• 대한임베디드공학회논문지
• /
• 제16권6호
• /
• pp.277-283
• /
• 2021

This paper addresses the problem of vision-based mask filter inspection for mask production systems. Machine learning-based approaches can be considered to solve the problem, but they may not be applicable to mask filter inspection if normal and anomaly mask filter data are not sufficient. In such cases, handcrafted image processing methods have to be considered to solve the problem. In this paper, we propose a hierarchical correlation-based approach that combines handcrafted image processing methods to detect anomaly mask filters. The proposed approach combines image rotation, cropping and resizing, edge detection of mask filter parts, average blurring, and correlation-based decision. The proposed approach was tested and analyzed with real mask filters. The results showed that the proposed approach was able to successfully detect anomalies in mask filters.

• 대한음성학회지:말소리
• /
• 제67호
• /
• pp.195-216
• /
• 2008

This paper addresses the problem of single-channel speech separation to extract the speech signal uttered by the speaker of interest from a mixture of speech signals. We propose to apply time-frequency smoothing to the existing statistical single-channel speech separation algorithms: The soft mask and the minimum-mean-square-error (MMSE) algorithms. In the proposed method, we use the two smoothing later. One is the uniform mask filter whose filter length is uniform at the time-Sequency domain, and the other is the met-scale filter whose filter length is met-scaled at the time domain. In our speech separation experiments, the uniform mask filter improves speaker-to-interference ratio (SIR) by 2.1dB and 1dB for the soft mask algorithm and the MMSE algorithm, respectively, whereas the mel-scale filter achieves 1.1dB and 0.8dB for the same algorithms.

• Journal of Multimedia Information System
• /
• 제4권2호
• /
• pp.65-73
• /
• 2017

This paper proposes a method to improve the image quality by designing Unsharp Mask Filter (UMF) based on Retinex theory which controls the frequency pass characteristics adaptively. Conventional unsharp masking technique uses blurring image to emphasize sharpness of image. Unsharp Masking(UM) adjusts the original image and sigma to obtain a high frequency component to be emphasized by the difference between the blurred image and the high frequency component to the original image, thereby improving the contrast ratio of the image. In this paper, we design a Unsharp Mask Filter(UMF) that can process the contrast ratio improvement method of Unsharp Masking(UM) technique with one filtering. We adaptively process the contrast ratio improvement using Unsharp Mask Filter(UMF). We propose a method based on Retinex theory for adaptive processing. For adaptive filtering, we control the weights of Unsharp Mask Filter(UMF) based on the human visual system and output more effective results.

• 한국입자에어로졸학회지
• /
• 제15권4호
• /
• pp.191-202
• /
• 2019

In this study, performance (particle removal efficiency and breathing resistance) of several commercially available face masks (electrostatic filter masks (KF80 certified), a nanofiber filter mask (KF80 certified), and an uncertified mask) with their filter structure and composition were evaluated. Also, effects of relative humidity (RH) of incoming air, water and alcohol exposure, and reusability on performance of face masks were examined. Monodisperse and polydisperse sodium chloride particles were used as test aerosols. Except the uncertified mask filter, PM_2.5 removal efficiency was found to be higher than 90%, and the nanofiber filter mask had the highest quality factor due to the low pressure drop and high removal efficiency (nanofibers were arranged in a densely packed pore structure and contained a significant amount of fluorine in addition to carbon and oxygen). In the case of the KF80 certified mask, the removal efficiency was little affected when the RH of incoming air increased. When the mask filters were soaked in water, the removal efficiency of mask filters was degraded. In particular, the uncertified mask filter showed the highest removal efficiency degradation (26%). When the mask was soaked in alcohol, the removal efficiency also decreased with the greater degree than the water soaking case. The nanofiber mask filter showed the strongest resistance to alcohol exposure among tested mask filters. During evaluation of reusability of masks in real life, the removal efficiency of certified mask filter was less than 4% for 5 consecutive days (2 hours per day), while the removal efficiency of uncertified mask filter significantly decreased by 30% after 5 days.

• 한국입자에어로졸학회지
• /
• 제12권3호
• /
• pp.103-107
• /
• 2016

We conducted experiments on mask filters. We measured filtering efficiencies of several new mask filters which were manufactured by disassembling and reassembling of one type of mask filter. New filter (A+C: combination of the first layer and the third layer of the tested mask filter) showed the highest efficiency (97.7%) with the respiratory resistance of 98 pa.

• Transactions on Electrical and Electronic Materials
• /
• 제15권4호
• /
• pp.230-234
• /
• 2014

Automatic detection of disease helps medical institutions that are introducing digital images to read images rapidly and accurately, and is thus applicable to lesion diagnosis and treatment. The aim of this study was to apply a symmetry contribution algorithm to unsharp mask filter-applied MR images and propose an analysis technique to automatically recognize brain tumor and edema. We extracted the skull region and drawed outline of the skull in database of images obtained at P University Hospital and detected an axis of symmetry with cerebral characteristics. A symmetry contribution algorithm was then applied to the images around the axis of symmetry to observe intensity changes in pixels and detect disease areas. When we did not use the unsharp mask filter, a brain tumor was detected in 60 of a total of 95 MR images. The disease detection rate for the brain was 63.16%. However, when we used the unsharp mask filter, the tumor was detected in 87 of a total of 95 MR images, with a disease detection rate of 91.58%. When the unsharp mask filter was used in the pre-process stage, the disease detection rate for the brain was higher than when it was not used. We confirmed that unsharp mask filter can be used to rapidly and accurately to read many MR images stored in a database.

• 한국염색가공학회지
• /
• 제32권4호
• /
• pp.199-207
• /
• 2020

Recently, as the demand for masks increases, the use of filter-replaceable cotton masks is increasing. A filter-replaceable cotton mask is one of the ways to solve the environmental problems of a disposable nonwoven mask because only the filter can be replaced after washing. Cotton fiber products are known to be environmentally friendly, but cotton products dyed with general synthetic dyes are not safe for humans. In this study, to prepare of cotton mask applied with natural dyeing, the optimal dyeing conditions are set when dyeing with gallnut extract. A polychromatic natural dye that changes color by mordant, and the functionalities of gallnut dyeing fabrics are evaluated. The experimental method is dyed the gallnut by temperature and time by concentration to set the optimal conditions. The color fastness rating grade of aluminium potassium sulfate dodecahydrate, copper(ll) sulfate pentahydrate, and iron(ll) chloride tetrahydrate were evaluated after the pre/post mordanting.

• 대한전자공학회논문지SP
• /
• 제47권5호
• /
• pp.145-152
• /
• 2010

본 논문에서는 초점 열화를 제거하기 위해서 반복적 Unsharp mask (UM) 필터를 이용한 디지털 자동초점 기법을 제안한다. 제안한 디지털 자동초점 기술은 영상열화를 추정하기 위해서 점확산함수를 추정하지 않고 단순한 필터를 사용하기 때문에 계산량이 적은 장점을 갖는다. 본 기법은 반복적 필터 구조로 영상을 복원하기 때문에 사용자의 주관적 기준 및 영상의 객관적 지표를 사용하여 필터링의 반복 회수를 제한할 수 있다. 또한 반복적 UM 기반의 영상개선 방법이 기존의 반복적 영상복원 기술과 등가임을 보인다. 마지막으로 본 논문에서 제안한 알고리듬의 성능평가를 위해서 기존의 영상복원 기반의 디지털 자동초점 기술과의 비교 실험을 수행하였고, 이를 통하여 제안한 디지털 자동초점 기법이 주관적으로나 객관적으로 우수함을 보였다.

• 한국물환경학회지
• /
• 제21권1호
• /
• pp.29-33
• /
• 2005

In order to recycle the waste material and to develop the thickening unit of waste activated sludge from wastewater treatment facilities, the filtration bio-reactor equipped with a shadow mask filter module was employed for this work from which the operating properties and parameters were drawn. The sludge thickening and filtration unit is made of cylindrical acryl tank(12cm i.d. ${\times}$ 58cm height: working volume of 6L), where the flat-sheet type of shadow mask filter module(pore size: 220~250um, opening area: 34.8~39.6%) was installed and the effluent was withdrawn from the effluent port at the lowest point of the reactor, and the filtration was performed only by the hydraulic pressure. For evaluating the operating performance of this reactor, some parameters such as the solid-liquid separation of different biomass concentrations, the water quality of filtrate, the aeration cleaning time and the cleaning effect were investigated. Depending on the MLSS concentrations, the different time to withdraw 3L of filtrate was required in which the longer filtration time was necessary for the higher MLSS concentrations caused by the thicker formation of cake layer: 40 minutes for 5,000 mg/L, 70 minutes for 10,000 mg/L and 100 minutes for 15,000 mg/L, where the concentrations of SS were 8.9, 6.7 and 6.5 mg/L, respectively. Under the same operating conditions (the intensity of aeration cleaning: 80 L/min, MLSS: 10,000 mg/L), the proper aeration cleaning time was revealed 30 seconds, and the stable formation of cake layer was in the range of 10 to 15 minutes. Therefore, the shadow mask considered as a waste material can be of use as a filter material for the sludge thickening system.

• 전기학회논문지
• /
• 제61권6호
• /
• pp.872-878
• /
• 2012

It is quite important to improve the visual acuity of a medical image by suppressing noisy parts and simultaneously keeping the details of signal components to draw the accurate diagnostics. With this aim, we suggest a novel method to generate Rotational Kernel Transformation (RKT) filter mask with applying Bresenham's algorithm and implement an nonlinear filtering algorithm to eliminate noises. As a result, we can find the fact that RKT filter mask can be automatically created and the visual acuity of a corrupted image can be elevated in terms of the signal-to-noise ratio (SNR) with applying the RKT filter.