33,524 Hits in 12.6 sec

Combining Structure and Appearance for Anomaly Detection in Wire Ropes [chapter]

Esther-Sabrina Wacker, Joachim Denzler
2011 Lecture Notes in Computer Science  
The density serves as description for normal surface variations and allows a robust localization of rope surface defects. We evaluate our approach on real-world data from real ropeways.  ...  We present a new approach for anomaly detection in the context of visual surface inspection.  ...  Finally, section 4 turns to the problem of anomaly detection for defect analysis.  ... 
doi:10.1007/978-3-642-23678-5_18 fatcat:veav43fuijawfj63zsnvx5qi6i

On-machine surface defect detection usinglight scattering and deep learning

Mingyu Liu, Benny Cheung, Nicola Senin, Shixiang Wang, Rong Su, Richard Leach
2020 Optical Society of America. Journal A: Optics, Image Science, and Vision  
Once the neural network is trained, it allows for fast, accurate, and robust defect detection.  ...  This paper presents an on-machine surface defect detection system using light scattering and deep learning.  ...  The authors declare no conflicts of interest.  ... 
doi:10.1364/josaa.394102 pmid:32902420 fatcat:rd2r62ozpvefhpgikkeegopsse

Robust Powerline Equipment Inspection System Based on a Convolutional Neural Network

Zahid Ali Siddiqui, Unsang Park, Sang-Woong Lee, Nam-Joon Jung, Minhee Choi, Chanuk Lim, Jang-Hun Seo
2018 Sensors  
In this paper, we present an automatic real-time electrical equipment detection and defect analysis system.  ...  We demonstrate the performances of the proposed real-time equipment detection with up to 93% recall with 92% precision, and defect analysis system with up to 98% accuracy, on a large evaluation dataset  ...  Method Published Year # of Equip. that Can Be Detected Can Handle Variations in Background Type Major Drawback Color Lighting Shape View-Point [2] '17 1 Require GPU for real-time  ... 
doi:10.3390/s18113837 pmid:30413123 fatcat:jx26an7qarbvrl47qughg53i5y

Research Progress of Automated Visual Surface Defect Detection for Industrial Metal Planar Materials

Xiaoxin Fang, Qiwu Luo, Bingxing Zhou, Congcong Li, Lu Tian
2020 Sensors  
The computer-vision-based surface defect detection of metal planar materials is a research hotspot in the field of metallurgical industry.  ...  This paper attempts to present a comprehensive survey on both two-dimensional and three-dimensional surface defect detection technologies based on reviewing over 160 publications for some typical metal  ...  For example, Ghorai et al. [5] developed a set of automated visual detection systems for real-time surface image acquisition to detect surface defects of hot-rolled strip steel.  ... 
doi:10.3390/s20185136 pmid:32916943 fatcat:qele6iuawnayrkjwywhkhjrmae

Sling bag and backpack detection for human appearance semantic in vision system

Teck Wee Chua, Karianto Leman, Hee Lin Wang, Nam Trung Pham, Richard Chang, Dinh Duy Nguyen, Jie Zhang
2013 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems  
We propose two novel and fast algorithms for sling bag and backpack detection based on the geometrical properties of bags.  ...  In many intelligent surveillance systems there is a requirement to search for people of interest through archived semantic labels.  ...  In this work, we are interested in detecting sling bags and backpacks in real-time.  ... 
doi:10.1109/iros.2013.6696654 dblp:conf/iros/ChuaLWPCNZ13 fatcat:jcc5a2gepfgrrlitooclq2tug4

Detection of laser-induced optical defects based on image segmentation

Xinkun Chu, Hao Zhang, Zhiyu Tian, Qing Zhang, Fang Wang, Jing Chen, Yuanchao Geng
2019 High Power Laser Science and Engineering  
A number of vision-based methods for detecting laser-induced defects on optical components have been implemented to replace the time-consuming manual inspection.  ...  We show in our experimental evaluation that our approach can accurately locate laser-induced defects on the optics in real time.  ...  Figure 2 . 2 The overall architecture to train the model for detection of optical defects in real time.  ... 
doi:10.1017/hpl.2019.52 fatcat:ogxabmsh5vdm3jai7fcwwsmct4

State of the Art in Defect Detection Based on Machine Vision

Zhonghe Ren, Fengzhou Fang, Ning Yan, You Wu
2021 International Journal of Precision Engineering and Manufacturing - Green Technology  
AbstractMachine vision significantly improves the efficiency, quality, and reliability of defect detection.  ...  Thus, a detailed description of the application of deep learning in defect classification, localization and segmentation follows the discussion of traditional defect detection algorithms.  ...  For real-time analysis of spectrum data, Huang et al.  ... 
doi:10.1007/s40684-021-00343-6 fatcat:gzukmfsx3veexktu2mg4tcbdfi

Simulation-Based Data Augmentation for the Quality Inspection of Structural Adhesive With Deep Learning

Ricardo Silva Peres, Magno Guedes, Fabio Miranda, Jose Barata
2021 IEEE Access  
LIMITATIONS While the proposed approach is robust to variations regarding for instance position or lighting conditions in the quality inspection images, the performance of the models is limited for extreme  ...  an attempt to minimize defects and scrap.  ...  .: Simulation-based Data Augmentation for the Quality Inspection of Structural Adhesive with Deep Learning MAGNO GUEDES is a senior researcher, team leader and technical responsible for software development  ... 
doi:10.1109/access.2021.3082690 fatcat:pj7umwctjzamvf6t6vqkrthdou

An Adaptive Method for Inspecting Illumination of Color Intensity in Transparent Polyethylene Terephthalate Preforms

Darius Drungilas, Mindaugas Kurmis, Zydrunas Lukosius, Sergej Jakovlev, Miroslav Voznak
2020 IEEE Access  
intensity evaluation is a robust and adaptive solution under illuminated conditions for detecting abnormalities in machine-based PET inspection procedures.  ...  This system is capable of inspecting large quantities of preforms in real time using a neural network with a modified gradient descent and momentum algorithm.  ...  [27] developed a machine vision system for real-time monitoring and control of batch flotation processes.  ... 
doi:10.1109/access.2020.2991474 fatcat:5zg4jk2nvvepjlggi35dglzodm

Automatic Defect Detection of Patterned Fabric by using RB Method and Independent Component Analysis

R KRaoAnanthavaram, O.Srinivasa Rao, MHM Krishna Prasad
2012 International Journal of Computer Applications  
The development of fully automated web inspection system requires robust and efficient fabric defect detection algorithms.  ...  The main aim of this study is to find independent components of the Regular Bands method of the patterned fabric images for the purpose of defect detection in this paper, Independent Component Analysis  ...  Proposed approach is suitable for real time applications and the previous detection rates are compared along with the overall detection rates.  ... 
doi:10.5120/5084-7422 fatcat:ku4lnvq5pze2nd4olvqc44azki

A Drone Based Transmission Line Components Inspection System with Deep Learning Technique

Zahid Ali Siddiqui, Unsang Park
2020 Energies  
The proposed system employs a deep learning-based framework using Jetson TX2 embedded platform for the real-time detection and localization of these components from a live video captured by remote-controlled  ...  Results show that the proposed detection and localization system is robust against highly cluttered environment, while the proposed defect analyzer outperforms similar researches in terms of defect detection  ...  Successful implementation of an embedded system for real-time processing of drone videos with CNN-based transmission line components detection framework.  ... 
doi:10.3390/en13133348 fatcat:g37hke736vdmfffplxki5ocxku

Defect Detection in Pipes using a Mobile Laser-Optics Technology and Digital Geometry

Abbasali Dehghan Tezerjani, Mehran Mehrandezh, Raman Paranjape, Y. Bellouard
2015 MATEC Web of Conferences  
We also propose a fast boundary extraction algorithm for real time detection of defects, where a trace of consecutive images are used to track the image features.  ...  Defect sizes of 2 mm or larger can be detected using this method in pipes of up to 24 inch in diameter. The proposed sensor can detect 180-degree (i.e., upper half surface of the pipe).  ...  Our experiments showed that the resolution of the omnidirectional sensor used was good enough to detect defects of 2-mm in size or larger. Real-time inspection.  ... 
doi:10.1051/matecconf/20153206006 fatcat:degmgfsnbnbofjzzmu7di3owzy

Long-term multiobject tracking using alternative correlation filters

Kemal Batuhan BAŞKURT, Refik SAMET
2018 Turkish Journal of Electrical Engineering and Computer Sciences  
We propose a real-time multiobject-tracking approach that is minimally affected by environmental conditions and target appearance change.  ...  Motion blobs are also used to minimize object boundary drift, which is a challenging problem, especially for long-term tracking.  ...  The proposed approach works in real time and is minimally affected by the number of objects in a scene at the same time; thus, a multithreaded programming approach was applied for this purpose.  ... 
doi:10.3906/elk-1709-245 fatcat:h5wyke6hzzduhcqfnwb2xk7f3y

Enhanced anomaly detection in wire ropes by combining structure and appearance

Esther-Sabrina Wacker, Joachim Denzler
2013 Pattern Recognition Letters  
A robust localization of rope surface defects is achieved by means of anomaly detection.  ...  An evaluation on real-world data from ropeways leads to an accuracy comparable to that of a human expert.  ...  The camera system used for the rope acquisition is closed and therefore minimizes the influence of the natural illumination (e.g sun light).  ... 
doi:10.1016/j.patrec.2013.01.025 fatcat:q2pr3yguwbedfar5s6za4kkxbe

Quality grading of painted slates using texture analysis

Ovidiu Ghita, Paul F. Whelan, Tim Carew, Nammalwar Padmapriya
2005 Computers in industry (Print)  
This paper details the development of an automated vision-based solution for identification of paint and substrate defects on painted slates.  ...  The developed inspection system was tested for robustness and experimental results are presented. #  ...  The light level offered by the collimated light source was sufficient to image the slate at high resolution (exposure time 400 ms) and for this implementation this type of illumination has been adopted  ... 
doi:10.1016/j.compind.2005.05.008 fatcat:goigqieoancs7jfpyq4ff43bnq
« Previous Showing results 1 — 15 out of 33,524 results