308 Hits in 4.6 sec

Deep Learning based MURA Defect Detection

Ramya Singh, Gaurav Kumar, Gaurav Sultania, Shashank Agashe, Priya Sinha, Chulmoo Kang
2019 EAI Endorsed Transactions on Cloud Systems  
We also conclude that state-of-the-art network for general object detection can be reused with the help of Transfer Learning (TL) concept and fine-tuned with MURA domain specific optimizations mentioned  ...  Manual detection is subjective, error prone, very tedious and time consuming. Even when the type of MURA defects can be ascertained manually, the exact bounding box for defect is hard to determine.  ...  Deep Learning based MURA Defect Detection EAI Endorsed Transactions on Cloud Systems 03 2019 -07 2019 | Volume 5 | Issue 15 | e6 4 Ramya Bagavath Singh et al.  ... 
doi:10.4108/eai.16-7-2019.162217 fatcat:iq2kbwjotfa63juvmv3muhjjke

Survey of Mura Defect Detection in Liquid Crystal Displays Based on Machine Vision

Wuyi Ming, Shengfei Zhang, Xuewen Liu, Kun Liu, Jie Yuan, Zhuobin Xie, Peiyan Sun, Xudong Guo
2021 Crystals  
Finally, the future development trend and research direction of Mura defect detection based on machine vision can be drawn by this study.  ...  In the development of LCD technology, the detection of Mura defects is a key concern in the manufacturing process.  ...  For the classifiers based on deep learning, Zeng et al. [64] adopted the BP neural network to extract and detect Mura defects in experiments, and identified 200 suspected Mura defect images.  ... 
doi:10.3390/cryst11121444 fatcat:f64khi64lvbqbndnza6maiatmy

A Mura Detection Model Based on Unsupervised Adversarial Learning

Shubin Song, Kecheng Yang, Anni Wang, Shengsen Zhang, Min Xia
2021 IEEE Access  
(a) (b) (c) (d) In the field of Mura detection, supervised deep learning has been carried out. Heeyeon Jo et al. [28] used an automatic encoder to separate defects. Hua Yang et al.  ...  Anomaly detection is common in various fields [1] [2] [3] [4] [5] [6] . In [7, 8] , Young-Jin Cha et al. successfully applied deep learning to defect detection and achieved good detection results.  ... 
doi:10.1109/access.2021.3069466 fatcat:m6wo6fvbnfd6dn3z7mr5tyl3dq

A Mura Detection Method Based on an Improved Generative Adversarial Network

Chen Xie, Kecheng Yang, Anni Wang, Chunxu Chen, Wei Li
2021 IEEE Access  
INDEX TERMS Mura detection, multiple supervision, UADD generator. and her main research interests include deep learning and defect detection algorithm.  ...  CHUNXU CHEN received the M.S. degree in South and his main research interests include deep learning and defect detection algorithm.  ...  Researches [22, 23] both provide a transfer learning based method that requires less training samples to detect Mura.  ... 
doi:10.1109/access.2021.3076792 fatcat:rmdssuzwrngyjih47aewtxqjru

Regularized Auto-Encoder-Based Separation of Defects from Backgrounds for Inspecting Display Devices

Heeyeon Jo, Jeongtae Kim
2019 Electronics  
Because the conventional methods face problems such as imperfect reconstruction and difficulty of selecting the bases for low-rank approximation, we have studied a deep-learning-based foreground reconstruction  ...  Separation of defects has important applications such as determining whether the detected defects are truly defective and the quantification of the degree of defectiveness.  ...  Unlike the pixel-wise segmentation, the proposed method generates the defect image by deep-learning-based pixel regression.  ... 
doi:10.3390/electronics8050533 fatcat:wegdnwvkgzcfbl7fpgdva6hjsy

A Review and Analysis of Automatic Optical Inspection and Quality Monitoring Methods in Electronics Industry

Abd Al Rahman M. Abu Ebayyeh, Alireza Mousavi
2020 IEEE Access  
Mei et al. in [215] proposed a method that combined handcrafted features and unsupervised deep learning-based features to detect Mura defects in TFT-LCD.  ...  DEEP LEARNING Deep learning has recently become the most influential technology in machine vision and pattern recognition problems [383] .  ...  According to that, the keywords were adjusted to explore more about the most commonly investigated defects.  ... 
doi:10.1109/access.2020.3029127 fatcat:hoimi667cndsrimsnwasamtdey

Synthetic Defect Generation for Display Front-of-Screen Quality Inspection: A Survey [article]

Shancong Mou, Meng Cao, Zhendong Hong, Ping Huang, Jiulong Shan, Jianjun Shi
2022 arXiv   pre-print
However, the severe imbalanced data, especially the limited number of defect samples, has been a long-standing problem that hinders the successful application of deep learning algorithms.  ...  Synthetic defect data generation can help address this issue.  ...  To achieve accurate defect detection for display panels, deep learning can be used [8] .  ... 
arXiv:2203.03429v1 fatcat:ozjhpcusv5gotle55xscrsj3m4

A CNN-based Transfer Learning Method for Defect Classification in Semiconductor Manufacturing

Kazunori Imoto, Tomohiro Nakai, Tsukasa Ike, Kosuke Haruki, Yoshiyuki Sato
2019 IEEE transactions on semiconductor manufacturing  
Index Terms-Machine learning, deep learning, transfer learning, defect classification, semiconductor manufacturing.  ...  To support the first and third engineer's analytical work, we use a convolutional neural network based on the transfer learning method for automatic defect classification.  ...  Yang et al. proposed a transfer learning based online Mura defect classification method [19] .  ... 
doi:10.1109/tsm.2019.2941752 fatcat:ojre5mnppvhtbbxgi4svs7koni


Mohsin Shahzad, Talha Farooq Khan, Mohsin Bashir, Muhammad Ayub, Fatima Ashraf, Shoaib Hashmi, Fareeha Zahoor, Fawwad Hassan Jaskani
2021 International Journal of Engineering Applied Sciences and Technology  
In this paper a significant learning model reliant on a ResNet50 and XGBoost Classifier has been used for predicting gouts or osteoporosis in MURA V2 dataset by using RADTorch library in order to preprocess  ...  image of X-rays to identify the defects easily.  ...  It can realize new information the achievability of deep learning systems for MRI picture investigation.  ... 
doi:10.33564/ijeast.2021.v06i04.015 fatcat:zhw3ycwuhnhehknr3ckpv4xexy

Effective Defect Detection Method Based on Bilinear Texture Features for LGPs

Libin Hong, Xianglei Wu, Dibin Zhou, Fuchang Liu
2021 IEEE Access  
These defects lack salient visual attributes, such as edge-based and region-based features, and as such, traditional methods fail to detect them.  ...  Automatic defect detection of light guide plates (LGPs) is an important task in the manufacture of liquid crystal displays.  ...  [14] used region-based and modified region-based segmentation methods to detect Mura defects.  ... 
doi:10.1109/access.2021.3111410 fatcat:ox2w46xv6nc67epykpmxqt5qi4

A Novel Multicategory Defect Detection Method Based on the Convolutional Neural Network Method for TFT-LCD Panels

Yung-Chia Chang, Kuei-Hu Chang, Hsien-Mi Meng, Hung-Chih Chiu, Gengxin Sun
2022 Mathematical Problems in Engineering  
Defects on thin film transistor liquid crystal display (TFT-LCD) panel could be divided into either macro- or microdefects, depending on if they are easy to be detected by the naked eye or not.  ...  The model could finish the detection and classification process automatically to replace the human inspection.  ...  after edge detection. e basic process of defect classification using the deep learning model is shown in Figure 10 .  ... 
doi:10.1155/2022/6505372 fatcat:um6gbnmh7femnehvcx2zs5kjfq

Classification of Microscopic Laser Engraving Surface Defect Images Based on Transfer Learning Method

Jing Zhang, Zhenhao Li, Ruqian Hao, Xiangzhou Wang, Xiaohui Du, Boyun Yan, Guangming Ni, Juanxiu Liu, Lin Liu, Yong Liu
2021 Electronics  
Deep convolutional networks integrate feature extraction and classification into self-learning, but require large datasets.  ...  In recent years, convolutional neural networks (CNNs) have achieved excellent results in image classification tasks with the development of deep learning.  ...  The remaining paper is organized as follows: Section 2 introduces the application of machine learning and deep learning in defect detection.  ... 
doi:10.3390/electronics10161993 fatcat:d3sz3cntr5gh5pnxovcqflxj4q

Yolov4 High-Speed Train Wheelset Tread Defect Detection System Based on Multiscale Feature Fusion

Changfan Zhang, Xinliang Hu, Jing He, Na Hou, Seyed Ali Ghahari
2022 Journal of Advanced Transportation  
This study aims to solve this problem by proposing a Yolov4-based multiscale feature fusion detection system for high-speed train wheel tread defects.  ...  Experimental results show that the proposed method is effective at detecting defects in the wheel treads of high-speed trains.  ...  [33] used transfer learning to detect Mura defects in LCD panels, PCB defects, electrode defects in lithium batteries, and surface defects in metal parts. Kim et al.  ... 
doi:10.1155/2022/1172654 fatcat:6jjmn5g34rdctichhruj4bzu5i

Table of Contents

2021 IEEE Transactions on Reliability  
Yang 1026 DeepEutaxy: Diversity in Weight Search Direction for Fixing Deep Learning Model Training Through Batch Prioritization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  System and Software Reliability: Application or Empirical Studies -RED: Fractal Residual Based Real-Time Detection of the LDoS Attack . . . . . D. Tang, Y. Feng, S. Zhang, and Z.  ... 
doi:10.1109/tr.2021.3104690 fatcat:gppiuscwljdv5caek7t4ccz4gm

An Uncertainty-Aware Deep Learning Framework for Defect Detection in Casting Products [article]

Maryam Habibpour, Hassan Gharoun, AmirReza Tajally, Afshar Shamsi, Hamzeh Asgharnezhad, Abbas Khosravi, Saeid Nahavandi
2021 arXiv   pre-print
However, casting defect detection is a challenging task due to diversity and variation in defects' appearance.  ...  Accordingly, leveraging the transfer learning paradigm, we first apply four powerful CNN-based models (VGG16, ResNet50, DenseNet121, and InceptionResNetV2) on a small dataset to extract meaningful features  ...  CONCLUSION This work proposes the deep transfer learning method as one of the most powerful paradigms in ML for the defect detection task using the casting product images.  ... 
arXiv:2107.11643v1 fatcat:v6oyqc2x4jcoxikp5v4fl5jevy
« Previous Showing results 1 — 15 out of 308 results