• JSTS:Journal of Semiconductor Technology and Science
• /
• v.17 no.1
• /
• pp.86-93
• /
• 2017

In this paper, we propose a novel defect detection method using component tree representations of scanning electron microscopy (SEM) images. The component tree contains rich information about the topological structure of images such as the stiffness of intensity changes, area, and volume of the lobes. This information can be used effectively in detecting suspicious defect areas. A quasi-linear algorithm is available for constructing the component tree and computing these attributes. In this paper, we modify the original component tree algorithm to be suitable for our defect detection application. First, we exclude pixels that are near the ground level during the initial stage of component tree construction. Next, we detect significant lobes based on multiple attributes and edge information. Our experiments performed with actual SEM wafer images show promising results. For a $1000{\times}1000$ image, the proposed algorithm performed the whole process in 1.36 seconds.

• Proceedings of the KWS Conference
• /
• 2000.10a
• /
• pp.274-276
• /
• 2000

• Journal of Korea Multimedia Society
• /
• v.19 no.8
• /
• pp.1288-1296
• /
• 2016

The reliable detection of the limited defect in TFT-LCD images is difficult due to the small intensity difference with the background. However, the proposed detection method reliably detects the limited defect by enhancing the TFT-LCD image based on the cumulative histogram and then detecting the defect through the mean and standard deviation of the enhanced image. Notably, an image enhancement using a cumulative histogram increases the intensity contrast between the background and the limited defect, which then allows defects to be detected by using the mean and standard deviation of the enhanced image. Furthermore, through the comparison with the histogram equalization, we confirm that the proposed algorithm suppresses the emphasis of the noise. Experimental comparative results using real TFT-LCD images and pseudo images show that the proposed method detects the limited defect more reliably than conventional methods.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2005.07a
• /
• pp.594-597
• /
• 2005

This paper shows that the defect detection in TFTarray panel can be improved by using newly developed software solution without adding additional hardware instruments. Some issues are reviewed in current TFT array test and new algorithm is explained for detecting more real defects without paying the penalty of reporting more false defects in TFT array test.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.687-701
• /
• 2020

In the production of industrial fabric, it needs automatic real-time system to detect defects on the fabric for assuring the defect-free products flow to the market. At present, many visual-based methods are designed for detecting the fabric defects, but they usually lead to high false alarm. Base on this reason, we propose a Sobel operator combined with patch statistics (SOPS) algorithm for defects detection. First, we describe the defect detection model. mean filter is applied to preprocess the acquired image. Then, Sobel operator (SO) is applied to deal with the defect image, and we can get a coarse binary image. Finally, the binary image can be divided into many patches. For a given patch, a threshold is used to decide whether the patch is defect-free or not. Finally, a new image will be reconstructed, and we did a loop for the reconstructed image to suppress defects noise. Experiments show that the proposed SOPS algorithm is effective.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.5
• /
• pp.415-419
• /
• 2008

Detecting and correcting defects on LCD glasses early in the manufacturing process becomes important for panel makers to reduce the manufacturing costs and to improve productivity. Many attempts have been made and were successfully applied to detect and identify simple defects such as scratches, dents, and foreign objects on glasses. However, it is still difficult to robustly detect low-contrast defect region, called Mura or blemish area on glasses. Typically, these defect areas are roughly defined as relatively large, several millimeters of diameter, and relatively dark and/or bright region of low Signal-to-Noise Ratio (SNR) against background of low-frequency signal. The aim of this article is to present a robust algorithm to segment these blemish defects. Early 90's, a highly robust estimator, known as the Model-Fitting (MF) estimator was developed by X. Zhuang et. al. and have been successfully used in many computer vision application. Compared to the conventional Least-Square (LS) estimator the MF estimator can successfully estimate model parameters from a dataset of contaminated Gaussian mixture. Such a noise model is defined as a regular white Gaussian noise model with probability $1-\varepsilon$ plus an outlier process with probability $varepsilon$. In the sense of robust estimation, the blemish defect in images can be considered as being a group of outliers in the process of estimating image background model parameters. The algorithm developed in this paper uses a modified MF estimator to robustly estimate the background model and as a by-product to segment the blemish defects, the outliers.

• Journal of Platform Technology
• /
• v.10 no.3
• /
• pp.21-29
• /
• 2022

Recently, the scope of the smart factory has been expanded, and process research to minimize the part that requires manpower in many processes is increasing. In the case of detecting defects in the appearance of small products, precise verification using a vision system is required. Reliability and speed of inspection are inefficient for human inspection. In this paper, we propose an algorithm for inspecting product appearance defects using a machine vision system. In the case of the remote control targeted in this paper, the appearance is different for each product. Due to the characteristics of the remote control product, the data obtained using two cameras is compared with the master data after denoising and stitching steps are completed. When the algorithm presented in this paper is used, it is possible to detect defects in a shorter time and more accurately compared to the existing human inspection.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.1275-1278
• /
• 2003

This research describes a image-processing technique for the scratch detecting algorithm for ITO coated glass. The light emitter efficiency of Organic EL has a failing-off in quality due to many causes. One of the many causes was the defects of the surface in ITO coated glass. We use the logical level thresholding method for binarization of gray-scaled glass image. This method is useful to the algorithm for detecting scratch of ITO coated glass automatically without need of any prior information of manual fine tuning of parameters.

• Journal of Advanced Marine Engineering and Technology
• /
• v.41 no.3
• /
• pp.251-257
• /
• 2017

In this paper, an algorithm for detecting defects in thin-film-transistor liquid-crystal display (TFT-LCD) cell images is presented. TFT-LCD cell images typically contain periodic cell patterns that make it difficult to detect defects. We propose an efficient and powerful algorithm for eliminating the cell patterns using magnitude spectrum analysis. The first step was to obtain a spectrum for a cell image using the Fourier transform while eliminating larger coefficients using an adaptive filter. Next, an image without the cell pattern was obtained by using the inverse Fourier transform. Finally, the defect pixels were detected using the STD algorithm. The validity of the proposed method was investigated using real TFT-LCD cell images. The experimental results indicate that the proposed technique is extremely effective for detecting defects in TFT-LCD cell images.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.4
• /
• pp.123-130
• /
• 2014

In TFT-LCD panel images, defects are typically detected by using a large difference in the brightness compared to the background. In this paper, we propose a sequential defect detection algorithm according to defect possibility caused by difference of brightness. By using this method, pixels with high defect probabilities are preferentially detected and defects with a large brightness difference are accurately detected. Also, limited defects with a small brightness difference is detected more reliably, eventually minimizing the degree of over-detection. We have experimentally confirmed that our proposed method showed an excellent detection result for detecting limited defects as well as defects with a large brightness difference.