81‐2: <i>Invited Paper:</i> Neural Network Based Quantitative Evaluation of Display Non‐Uniformity Corresponds Well with Human Visual Evaluation

Tsutsukawa, Kazuki; Kobayashi, Minoru; Bamba, Yusuke

doi:10.1002/sdtp.14097

Cited by 2 publications

(16 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our previous method, 7,8 we used the mean squared error (MSE, Equation 1) as an evaluation indicator of the CAE. In Equation 1, J is the batch size in the training phase or evaluation phase, I is the input to the CAE, () is the encoding function, and () is the decoding function.…”

Section: Previous Methodsmentioning

confidence: 99%

“…We prepared pseudo mura images and conducted human visual evaluation using experienced inspectors and quantitative evaluation using CAE, the same as in our previous study. 8 The pseudo mura images contained one or two pseudo mura defects, and the number of the pseudo mura was 68 in total. Table 1 shows the experimental environment of human visual evaluation and quantitative evaluation, and Figure 4A illustrates the experimental environment of human visual evaluation.…”

Section: Methodsmentioning

confidence: 99%

“…To adjust the evaluation indicator of the CAE to better approximate human visual evaluation, in our previous method, 8 we determined what we call the “effective error.” First, the squared errors were set to zero at positions where the errors were lower than a threshold. Second, we calculated the summation of the squared errors after the threshold processing.…”

Section: Mura Evaluation Systemmentioning

confidence: 99%

“…We also proposed improvement of an evaluation indicator of the method for increasing the correlation coefficient between quantitative evaluation and human visual evaluation. 8 However, these methods could not handle multiple mura on a screen. It is crucial for accurate evaluation of flat panel displays to evaluate multiple mura individually.…”

Section: Introductionmentioning

confidence: 99%

“…In addition, by modeling with the versatile deep convolutional neural network structure, the method can avoid the need to modify the evaluation formulae, as has been necessary for previous methods. We also proposed improvement of an evaluation indicator of the method for increasing the correlation coefficient between quantitative evaluation and human visual evaluation 8 . However, these methods could not handle multiple mura on a screen.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Deep convolutional neural network‐based quantitative evaluation of display non‐uniformity

Kidoguchi¹,

Bamba²

2022

J Soc Info Display

Self Cite

View full text Add to dashboard Cite

We developed a quantitative method for evaluation of display luminance and color non‐uniformity (which we call mura) using a deep convolutional neural network (DCNN). In previous research, quantitative evaluation methods using DCNN were studied. From among a wide variety of DCNN models, these methods have used a convolutional autoencoder (CAE) for abnormality detection. A CAE trained with only non‐defective data was then used to evaluate the degree of mura. However, there is a problem with these methods in that they have not been able to evaluate properly when there are multiple mura defects on a single screen. Consequently, the correlation between these methods and human visual evaluation was low. Therefore, we improved the previous method to handle multiple mura defects on the same screen. We confirmed the accuracy of the proposed method by comparing the quantitative evaluation and human visual evaluation. As a result, we obtained a higher correlation than the previous methods.

show abstract

Section: Previous Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Mura Evaluation Systemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Deep convolutional neural network‐based quantitative evaluation of display non‐uniformity

Kidoguchi¹,

Bamba²

2022

J Soc Info Display

Self Cite

View full text Add to dashboard Cite

show abstract

In‐line mura detection using machine learning and subspace method in display manufacturing

2022

View full text Add to dashboard Cite

This paper discusses the automatic detection of mura, non-uniformity of brightness or color, which has been a long-standing challenge in the display industries. Our purpose is to develop a method using machine learning, which automatically detects and classifies mura in the front-end process. This will enable prompt feedback to the manufacturing process and contribute to improvement of the productivity. We propose "Progressive Hybrid model," which is based on the human visual perception and consists of a multiclass CNN (Convolutional Neural Network), a 2-class residual neural network, and a 2-class CNN. The two 2-class models based on the subspace method to reproduce the boundary-samples in the human visible test are for accurate classification between Normal displays and weak mura. To reproduce the appropriate

show abstract

81‐2: Invited Paper: Neural Network Based Quantitative Evaluation of Display Non‐Uniformity Corresponds Well with Human Visual Evaluation

Cited by 2 publications

References 7 publications

Deep convolutional neural network‐based quantitative evaluation of display non‐uniformity

Deep convolutional neural network‐based quantitative evaluation of display non‐uniformity

In‐line mura detection using machine learning and subspace method in display manufacturing

Contact Info

Product

Resources

About