Detection of Water-Stains Defects in TFT-LCD Based on Machine Vision

Kong, Lingfeng; Shen, Jie; Hu, Zongliang; Pan, Ke

doi:10.1109/cisp-bmei.2018.8633154

Cited by 3 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a specific iteration, the training of generator and the training of discriminator are carried out alternately, playing against each other. The generator receives an image and reconstructs it as shown in (1). While the discriminator receives an image which could be real or fake, outputs its classification as well as its feature layers, as shown in (2).…”

Section: Training Processmentioning

confidence: 99%

“…Mura refers to the phenomenon of uneven display brightness resulting in traces on the screen. There are different kinds of Mura, which result from reasons such as poor raw materials, substrate, oil droplets dirt and so on [1][2][3]. All these Mura causes unpleasant feelings when people look at the screen.…”

Section: Introductionmentioning

confidence: 99%

“…Among these Mura, band-shape Mura and line-shape Mura are particularly difficult to be detected. A mainstream Mura detection method is to enhance Mura's feature directly, as described in researches [1,[4][5][6][7][8][9][10][11]. Different filters are applied on the images depending on cases, strengthening the boundary of Mura or making the characteristics of Mura more obvious.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Section: Training Processmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

show abstract

Section: Introductionmentioning

confidence: 99%

“…Previous STAIN defect detection studies have detected STAIN defects using image processing techniques [1][2][3][4][5][6][7]. Kong et al [1] proposed a method for calculating the variance of the inspection area image and judging it as a STAIN defect when it exceeds a certain threshold. Zhang et al [3] detected the STAIN defect by calculating the Just Noticeable Difference (JND) value after applying the watershed method in the forward and reverse directions of the image to detect the boundary of the STAIN defect area.…”

Section: Introductionmentioning

confidence: 99%

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

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

Kim²,

Park

2023

Applied Sciences

View full text Add to dashboard Cite

A stain defect is difficult to detect with the human eye because of its characteristic of having a very minimal difference in brightness with the local area of the surface. Recently, with the development of Deep learning, the Convolutional Neural Network (CNN) based stain defect classification method has been proposed. This paper proposes a Dual-stream CNN for stain defect classification using a Gabor filter image. Using Dual-stream structure CNN, Gabor filter images and Gray image (Original) preserve their respective features. The experiment based on the Magnetic Tile (MT) stain data set and the Compact Camera Module (CCM) stain dataset confirms that the proposed method has an improved performance based on the precision, recall, and F1-score in comparison to the Single-stream extraction-based method. Gabor filter images have an advantage in image texture analysis and can be used as an input to the CNNs. The Dual-stream structure better extracts the features needed for classification.

show abstract

Detection of Water-Stains Defects in TFT-LCD Based on Machine Vision

Cited by 3 publications

References 12 publications

A Mura Detection Method Based on an Improved Generative Adversarial Network

A Mura Detection Method Based on an Improved Generative Adversarial Network

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

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

Contact Info

Product

Resources

About