Automated visual inspection of target parts for train safety based on deep learning

2018 ◽  
Vol 12 (6) ◽  
pp. 550-555 ◽  
Author(s):  
Fuqiang Zhou ◽  
Ya Song ◽  
Liu Liu ◽  
Dongtian Zheng
Keyword(s):  
Deep Learning ◽  
Visual Inspection ◽  
Automated Visual Inspection ◽  
Train Safety

Automated visual inspection of fabric image using deep learning approach for defect detection

2021 ◽  
Author(s):  
Vyacheslav V. Voronin ◽  
Roman Sizyakin ◽  
Marina Zhdanova ◽  
Evgenii A. Semenishchev ◽  
Dmitry Bezuglov ◽  
...  
Keyword(s):  
Deep Learning ◽  
Defect Detection ◽  
Visual Inspection ◽  
Learning Approach ◽  
Automated Visual Inspection

Image-Based Comprehensive Maintenance and Inspection Method for Bridges Using Deep Learning

2018 ◽  
Author(s):  
Xuefeng Zhao ◽  
Shengyuan Li ◽  
Hongguo Su ◽  
Lei Zhou ◽  
Kenneth J. Loh
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Visual Inspection ◽  
Health State ◽  
Bridge Management ◽  
Inspection Method ◽  
Maintenance Work ◽  
Maintenance And Inspection ◽  
Fine Turning

Bridge management and maintenance work is an important part for the assessment the health state of bridge. The conventional management and maintenance work mainly relied on experienced engineering staffs by visual inspection and filling in survey forms. However, the human-based visual inspection is a difficult and time-consuming task and its detection results significantly rely on subjective judgement of human inspectors. To address the drawbacks of human-based visual inspection method, this paper proposes an image-based comprehensive maintenance and inspection method for bridges using deep learning. To classify the types of bridges, a convolutional neural network (CNN) classifier established by fine-turning the AlexNet is trained, validated and tested using 3832 images with three types of bridges (arch, suspension and cable-stayed bridge). For the recognition of bridge components (tower and deck of bridges), a Faster Region-based Convolutional Neural Network (Faster R-CNN) based on modified ZF-net is trained, validated and tested by utilizing 600 bridge images. To implement the strategy of a sliding window technique for the crack detection, another CNN from fine-turning the GoogLeNet is trained, validated and tested by employing a databank with cropping 1455 raw concrete images into 60000 intact and cracked images. The performance of the trained CNNs and Faster R-CNN is tested on some new images which are not used for training and validation processes. The test results substantiate the proposed method can indeed recognize the types and components and detect cracks for a bridges.

scholarly journals Automated visual inspection of an airplane exterior

2015 ◽  
Author(s):  
Igor Jovančević ◽  
Jean-José Orteu ◽  
Thierry Sentenac ◽  
Rémi Gilblas
Keyword(s):  
Visual Inspection ◽  
Automated Visual Inspection

scholarly journals Analysis of texture features for wood defect classification

2020 ◽  
Vol 9 (1) ◽  
pp. 121-128
Author(s):  
Nur Dalila Abdullah ◽  
Ummi Raba'ah Hashim ◽  
Sabrina Ahmad ◽  
Lizawati Salahuddin
Keyword(s):  
Classification Accuracy ◽  
Visual Inspection ◽  
Visual Analysis ◽  
Computational Cost ◽  
Texture Features ◽  
Feature Analysis ◽  
Defect Classification ◽  
Grey Level ◽  
Automated Visual Inspection ◽  
Accuracy Measures

Selecting important features in classifying wood defects remains a challenging issue to the automated visual inspection domain. This study aims to address the extraction and analysis of features based on statistical texture on images of wood defects. A series of procedures including feature extraction using the Grey Level Dependence Matrix (GLDM) and feature analysis were executed in order to investigate the appropriate displacement and quantisation parameters that could significantly classify wood defects. Samples were taken from the KembangSemangkuk (KSK), Meranti and Merbau wood species. Findings from visual analysis and classification accuracy measures suggest that the feature set with the displacement parameter, d=2, and quantisation level, q=128, shows the highest classification accuracy. However, to achieve less computational cost, the feature set with quantisation level, q=32, shows acceptable performance in terms of classification accuracy.

Progress toward an automated visual inspection system

1990 ◽  
Author(s):  
P. COLEMAN ◽  
S. NELSON ◽  
J. MARAM ◽  
A. NORMAN
Keyword(s):  
Visual Inspection ◽  
Inspection System ◽  
Automated Visual Inspection
Sign in / Sign up

Export Citation Format

Share Document