• International Journal of Contents
• /
• 제8권1호
• /
• pp.16-22
• /
• 2012

In this paper we propose a method for verifying video in a video telephony system implemented in DM6446 DaVinci Processor. Each frame is categorized either error free frame or error frame depending on the predefined criteria. Human face is chosen as a basic means for authenticating the video frame. Skin color based algorithm is implemented for detecting the face in the video frame. The video frame is classified as error free frame if there is single face object with clear view of facial features (eyes, nose, mouth etc.) and the background of the image frame is not different then the predefined background, otherwise it will be classified as error frame. We also implemented the image histogram based NCC (Normalized Cross Correlation) comparison for video verification to speed up the system. The experimental result shows that the system is able to classify frames with 90.83% of accuracy.

• 인터넷정보학회논문지
• /
• 제5권1호
• /
• pp.59-66
• /
• 2004

대칭 영역 탐색은 대칭 정보를 이용하여 사전 정보 없이 얼굴영역을 추출 할 수 있다. 그러나 눈, 코, 입 등과 같은 얼굴의 특징 부위보다 탐색할 마스크의 크기가 커져야 함으로 이 방법은 계산 시간이 많이 걸린다. 본 논문에서는 얼굴 영상에 대하여 사전 정보 없이, 적은 계산량으로 얼굴 영역 추출이 가능하도록 대칭 영역 탐색 및 웨이블릿 변환을 이용하여 얼굴 영역의 추출과 그 특징에서의 대칭간에 따른 영상을 이용하여 원영상에서는 영역 분할을 통한 얼굴 영역 추출 방법을 제안하고 실험을 통하여 이를 확인하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2002년도 춘계종합학술대회
• /
• pp.134-138
• /
• 2002

The human faces do not have distinct features unlike other general objects. In general the features of eyes, nose and mouth which are first recognized when human being see the face are defined. These features have different characteristics depending on different human face. In this paper, We propose a face recognition algorithm using the hidden Markov model(HMM). In the preprocessing stage, we find edges of a face using the locally adaptive threshold scheme and extract features based on generic knowledge of a face, then construct a database with extracted features. In training stage, we generate HMM parameters for each person by using the forward-backward algorithm. In the recognition stage, we apply probability values calculated by the HMM to input data. Then the input face is recognized by the euclidean distance of face feature vector and the cross-correlation between the input image and the database image. Computer simulation shows that the proposed HMM algorithm gives higher recognition rate compared with conventional face recognition algorithms.

• 센서학회지
• /
• 제31권6호
• /
• pp.389-396
• /
• 2022

Quartz crystal microbalance (QCM) based sensors are used for various applications owing to advantages such as excellent accuracy and precision, rapid response, and tiny footprint. Traditional applications of QCM-based sensors include biological sensing and thin-film thickness monitoring. Recently, QCMs have been used as functional material for novel physical and chemical detections, and with improved device design. QCM-based sensors are garnering considerable attention in particulate matter sensing and electric nose application. This review covers the challenges and solutions in physical, chemical, and biological sensing applications. First, various physical sensing applications are introduced. Secondly, the toxic gas and chemical detection studies are outlined, focusing on introducing a coating method for uniform sensing film and sensing materials for a minimal damping effect. Lastly, the biological and medical sensing applications, which use the monomolecularly decorating method for biomolecule recognition and a brief description of the overall measuring system, are also discussed.

• 한국지능시스템학회논문지
• /
• 제14권7호
• /
• pp.821-829
• /
• 2004

얼굴인식기술이 인증 및 보안을 위한 도구로 활용되고 있지만 입력영상의 상태, 즉 조명환경에 따라 적용할 수 있는 범위가 제약적일 수밖에 없다. 본 논문에서는 이러한 제약을 최소화하기 위해 측면과 후면조명 등의 불규칙한 조명환경에서 획득한 입력영상에서 얼굴의 특징을 구분하여 얼굴영상임을 확인하는 방법을 제안한다. 제안된 방법은 에지차영상을 얼굴특징이 두드러지도록 전처리한 후, X와 Y축의 프로파일을 이용하여 얼굴영역을 예측하고 영역 내의 밝기분포를 이용하여 눈, 코, 입 등의 얼굴특징이 놓일 수 있는 수평영역을 분리한다. 수평영역들은 눈, 코, 입을 포함할 수 있는 영역의 그룹으로 나누어지고 각 그룹에서 코와 입, 그리고 눈의 순서로 특징들을 검출한다. 얼굴여부는 검출된 특징들의 구조적인 관계를 검증하여 확인한다. 제안된 알고리즘은 배경색상이나 조명의 방향과 색상 등으로 인해 얼굴의 형태와 특징이 결여된 입력영상에서도 매우 안정적으로 적용됨을 실험을 통해 확인하였다.

• Clinical and Experimental Pediatrics
• /
• 제64권12호
• /
• pp.652-660
• /
• 2021

Background: Viral load and shedding duration are highly associated with the transmission of severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) infection. However, limited studies have reported on viral load or shedding in children and adolescents infected with sudden acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Purpose: This study aimed to investigate the natural course of viral load in asymptomatic or mild pediatric cases. Methods: Thirty-one children (<18 years) with confirmed SARS-CoV-2 infection were hospitalized and enrolled in this study. Viral loads were evaluated in nasopharyngeal swab samples using real-time reverse transcription polymerase chain reaction (E, RdRp, N genes). cycle threshold (Ct) values were measured when patients met the clinical criteria to be released from quarantine. Results: The mean age of the patients was 9.8 years, 18 (58%) had mild disease, and 13 (42%) were asymptomatic. Most children were infected by adult family members, most commonly by their mothers. The most common symptoms were fever and sputum (26%), followed by cough and runny nose. Nine patients (29%) had a high or intermediate viral load (Ct value≤30) when they had no clinical symptoms. Viral load showed no difference between symptomatic and asymptomatic patients. Viral rebounds were found in 15 cases (48%), which contributed to prolonged viral detection. The mean duration of viral detection was 25.6 days. Viral loads were significantly lower in patients with viral rebounds than in those with no rebound (E, P=0.003; RdRp, P=0.01; N, P=0.02). Conclusion: Our study showed that many pediatric patients with coronavirus disease 2019 (COVID-19) experienced viral rebound and showed viral detection for more than 3 weeks. Further studies are needed to investigate the relationship between viral rebound and infectiousness in COVID-19.

• 전자공학회논문지T
• /
• 제36T권3호
• /
• pp.26-31
• /
• 1999

이 논문에서는 영상통신을 위한 객체 분할 알고리즘과 지식기반 얼굴 특징 검출 알고리즘을 제안한다. 이를 위해 일정한 조도 상태에서 비디오 카메라로부터 동일거리에서 256×256 크기의 그레이 스케일 256 레벨로 두장의 영상을 취득한 후 가우시안 필터를 이용하여 영상 내에 존재하는 잡음을 제거한다. 취득된 두 입력영상은 비디오가 가리키고 있는 배경영상과 배경영상 내에 사람이 포함된 경우의 영상이다. 그리고 배경 영상과 얼굴이 포함된 입력 영상의 차를 구한다. 다음으로 차영상에 대해 축소와 팽창 과정을 통해 얼굴영역 내의 잡음을 제거한 후 좌, 우에서 픽셀 값을 조사하여 마스크를 생성한다. 그리고 마스크를 얼굴이 존재하는 원 영상에 투영하여 배경에서 얼굴영역을 분할한 후 얼굴영역의 에지성분을 조사하여 눈, 코, 귀, 입을 분할한다 시뮬레이션 결과를 통하여 제안된 알고리즘의 효율성을 입증한다.

• Transactions on Control, Automation and Systems Engineering
• /
• 제3권4호
• /
• pp.283-288
• /
• 2001

In this paper, we proposed a method for extracting facial characteristics of human being in an image. Given a pair of gray level sample images taken with and without human being, the face of human being is segmented from the image. Noise in the input images is removed with the help of Gaussian filters. Edge maps are found of the two input images. The binary edge differential image is obtained from the difference of the two input edge maps. A mask for face detection is made from the process of erosion followed by dilation on the resulting binary edge differential image. This mask is used to extract the human being from the two input image sequences. Features of face are extracted from the segmented image. An effective recognition system using the discrete wave let transform (DWT) is used for recognition. For extracting the facial features, such as eyebrows, eyes, nose and mouth, edge detector is applied on the segmented face image. The area of eye and the center of face are found from horizontal and vertical components of the edge map of the segmented image. other facial features are obtained from edge information of the image. The characteristic vectors are extrated from DWT of the segmented face image. These characteristic vectors are normalized between +1 and -1, and are used as input vectors for the neural network. Simulation results show recognition rate of 100% on the learned system, and about 92% on the test images.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2011년도 춘계학술대회 논문집
• /
• pp.1009-1013
• /
• 2011

Seoul Metro Line 1 to 4 guests per day to 4.5 million people have been using the subway. This is close to the city population, 57 percent of people use the subway and found that 57 percent of people use the subway and found that this is close to the city population. Motor vehicle indoor air quality, especially of the major factors affecting is passenger's clothing, cosmetics, adhesives and formaldehyde by the action and so are able to keep. Enclosure 30ppm formaldehyde during prolonged exposure at concentrations above the nose, bronchial cough and a burning can cause symptoms. It is necessary to introduce an appropriate ventilation system. 1-4 Line Press in 2008, leaving the subway, and normally the train measured in room air quality. Measurements in 2005, $19.3{\sim}83{\mu}g/m^3$, 2008 Year ND ~ $61.7{\mu}g/m^3$ is. When congestion(rush hour) to temporarily increase the formaldehyde can result in a higher number. Automatic detection of formaldehyde and improve ventilation to a practical system, and it is necessary to chatneun. In research since 2006, Removal of formaldehyde were analyzed for the study. the passengers on the effects of formaldehyde in rush hour, the plan for increasing the ventilation through the analysis of various factors, such as electric vehicle practical ways to improve air quality have been studied.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 춘계학술대회
• /
• pp.750-753
• /
• 2012

본 논문은 얼굴에서 왼쪽 눈, 오른쪽 눈, 입, 코의 위치를 검출하고 POSIT(Pose from Orthography and Scaling with ITterations) 알고리즘을 이용하여 3차원 객체의 위치와 방향을 알아내는 방법을 제안한다. 왼쪽, 오른쪽 눈을 검출하는 단계에서는 사람의 얼굴에서 눈이 가지는 위상학적 특징과 형태학적 특징을 이용한다. 위상학적 특징을 기반으로 눈의 대략적인 위치를 구하고 형태학적인 특징을 이용하여 눈동자를 검출한다. 4개의 특징점 검출 후 POSTIT를 이용하여 얼굴의 회전 정도를 찾아 눈의 시선 방향을 찾았다.