Quality inspection method of micro-nano parts based on deep learning

2018 ◽  
Vol 32 (30) ◽  
pp. 1850363
Author(s):  
Dongjie Li ◽  
Cong Liu
Keyword(s):  
Deep Learning ◽  
Detection System ◽  
Detection Methods ◽  
Work Intensity ◽  
Inspection Method ◽  
Image Information ◽  
Manual Methods ◽  
Low Efficiency ◽  
High Work

There are some disadvantages such as low efficiency, high work intensity by using the manual methods to detect the quality of micro-nano parts because of the characteristics such as small size and fragile structure. Considering about the disadvantages, computer microscopic vision is introduced into the detection system in this paper, which can collects the image information of the parts into the computer system efficiently. The parts to be detected are transmitted by the spin material platform driven by the stepping motor. It is CNN based on deep learning that used to detect the surface quality and classify the defects of the parts according to the image information in this paper, which can improve the accuracy of the detection and reduce the work intensity of human compared with not only the traditional manual detection methods but also some edge detection methods that former researchers used.

scholarly journals Mining and Reuse on Design Knowledge of Non-standard Special Tool Based on Deep Learning

2020 ◽  
Author(s):  
Mingwei Wang ◽  
Jingtao Zhou ◽  
Xiaoying Chen ◽  
Zeyu Li
Keyword(s):  
Deep Learning ◽  
Association Rule ◽  
Deep Belief Network ◽  
Design Knowledge ◽  
Machining Features ◽  
Belief Network ◽  
Dual Channel ◽  
Engineering Drawings ◽  
Low Efficiency

Abstract Aiming at the problems of design difficulty, low efficiency and unstable quality of non-standard special tools, facing the strong correlation between part machining features and tools, this article takes the two-dimensional engineering drawings of tools and parts as research objects, proposes the research on mining and reuse on design knowledge of non-standard special tool based on deep learning. Firstly, a dual-channel deep belief network is established to complete the feature modeling of machining features and tool features; secondly, the deep belief network is used to realize the association relationship mining between the machining features and tool features; thirdly, both the key local features of the tool and the overall similar design case of the tool are reused through association rule reasoning; finally, the non-standard special turning tool is used as an example to verify the effectiveness of the proposed method.

scholarly journals Robust Self-Adaptation Fall-Detection System Based on Camera Height

Sensors ◽  
2019 ◽  
Vol 19 (17) ◽  
pp. 3768 ◽  
Author(s):  
Kong ◽  
Chen ◽  
Wang ◽  
Chen ◽  
Meng ◽  
...  
Keyword(s):  
Deep Learning ◽  
Detection System ◽  
Fall Detection ◽  
Daily Activities ◽  
Detection Methods ◽  
Depth Camera ◽  
Detection Accuracy ◽  
Data Set ◽  
Human Segmentation ◽  
Self Adaptation

Vision-based fall-detection methods have been previously studied but many have limitations in terms of practicality. Due to differences in rooms, users do not set the camera or sensors at the same height. However, few studies have taken this into consideration. Moreover, some fall-detection methods are lacking in terms of practicality because only standing, sitting and falling are taken into account. Hence, this study constructs a data set consisting of various daily activities and fall events and studies the effect of camera/sensor height on fall-detection accuracy. Each activity in the data set is carried out by eight participants in eight directions and taken with the depth camera at five different heights. Many related studies heavily depended on human segmentation by using Kinect SDK but this is not reliable enough. To address this issue, this study proposes Enhanced Tracking and Denoising Alex-Net (ETDA-Net) to improve tracking and denoising performance and classify fall and non-fall events. Experimental results indicate that fall-detection accuracy is affected by camera height, against which ETDA-Net is robust, outperforming traditional deep learning based fall-detection methods.

5G Edge Cloud Power Real-time Inspection Technology Based on YOLOV4-Tiny

2021 ◽  
Author(s):  
Jiaqi Song ◽  
Jing Li ◽  
Di Wu ◽  
Guangye Li ◽  
Jiaxin Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
High Efficiency ◽  
Real Data ◽  
Detection Algorithm ◽  
Power Line ◽  
Edge Computing ◽  
Inspection Method ◽  
Computing Architecture ◽  
Low Efficiency

Power line corridor inspection plays a vital role in power system safe operation, traditional human inspection’s low efficiency makes the novel inspection method requiring high precision and high efficiency. Combined with the current deep learning target detection algorithm based on high accuracy and strong real-time performance, this paper proposes a YOLOV4-Tiny based drone real-time power line inspection method. The 5G and edge computing technology are combined properly forming a complete edge computing architecture. The UAV is treated as an edge device with a YOLOV4-Tiny deep- learning-based object detection model and AI chip on board. Extensive experiments on real data demonstrate the 5G and Edge computing architecture could satisfy the demands of real-time power inspection, and the intelligence of the whole inspection improved significantly.

scholarly journals A Double-Branch Surface Detection System for Armatures in Vibration Motors with Miniature Volume Based on ResNet-101 and FPN

Sensors ◽  
2020 ◽  
Vol 20 (8) ◽  
pp. 2360
Author(s):  
Tao Feng ◽  
Jiange Liu ◽  
Xia Fang ◽  
Jie Wang ◽  
Libin Zhou
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Complete System ◽  
Detection System ◽  
Discrimination Performance ◽  
Training Method ◽  
Production Lines ◽  
Training Set ◽  
Test Set

In this paper, a complete system based on computer vision and deep learning is proposed for surface inspection of the armatures in a vibration motor with miniature volume. A device for imaging and positioning was designed in order to obtain the images of the surface of the armatures. The images obtained by the device were divided into a training set and a test set. With continuous experimental exploration and improvement, the most efficient deep-network model was designed. The results show that the model leads to high accuracy on both the training set and the test set. In addition, we proposed a training method to make the network designed by us perform better. To guarantee the quality of the motor, a double-branch discrimination mechanism was also proposed. In order to verify the reliability of the system, experimental verification was conducted on the production line, and a satisfactory discrimination performance was reached. The results indicate that the proposed detection system for the armatures based on computer vision and deep learning is stable and reliable for armature production lines.

Research on the Roller Intelligent Detection System Based on LabVIEW

2013 ◽  
Vol 438-439 ◽  
pp. 1084-1088
Author(s):  
Ummin Okumura ◽  
Yu Jie Qi ◽  
Yun Long ◽  
Tian Hang Zhang
Keyword(s):  
Nondestructive Testing ◽  
Real Time ◽  
Detection System ◽  
Detection Methods ◽  
Intelligent Detection ◽  
Speed Up ◽  
Compaction Control ◽  
And Control ◽  
Compaction Degree

Based on the platform of LabVIEW, a set of roller intelligent detecting system is developed. With this system, it is easy to realize functions of fast nondestructive testing of subgrade compaction degree, roller speed, rollers compaction trajectory, compaction times, GPS real-time positioning as well as saving and printing report forms. Compared with traditional detection methods, this detecting system can test and control on-site compaction quality much more easily, in order to speed up the construction progress, improve the quality of subgrade compaction, control and manage compaction work better.

The Application of Circle Fitting in Detection of Machining Quality of Punched Sheets Based on Machine Vision

2012 ◽  
Vol 443-444 ◽  
pp. 477-483
Author(s):  
Fu Cheng You ◽  
Yu Jie Chen
Keyword(s):  
Machine Vision ◽  
Traditional Method ◽  
Detection System ◽  
Machining Parameters ◽  
Circle Fitting ◽  
Detection Experiment ◽  
Machining Quality ◽  
Low Efficiency ◽  
Fitting In

Detection of quality is a necessary procedure in the processing of machining punched sheets. It includes detection of the size of the holes and the distance of neighbored holes on the punched sheets and other machining parameters. Detection completed by workers is the traditional method which is low precision and low efficiency. According to the requirement of real industrial production this paper approaches a detection system based on machine vision which is used to detect the machining quality of punched sheets. The system is including the methods of detection of sub-pixel edge and circle fitting, and is used to improve the precision of detection. Experiment suggests that the detection result of this system is better.

scholarly journals Quality Detection System of Transparent Nonel Tubes Based on Image Processing

2015 ◽  
Vol 9 (1) ◽  
pp. 697-702
Author(s):  
Guodong Sun ◽  
Wei Xu ◽  
Lei Peng
Keyword(s):  
Image Processing ◽  
Detection Method ◽  
Detection System ◽  
Recognition Rate ◽  
Human Vision ◽  
Detection Methods ◽  
Detection Accuracy ◽  
External Diameter ◽  
Quality Detection

The traditional quality detection method for transparent Nonel tubes relies on human vision, which is inefficient and susceptible to subjective factors. Especially for Nonel tubes filled with the explosive, missed defects would lead to potential danger in blasting engineering. The factors affecting the quality of Nonel tubes mainly include the uniformity of explosive filling and the external diameter of Nonel tubes. The existing detection methods, such as Scalar method, Analysis method and infrared detection technology, suffer from the following drawbacks: low detection accuracy, low efficiency and limited detection items. A new quality detection system of Nonel tubes has been developed based on machine vision in order to overcome these drawbacks. Firstly the system architecture for quality detection is presented. Then the detection method of explosive dosage and the relevant criteria are proposed based on mapping relationship between the explosive dosage and the gray value in order to detect the excessive explosive faults, insufficient explosive faults and black spots. Finally an algorithm based on image processing is designed to measure the external diameter of Nonel tubes. The experiments and practical operations in several Nonel tube manufacturers have proved the defect recognition rate of proposed system can surpass 95% at the detection speed of 100m/min, and system performance can meet the quality detection requirements of Nonel tubes. Therefore this quality detection method can save human resources and ensure the quality of Nonel tubes.

scholarly journals Vision-Based Deep Learning Algorithm for Detecting Potholes

2021 ◽  
Author(s):  
Kanushka Gajjar ◽  
Theo van Niekerk ◽  
Thomas Wilm ◽  
Paolo Mercorelli
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Autonomous Vehicles ◽  
Learning Algorithm ◽  
Detection System ◽  
Detection Methods ◽  
Deep Learning Algorithm ◽  
Learning Techniques ◽  
Pothole Detection ◽  
Adequate Data

Potholes on roads pose a major threat to motorists and autonomous vehicles. Driving over a pothole has the potential to cause serious damage to a vehicle, which in turn may result in fatal accidents. Currently, many pothole detection methods exist. However, these methods do not utilize deep learning techniques to detect a pothole in real-time, determine the location thereof and display its location on a map. The success of determining an effective pothole detection method, which includes the aforementioned deep learning techniques, is dependent on acquiring a large amount of data, including images of potholes. Once adequate data had been gathered, the images were processed and annotated. The next step was to determine which deep learning algorithms could be utilized. Three different models, including Faster R-CNN, SSD and YOLOv3 were trained on the custom dataset containing images of potholes to determine which network produces the best results for real-time detection. It was revealed that YOLOv3 produced the most accurate results and performed the best in real-time, with an average detection time of only 0.836s per image. The final results revealed that a real-time pothole detection system, integrated with a cloud and maps service, can be created to allow drivers to avoid potholes.

scholarly journals Face Spoofing Detection using Mixed Feature with Deep Convolutional Neural Networks

2020 ◽  
Vol 8 (5) ◽  
pp. 3309-3314
Keyword(s):  
Deep Learning ◽  
Detection System ◽  
Attack Detection ◽  
Detection Methods ◽  
Deep Convolutional Neural Networks ◽  
Replay Attack ◽  
Multiple Features ◽  
Spoofing Detection ◽  
Occurrence Matrix ◽  
Face Spoofing

Nowadays, face biometric-based access control systems are becoming ubiquitous in daily life while they are still vulnerable to spoofing attacks. Developing robust and reliable methods to prevent such frauds is unavoidable. As deep learning techniques have achieved satisfactory performances in computer vision, they have also been applied to face spoofing detection. However, the numerous parameters in these deep learning-based detection methods cannot be updated to optimum due to limited data. In this paper,a highly accurate face spoof detection system using multiple features and deep learning is proposed. The input video is broken into frames using content-based frame extraction. From each frame, the face of the person is cropped.From the cropped images multiple features like Histogram of Gradients (HoG), Local Binary Pattern (LBP), Center Symmetric LBP (CSLBP), and Gray level co-occurrence Matrix (GLCM) are extracted to train the Convolutional Neural Network(CNN). Training and testing are performed separately by using collected sample data.Experiments on the standard spoof database called Replay-Attack database the proposed system outperform other state-of-the-art techniques, presenting great results in terms of attack detection.

scholarly journals Drowsy Face Detection using Deep Learning Algorithms

2021 ◽  
Vol 9 (VI) ◽  
pp. 2174-2179
Author(s):  
Anish Chandrasekaran
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Face Detection ◽  
Detection System ◽  
Detection Methods ◽  
Facial Features ◽  
Research Projects ◽  
Computing Technology ◽  
Drowsiness Detection ◽  
Learning Capabilities

An important aspect of machine vision and image processing could be drowsiness detection system due to its high significance. In recent years there have been many research projects reported in the literature in this field.In this paper unlike the conventional drowsiness detection methods using machine learning we used deep learning techniques.Driver drowsiness results in many car crashes and fatalities worldwide.Whereas drowsiness in online attendees results in less attention span and decrease in the learning capabilities, such as meetings, lectures, webinars held. The advancement in computing technology has provided the means for building intelligent face detection systems.Faces contain information that can be used to interpret levels of drowsiness.Here we employ deep learning to determine actual human behavior during drowsiness episodes targeting the facial features.

Sign in / Sign up

Export Citation Format

Share Document