter control. In [8,9], the authors present machine learning methods 2 of 13 in the task of identifying defective slate slabs and present the differences in the results to the adopted learning method.…”

Section: Introductionmentioning

confidence: 99%

Automated Control of Surface Defects on Ceramic Tiles Using 3D Image Analysis

Sioma

2020

Materials

View full text Add to dashboard Cite

This paper presents a method of acquisition and analysis of three-dimensional images in the task of automatic location and evaluation of defects on the surface of ceramic tiles. It presents a brief description of selected defects appearing on the surface of tiles, along with the analysis of their formation. The paper includes the presentation of the method of constructing a 3D image of the tile surface using the Laser Triangulation Method (LTM), along with the surface imaging parameters employed in the research. The algorithms of three-dimensional surface image analysis of ceramic tiles used in the process of image filtering and defect identification are presented. For selected defects, the method of measuring defect parameters and the method of visualization of defects on the surface are also presented. The developed method was tested on defective products to confirm its effectiveness in the field of quick defect detection in automated control systems installed on production lines.

show abstract

“…In addition, in order to achieve zero defect QC systems, machine vision systems have emerged as intelligent technologies for visual inspection of different attributes in wide range industries [4], [61]. For examples, in [21] an algorithm has been proposed for describing an automated inspection system in order to test slate slabs by a 3D color camera and study slate slab characteristics through using some algorithms in computer vision. In their model, texture…”

Section: Introductionmentioning

confidence: 99%

“…analysis had been used to extract required features before applying a neural network classifier [21]. In [44], authors proposed an algorithm of computer vision in order to measure and inspect O-rings.…”

Section: Introductionmentioning

confidence: 99%

A Machine Learning-Based Approach for Counting Blister Cards Within Drug Packages

Bahaghighat¹,

Akbari²,

Xin

2019

IEEE Access

View full text Add to dashboard Cite

Nowadays with the rapid development of technologies, machine vision has been used widely in various industries. The main applications of machine vision in industrial product lines are quality control (QC) and quality assurance (QA). The intelligent defects and anomalies recognition throughout the supply chain have come to be an integral part of quality control systems, in particular, in the food and pharmaceutical industries. In these industries, it is a legal requirement in manufacturing processes which can lead to minimizing the total number of defected products as well as maximizing the performance. In this paper, the machine vision has been utilized to monitor and control the proper packaging of drugs in pharmaceutical product lines. The main goal is counting the number of blister cards within a drug package. To tackle this problem, a new model based on object detection, feature extraction, and classification is proposed. Thanks to several strong approaches, such as the Haar cascade, HOG, ORG, Gabor wavelet, Radon transform, KNN, and SVM, and the accuracy over 88% is achieved in our experiments.

show abstract

Automated vision system for quality inspection of slate slabs

Cited by 59 publications

References 38 publications

Reliability Analysis of Power Distribution Network Based on PSO-DBN

Reliability Analysis of Power Distribution Network Based on PSO-DBN

Automated Control of Surface Defects on Ceramic Tiles Using 3D Image Analysis

A Machine Learning-Based Approach for Counting Blister Cards Within Drug Packages

Contact Info

Product

Resources

About