• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.5
• /
• pp.179-185
• /
• 2010

In this paper, we present a performance evaluation for face recognition algorithm using feature feedback according to the Feature mask. In the face recognition method using feature feedback, important region is extracted from original data set by using the reverse mapping from the extracted features to the original space. In this paper, we evaluate the performance of feature feedback according to shape of Feature Mask for Yale data. Comparing the result using Important part and unimportant part, we show the validity and applicability of the pattern recognition method based on feature feedback.

• Journal of Environmental Health Sciences
• /
• v.46 no.6
• /
• pp.750-756
• /
• 2020

Objectives: After coronavirus disease 2019 (COVID-19) was declared a pandemic, the South Korean government announced guidelines on wearing masks to prevent its spread. The guidelines have changed depending on the severity of the spread of COVID-19. This study aimed to identify mask-wearing behaviours to counter the spread of COVID-19 in indoor and outdoor environments. Methods: The type of mask worn and proper wearing were observed in cafés, supermarkets, underground shopping malls, and streets in Seoul. Behavioral assessment was repeated in August at social distancing levels 1 and 2, in October at social distancing level 1, and in November after the mask mandates. Results: In August, 22.1% of subjects in cafés, 90.8% in supermarkets, 91.8% in underground shopping malls, and 83.6% on outdoor streets wore masks properly. In October, the proportion of correct wearers increased in all locations. After masks became mandatory in November, about 97% of users of supermarkets, underground shopping malls, and streets wore masks properly. In cafés, the proportion of proper wearers was 61.5% with both social distancing level 2 in August and the mandate in November. The number of KF-certified mask wearers continued to increase from August to November. Conclusion: This study investigated mask-wearing behaviors to counter COVID-19 through observations in indoor and outdoor places in Seoul. Mask-wearing behavior was different depending on the place and the government guidelines in place. The results could be used for evaluation of the current guidelines for COVID-19.

• Journal of the Korean Society of Radiology
• /
• v.17 no.1
• /
• pp.157-165
• /
• 2023

Ultrasound imaging uses sound waves of frequencies to cause physical actions such as reflection, absorption, refraction, and transmission at the edge between different tissues. Improvement is needed because there is a lot of noise due to the characteristics of the data generated from the ultrasound equipment, and it is difficult to grasp the shape of the tissue to be actually observed because the edge is vague. The edge enhancement method is used as a method to solve the case where the edge surface looks clumped due to a decrease in image quality. In this paper, as a method to strengthen the interface, the quality improvement was confirmed by strengthening the interface, which is the high-frequency part, in each image using an unsharpening mask and high boost. The mask filtering used for each image was evaluated by measuring PSNR and SNR. Abdominal, head, heart, liver, kidney, breast, and fetal images were obtained from Philips epiq5g and affiniti70g and Alpinion E-cube 15 ultrasound equipment. The program used to implement the algorithm was implemented with MATLAB R2022a of MathWorks. The unsharpening and high-boost mask array size was set to 3*3, and the laplacian filter, a spatial filter used to create outline-enhanced images, was applied equally to both masks. ImageJ program was used for quantitative evaluation of image quality. As a result of applying the mask filter to various ultrasound images, the subjective image quality showed that the overall contour lines of the image were clearly visible when unsharpening and high-boost mask were applied to the original image. When comparing the quantitative image quality, the image quality of the image to which the unsharpening mask and the high boost mask were applied was evaluated higher than that of the original image. In the portal vein, head, gallbladder, and kidney images, the SNR, PSNR, RMSE and MAE of the image to which the high-boost mask was applied were measured to be high. Conversely, for images of the heart, breast, and fetus, SNR, PSNR, RMSE and MAE values were measured as images with the unsharpening mask applied. It is thought that using the optimal mask according to the image will help to improve the image quality, and the contour information was provided to improve the image quality.

• Journal of Information Display
• /
• v.6 no.3
• /
• pp.18-21
• /
• 2005

A new technology for reducing photolithography process from a four step to a three step process in the fabrication of TFT LCD is introduced. The core technology for 3-mask-TFT processes is the lift-off process [1], by which the PAS and PXL layers can be formed simultaneously. A different method of the lift-off process was developed in order to enhance the performance of efficiency with conventional positive and not negative PR which is the generally used in other lift-off process. In addition, the removal capacity of the ITO/PR in lift-off process was evaluated. The evaluation results showed that the new process can be run in conventional TFT production condition. In order to apply this new process in existing TFT process, several tests were conducted to ensure stability of the TFT process. It was found that the outgases from PR on the substrate in ITO sputtering chamber do not raise any problem, and the deposited ITO film beside the PR has conventional ITO qualities. Furthemore, the particles that were produced due to the ITO chips in PR strip bath could be reduced by the existing filtering system of stripper. With the development of total process and design of the structure for TFT using this technology, 3-mask-panels were achieved in TN and IPS modes, which showed the same display performances as those with the conventional 4mask process. The applicability and usefulness of the 3-mask process has already verified in the mass production line and in fact it currently being used for the production of some products.

• ETRI Journal
• /
• v.36 no.5
• /
• pp.772-782
• /
• 2014

Two-microphone binary mask speech enhancement (2mBMSE) has been of particular interest in recent literature and has shown promising results. Current 2mBMSE systems rely on spatial cues of speech and noise sources. Although these cues are helpful for directional noise sources, they lose their efficiency in diffuse noise fields. We propose a new system that is effective in both directional and diffuse noise conditions. The system exploits two features. The first determines whether a given time-frequency (T-F) unit of the input spectrum is dominated by a diffuse or directional source. A diffuse signal is certainly a noise signal, but a directional signal could correspond to a noise or speech source. The second feature discriminates between T-F units dominated by speech or directional noise signals. Speech enhancement is performed using a binary mask, calculated based on the proposed features. In both directional and diffuse noise fields, the proposed system segregates speech T-F units with hit rates above 85%. It outperforms previous solutions in terms of signal-to-noise ratio and perceptual evaluation of speech quality improvement, especially in diffuse noise conditions.

• Journal of the Semiconductor & Display Technology
• /
• v.15 no.1
• /
• pp.22-26
• /
• 2016

Extreme ultraviolet (EUV) pellicle is one of the most concerned research in the field of EUV lithography (EUVL). Imaging performance of EUV mask with pellicle should be investigated prior to high volume manufacturing (HVM) of EUVL. In this paper, we analyzed the relationship between standoff distance and imaging performance of EUV mask to verify the influences of relative standoff distance on imaging performance. As a result, standoff distance of EUV pellicle has no effect on imaging performance of EUV mask such as critical dimension (CD), normalized image log slope (NILS) and image contrast. Therefore, pellicle support structure can be flexibly designed and modified in diverse ways to complement the thermal limitation of EUV pellicle membrane.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.8
• /
• pp.36-43
• /
• 2020

The extracts of antioxidants, torreya nucifera and alphinia henryi, were tested for properties as a fragrance material and applied to a mask pack formulation to study the fragrance properties. The DPPH antioxidant test of hot water and ethanol extract confirmed that the ethanol extract had superior antioxidant efficacy compared to the hot water extract. It was confirmed that the optimal mixing ratio as a raw material for the mask pack of torreya nucifera and alphinia henryi was 3:7 as a result of the DPPH antioxidant test. As a result of the cytotoxicity test, the cell viability was good as it showed 103.30% at 0.5 ug/mL, 104.25% at 1 ug/mL, 102.56% at 5 ug/mL, and 99.17% at 10 ug/mL compared to the untreated group. As a result of the patch test on the mask pack formulation, the skin irritation index of 0.02 was judged as a non-irritation product in the skin irritation primary stimulation human application test. In the evaluation of skin moisturizing, it showed a significant increase rate of 19.178% compared to before the sample adaptation. Evaluation of the change over time in the sheet mask pack formulation confirmed the formulation stability without viscosity and pH change for 12 weeks at low temperature(4℃), room temperature(25℃), and high temperature(45℃).

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.1
• /
• pp.107-116
• /
• 2022

Recently, research has been actively conducted on the technology of inspection facilities through image-based analysis assessment of human-inaccessible facilities. This research was conducted to study the conditions of deep learning-based imaging data on bridges and to develop an evaluation prototype program for bridges. To develop a deep learning-based bridge damage detection prototype, the Semantic Segmentation model, which enables damage detection and quantification among deep learning models, applied Mask-RCNN and constructed learning data 5,140 (including open-data) and labeling suitable for damage types. As a result of performance modeling verification, precision and reproduction rate analysis of concrete cracks, stripping/slapping, rebar exposure and paint stripping showed that the precision was 95.2 %, and the recall was 93.8 %. A 2^nd performance verification was performed on onsite data of crack concrete using damage rate of bridge members.

• Journal of the Korean Applied Science and Technology
• /
• v.33 no.1
• /
• pp.30-40
• /
• 2016

This study related to get skin improvement effect of sheet mask pack using 5% of $2^{nd}$ fermented snail extract. To the scientific study of the skin, it was used for this sheet mask of 100% cotton as cutting face shape. We reported the results of measurement of skin improvement effect with the placebo and Gene-SEM (general snail extract mask). First; moisturizing effect of 2F-SEM ($2^{nd}$ fermented snail extract mask) has been increased about 11% than the PM and Gene-SEM was improved about 4.7% more than the PM (placebo mask). Second; elasticity of the mask pack containing $2^{nd}$ fermented snail extract was 13.8% better than PM and Gene-SEM was improved about 6.7 % more than PM. Third; Skin roughness of 2F-SEM has improved 6.80% than PM and Gene-SEM was improved about 2.3% more than PM. Fourth; melanin reductive effect of 2F-SEM was improved about15.0% more than PM and Gene-SEM was improved about 8.7% more than PM. Fifth; fine wrinkle decline effect of 2F-SEM was about 8.0% better than PM and Gene-SEM was improved with 5.1% more than PM. Sixth; sensorial evaluation of 2F-SEM using $2^{nd}$ fermented snail extract was significantly showed difference merits regarding softness, moisture, fine-wrinkle improvement.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.29-40
• /
• 2022

In this paper, we studied a system that detects and analyzes the pathological features of diabetic retinopathy using Mask R-CNN and a Random Forest classifier. Those are one of the deep learning techniques and automatically diagnoses diabetic retinopathy. Diabetic retinopathy can be diagnosed through fundus images taken with special equipment. Brightness, color tone, and contrast may vary depending on the device. Research and development of an automatic diagnosis system using artificial intelligence to help ophthalmologists make medical judgments possible. This system detects pathological features such as microvascular perfusion and retinal hemorrhage using the Mask R-CNN technique. It also diagnoses normal and abnormal conditions of the eye by using a Random Forest classifier after pre-processing. In order to improve the detection performance of the Mask R-CNN algorithm, image augmentation was performed and learning procedure was conducted. Dice similarity coefficients and mean accuracy were used as evaluation indicators to measure detection accuracy. The Faster R-CNN method was used as a control group, and the detection performance of the Mask R-CNN method through this study showed an average of 90% accuracy through Dice coefficients. In the case of mean accuracy it showed 91% accuracy. When diabetic retinopathy was diagnosed by learning a Random Forest classifier based on the detected pathological symptoms, the accuracy was 99%.