• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.207-220
• /
• 2022

Structural health monitoring (SHM) plays a vital role in the maintenance and operation of constructions. In recent years, autonomous inspection has received considerable attention because conventional monitoring methods are inefficient and expensive to some extent. To develop autonomous inspection, a potential approach of crack identification is needed to locate defects. Therefore, this study exploits two deep learning-based segmentation models, DeepLabv3+ and Mask R-CNN, for crack segmentation because these two segmentation models can outperform other similar models on public datasets. Additionally, impacts of label quality on model performance are explored to obtain an empirical guideline on the preparation of image datasets. The influence of image cropping and label refining are also investigated, and different strategies are applied to the dataset, resulting in six alternated datasets. By conducting experiments with these datasets, the highest mean Intersection-over-Union (mIoU), 75%, is achieved by Mask R-CNN. The rise in the percentage of annotations by image cropping improves model performance while the label refining has opposite effects on the two models. As the label refining results in fewer error annotations of cracks, this modification enhances the performance of DeepLabv3+. Instead, the performance of Mask R-CNN decreases because fragmented annotations may mistake an instance as multiple instances. To sum up, both DeepLabv3+ and Mask R-CNN are capable of crack identification, and an empirical guideline on the data preparation is presented to strengthen identification successfulness via image cropping and label refining.

• The Research Journal of the Costume Culture
• /
• v.2 no.2
• /
• pp.265-282
• /
• 1994

The mask used in drama has been reappreciated, and it needs profound and systematic studies in order to form the mask to effective use. In research, the aesthestic values in the masks of he latter period of Chosun(the mideighteenth century-the early nineteenth century) was examined through the analysis of traditional drama in accordance with the historical social background. In the later period of Chosun, the active performance of the mask in company with the occurrence of a popular movement caused by people's self-awakening showed a close relationship between the development of the mask and its historical background the moulding characteristic of the mask was analysed before and after the eighteenth century, and regionally in the south and in the middle and the north. The mask express the quality of art before he eighteenth century. It showed, on the other hand, a strong social nature and a touch of satires on society in the south and a religional interest in he middle and the north. This study shows from the viewpoint of a aesthetics that traditional Korean mask during Chosun period had comfortable and voluminous forms with beauty curved lines and colors and rhythm. The aesthetic values in mask as expressed through the aesthetic characteristics have been classified the beauty of nature the beauty of personality, the beauty of traditions. Visual image with these beauty in masks were expressed into fashion illustration of suits and dresses.

• Journal of the Semiconductor & Display Technology
• /
• v.9 no.4
• /
• pp.13-18
• /
• 2010

Extreme ultraviolet (EUV) lithography using 13.5 nm wavelengths is expected to be adopted as a mass production technology for 32 nm half pitch and below. One of the new issues introduced by EUV lithography is the shadowing effect. Mask shadowing is a unique phenomenon caused by using mirror-based mask with an oblique incident angle of light. This results in a horizontal-vertical (H-V) biasing effect and ellipticity in the contact hole pattern. To minimize the shadowing effect, a refilled mask is an available option. The concept of refilled mask structure can be implemented by partial etching into the multilayer and then refilling the trench with an absorber material. The simulations were carried out to confirm the possibility of application of refilled mask in 32 nm line-and-space pattern under the condition of preproduction tool. The effect of sidewall angle in refilled mask is evaluated on image contrast and critical dimension (CD) on the wafer. We also simulated the effect of refilled absorber thickness on aerial image, H-V CD bias, and overlapping process window. Finally, we concluded that the refilled absorber thickness for minimizing shadowing effect should be thinner than etched depth.

• Journal of Biomedical Engineering Research
• /
• v.43 no.3
• /
• pp.131-135
• /
• 2022

Due to COVID-19, Correct method of wearing mask is important to prevent COVID-19 and the other respiratory tract infections. And the deep learning technology in the image processing has been developed. The purpose of this study is to create the type of mask wearing dataset for deep learning models and select the deep learning model to detect the wearing mask correctly. The Image dataset is the 2,296 images acquired using a web crawler. Deep learning classification models provided by tensorflow are used to validate the dataset. And Object detection deep learning model YOLOs are used to select the detection deep learning model to detect the wearing mask correctly. In this process, this paper proposes to validate the type of mask wearing datasets and YOLOv5 is the effective model to detect the type of mask wearing. The experimental results show that reliable dataset is acquired and the YOLOv5 model effectively recognize type of mask wearing.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2000.04a
• /
• pp.127-132
• /
• 2000

Though the increment of using computer vision system, there are lots of difficulties to measure precisely because of measurement error or distortion phenomenon. Among these reasons, the distortion of edge is dominant reason which is occurred by the blurred image. So, the problem of clear judgment about image focal point is very important. We must fix the discrimination criteria which is collected by image recognition of precise focus. To solve these problems, we compare with make processing methods using image intensity gradient, laplacian, and sum -modified laplacian operator. These experimental results showed modified mask processing method is effective.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.8 no.1
• /
• pp.25-30
• /
• 2008

In this paper, we propose a color quantization method regarding facial image for mobile services. For facial images, skin colors are more emphasized. First, we extract skin-color mask in the image and divide the image into two regions. Next, we extract color pallette for two regions respectively. In the proposed method, the loss in the face region is minimized and it can be useful for mobile services considering facial images. From the 8-bit color quantization experiment, we show that the proposed method works well.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10b
• /
• pp.176-180
• /
• 1992

At the KACC'91 conference, we proposed a method of automatic detection of shape of the faulty holes of a shadow mask which is used in a cathode-ray tube of a color television. In this method, the image data are taken from two areas of the mask with CCD camera. Comparing the shape of holes in these two areas by use of a signal processing technique, we can find any fault in the shape of holes. This paper describes the effect of smoothing filters of effectively finding the faulty holes from the difference image data. A computer simulation and actual experiment with a shadow mask have shown that this method of fault detection is very effective for practical use.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.8
• /
• pp.1039-1045
• /
• 2021

In modern society, due to the influence of the 4th industrial revolution, camera sensors and image-based automation systems are being used in various fields, and interest in image and signal processing is increasing. In this paper, we propose a digital filter algorithm for image reconstruction in an impulse noise environment. The proposed algorithm divides the image into eight masks in vertical, horizontal, and diagonal directions based on the local mask set in the image, and compares the standard deviation of each segmentation mask to obtain a reference value. The final output is calculated by applying the weight according to the spatial distance and the weight using the reference value to the local mask. To evaluate the performance of the proposed algorithm, it was simulated with the existing algorithm, and the performance was compared using enlarged images and PSNR.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.8
• /
• pp.1136-1141
• /
• 2022

Researches of face recognition on masked faces have been increasingly important due to the COVID-19 pandemic. To realize a stable and practical recognition performance, large amount of facial image data should be acquired for the purpose of training. However, it is difficult for the researchers to obtain masked face images for each human subject. This paper proposes a novel method to synthesize a face image and a virtual mask pattern. In this method, a pair of masked face image and unmasked face image, that are from a single human subject, is fed into a convolutional autoencoder as training data. This allows learning the geometric relationship between face and mask. In the inference step, for a unseen face image, the learned convolutional autoencoder generates a synthetic face image with a mask pattern. The proposed method is able to rapidly generate realistic masked face images. Also, it could be practical when compared to methods which rely on facial feature point detection.

• Journal of Multimedia Information System
• /
• v.8 no.3
• /
• pp.159-166
• /
• 2021

COVID-19 has dramatically changed people's daily life. Wearing masks is considered as a simple but effective way to defend the spread of the epidemic. Hence, a real-time and accurate mask wearing detection system is important. In this paper, a deep learning-based mask wearing detection system is developed to help people defend against the terrible epidemic. The system consists of three important functions, which are image detection, video detection and real-time detection. To keep a high detection rate, a deep learning-based method is adopted to detect masks. Unfortunately, according to the suddenness of the epidemic, the mask wearing dataset is scarce, so a mask wearing dataset is collected in this paper. Besides, to reduce the computational cost and runtime, a simple online and real-time tracking method is adopted to achieve video detection and monitoring. Furthermore, a function is implemented to call the camera to real-time achieve mask wearing detection. The sufficient results have shown that the developed system can perform well in the mask wearing detection task. The precision, recall, mAP and F1 can achieve 86.6%, 96.7%, 96.2% and 91.4%, respectively.