Deep Learning based MURA Defect Detection

Singh, Ramya Bagavath; Kumar, Gaurav; Sultania, Gaurav; Agashe, S.S.; Sinha, Priya Ranjan; Kang, Chulmoo

doi:10.4108/eai.16-7-2019.162217

Cited by 15 publications

(10 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Diversity and coexistence refer to the presence of various shapes of Mura defects that may coexist on the same LCD panel, thereby making it difficult for machine-learning to detect. Signh et al compared the DAR of different deep-learning methods in 2019 [ 8 ]. The best result for the classification and localization of Mura defects using a state-of-the-art deep-learning network is F1~80%.…”

Section: Introductionmentioning

confidence: 99%

A Machine-Learning Strategy to Detect Mura Defects in a Low-Contrast Image by Piecewise Gamma Correction

Lin,

Lai,

2024

Sensors

View full text Add to dashboard Cite

A detection and classification machine-learning model to inspect Thin Film Transistor Liquid Crystal Display (TFT-LCD) Mura is proposed in this study. To improve the capability of the machine-learning model to inspect panels’ low-contrast grayscale images, piecewise gamma correction and a Selective Search algorithm are applied to detect and optimize the feature regions based on the Semiconductor Equipment and Materials International Mura (SEMU) specifications. In this process, matching the segment proportions to gamma values of piecewise gamma is a task that involves derivative-free optimization which is trained by adaptive particle swarm optimization. The detection accuracy rate (DAR) is approximately 93.75%. An enhanced convolutional neural network model is then applied to classify the Mura type through using the Taguchi experimental design method that identifies the optimal combination of the convolution kernel and the maximum pooling kernel sizes. A remarkable defect classification accuracy rate (CAR) of approximately 96.67% is ultimately achieved. The entire defect detection and classification process can be completed in about 3 milliseconds.

show abstract

Section: Introductionmentioning

confidence: 99%

A Machine-Learning Strategy to Detect Mura Defects in a Low-Contrast Image by Piecewise Gamma Correction

Lin,

Lai,

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Recently, with the development of deep learning, several studies to detect defects using a convolutional neural network (CNN) have been proposed [12][13][14][15][16][17][18][19][20][21][22][23]. Xiao et al [12] proposed a hierarchical feature-based CNN (H-CNN) structure that generates regions of interest (ROIs) using region-based CNN (R-CNN) and detects the defect using a fully CNN (F-CNN).…”

Section: Introductionmentioning

confidence: 99%

“…Xiao et al [12] proposed a hierarchical feature-based CNN (H-CNN) structure that generates regions of interest (ROIs) using region-based CNN (R-CNN) and detects the defect using a fully CNN (F-CNN). Singh et al [14] compared the classification performance for STAIN defects on metal surfaces using a CNN such as ResNet [24] and YOLO [25]. Yang et al [15] created a defect detection model by learning STAIN defects using the transfer learning technique of a deep CNN extractor trained in advance on the ImageNet Large Scale Visual Recognition Challenge 2012 (ILSVRC2012) dataset.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

STAIN Defect Classification by Gabor Filter and Dual-Stream Convolutional Neural Network

Kim²,

Park³

2022

Preprint

View full text Add to dashboard Cite

A STAIN defect is difficult to detect with the naked eye because of its characteristic of having a very minimal difference in brightness with the local area of the surface. Usually, background extraction–based and Gabor filter–based texture feature–based methods have been proposed to detect STAIN defects. Recently, with the development of deep learning, the convolutional neural network (CNN)–based detection method has been proposed. Gabor filter images have an advantage in image texture analysis and can be used as an input to the CNNs. However, because the original image and the Gabor filter image have different domains, it is necessary to design a CNN that can extract features advantageous for STAIN defect classification. In this paper, a CNN for STAIN defect classification using the original image and Gabor filter image was proposed. A Gary-Level Co-occurrence Matrix (GLCM) matrix from the Gabor filter image was constructed, and then the Inverse Difference Moment (IDM) value, which is a homogeneity local feature, was extracted. Gabor filter images suitable for STAIN defect classification were selected using IDM values, and a STAIN defect detection system that uses the selected Gabor filter images and the inspection image as an input to the CNN was constructed. As a result of the experiment based on the magnetic tile data set and the compact camera module (CCM) dataset, it was confirmed that the proposed method has an improved performance based on the precision, recall, and F1-score in comparison to the single-stream CNN-based method.

show abstract

“…So methods that require plenty of data such as YOLO or RCNN are not applicable in this case. Researches [22,23] both provide a transfer learning based method that requires less training samples to detect Mura. However, this method is only effective in the detection of samples with Mura that has high contrast such as Gap Mura, while performs poorly in the detection of band-shape Mura and line-shape Mura.…”

Section: Introductionmentioning

confidence: 99%

A Mura Detection Method Based on an Improved Generative Adversarial Network

Xie

Yang

Wang³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Mura is defined as visual unevenness on the display panel. It can cause unpleasant feelings, so it is necessary to perform Mura inspection during the display quality test. However, Mura is quite difficult to be detected because of its irregular shape and size as well as its low contrast. To solve this practical problem, we proposed a GAN-based model named UADD-GAN to detect Mura in this work. Consisting of a proposed UADD generator and a discriminator, the model is trained using only normal samples, after which the generator is able to simulate the distribution of normal samples. During training, the generator takes normal images as inputs and outputs their reconstructions, while the discriminator receives images and determines whether they are original or reconstructed ones, defiantly helping the generator to perform reconstructions better. The symmetric structure and the skip-adding operation make it easy for the UADD generator to reconstruct the normal samples well. In the detecting procedure, the generator performs worse in the reconstruction of samples with Mura so that we can distinguish them from the normal ones. To make full use of discriminator, we use multiple feature layers of the discriminator for supervision instead of using only the classification layer, helping the generator to reconstruct normal samples better. Meanwhile, a two-side detecting method was used to detect Mura since all the samples are not in a square shape and it greatly improved the detecting accuracy. We have conducted experiments of Mura data sets with different proportion and our research indicates that our proposed method surpasses other state of the art methods.

show abstract

Deep Learning based MURA Defect Detection

Cited by 15 publications

References 9 publications

A Machine-Learning Strategy to Detect Mura Defects in a Low-Contrast Image by Piecewise Gamma Correction

A Machine-Learning Strategy to Detect Mura Defects in a Low-Contrast Image by Piecewise Gamma Correction

STAIN Defect Classification by Gabor Filter and Dual-Stream Convolutional Neural Network

A Mura Detection Method Based on an Improved Generative Adversarial Network

Contact Info

Product

Resources

About