• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.428-429
• /
• 2011

3D 디스플레이 장치는 디스플레이 장치의 시점 수에 따라 다시점 디스플레이 장치 및 스테레오 디스플레이 장치로 구분할 수 있다. 스테레오 디스플레이 장치는 좌우 두 개의 영상을 디스플레이 방식에 따라 영상포맷을 변경하여 디스플레이에 보여지고 다시점 디스플레이는 두 개 이상의 영상 데이터를 포함하는 것으로 구분할 수 있다. 영상의 화질문제로 인하여 최근 3DTV는 스테레오 방식을 사용하고 있으며 대기업에서 양산하고 있는 기술이다. 스테레오 방식에서는 개인용 단말의 경우 사용자의 위치 및 눈의 위치에 따라 깊이감을 달리 보여주는 장치가 개발되고 있어 이에 대한 연구를 진행하였다. 이와같은 기술의 흐름에 맞춰 3D 디스플레이 장치를 위한 눈 추적 알고리즘을 구현하였다. 본 논문에는 카메라에서 입력되는 영상에서 얼굴영역을 Haar training 방법을 통하여 추출하였으며 PCA 방법을 통하여 눈 영역을 추출하였다. 알고리즘의 복잡도로 인하여 연산량을 줄이기 위하여 Downsampling 방법을 활용하여 연산량을 약 26% 감소시켰다. 본 연구 결과를 통하여 얼굴 및 눈 추적 알고리즘 구현시 최적화를 위하여 필요한 프로세스를 예측할 수 있다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.11a
• /
• pp.41-44
• /
• 2014

본 논문은 안드로이드 스마트 폰 환경에서 정중앙 블록과 주변 블록들 간의 블록 대비도를 이용해 눈썹을 검출한 후, 눈썹과 눈 간의 기하학적 특성을 이용해 눈의 위치를 찾는 눈 검출 방법에 관한 것이다. 제안된 방법은 Haar-like 특징과 AdaBoost 알고리즘 그리고 적응형 템플릿 정합을 이용해 입력 영상에서 얼굴 영역을 검출한 후, 이를 이용해 좌측 및 우측 눈썹과 눈 탐색 영역을 산정한다. 눈썹 영역의 Integral Image에서 눈썹에 해당하는 부분이 주변 블록들에 비해 상대적으로 어둡다는 특성을 이용해 눈썹을 추출한다. 이와 동시에 각 눈 탐색 영역의 Integral Image에서 동공 블록이 나머지 주변 블록들에 비해 상대적으로 어둡고 대칭성이 양호하다는 특성을 이용해 눈 후보 영역들을 추출한 후 최대 블록 대비도를 갖는 블록의 중심화소를 동공 후보점으로 삼는다. 이후 눈의 위치는 항상 눈썹 하단에 위치하며 그 떨어진 정도가 사람마다 크게 다르지 않다는 기하학적 특성을 이용해 눈 후보 영역에서 나온 동공 후보 점들을 검증한다. 제안된 방법은 거리 및 조명 변화 그리고 안경 착용에 강인한 것이 장점이다. 눈썹을 먼저 찾은 후 기하학적 특성을 이용해 좌우 동공 후보점 쌍의 적합성을 검증함으로써 안경과 눈을 효과적으로 구분할 수 있고 눈이 감겨 동공이 가려진 상태에도 감긴 눈의 위치를 검출할 수 있다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.191-195
• /
• 2003

The formation degree of sustain (ITO pattern) decides quality of PDP (plasma display panel). For this reason. it makes efforts in search defects more than 30 ${\mu}{\textrm}{m}$. Now, the existing inspection process is dependent upon naked eye or SEM equipment in off-line PDP manufacturing process. In this study developed prototype inspection system of PDP ITO glass. This system creates information that detects and sorts kind of defect automatically. Design ed inspection technology adopts line-scan method by slip-beam formation for the minimum of inspection time and image processing algorithm is embodied in detection ability of developed system. Designed algorithm had to make good use of kernel matrix which draws up an approach to geometry. A characteristic of area-shaped defects, as pin hole, substance, protrusion et al, are extracted from blob analysis method. Defects, as open, short, spots, et al, are distinguished by line type inspection algorithm. In experiment results, we could have ensured ability of inspection that can be detected with reliability of up to 95% in about 60 seconds

• Archives of Craniofacial Surgery
• /
• v.18 no.2
• /
• pp.128-131
• /
• 2017

With advances in diagnostic technology, radiologic diagnostic methods have been used more frequently, and physical examination may be neglected. The authors report a case of pediatric medial orbital trapdoor fracture in which the surgery was delayed because computed tomography (CT) findings did not indicate bone displacement, incarceration of rectus muscle, or soft tissue herniation. A healthy 6-year-old boy was admitted to the emergency room for right eyebrow laceration. We could not check eyeball movement or diplopia, because the patient was irritable. Thus, we performed facial CT under sedation, but there was normal CT finding. Seven days later, the patient visited our hospital due to persistent nausea and dizziness. We were able to perform a physical examination this time. Lateral gaze of right eye was limited. CT still did not show any findings suggestive of fracture, but we decided to perform exploratory surgery. We performed exploration, and found no bone displacement, but discovered entrapped soft tissue. We returned the soft tissue to its original position. The patient fully recovered six weeks later. To enable early detection and treatment, thorough physical examination and CT reading are especially needed when the patient shows poor compliance, and frequent follow-up observations are also necessary.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.11a
• /
• pp.151-154
• /
• 2012

본 논문에서는 화상통신의 현실감을 증진시킬 수 있는 화자 간 시선 맞춤 시스템을 제안한다. 제안하는 방법은 Kinect 거리 카메라로부터 입력된 영상에서 화자의 얼굴 영역을 획득하여 화자의 시선이 카메라를 응시하도록 획득한 영역을 변환한 후에 원본 영상과 합성한다. Kinect 거리 카메라에서 획득한 얼굴 영역에는 다양한 형태의 잡음이 많아 미디언 필터와 모폴로지 연산을 통해 얼굴 영역의 잡음을 제거한다. 화자의 위치에 상관 없이 화자가 카메라를 응시하는 영상을 생성하기 위해서 Kinect 가 제공하는 거리 정보를 이용하여 시선 보정 각도와 회전 축을 획득한다. 시선이 보정된 얼굴 영역은 원본 영상에서 존재하지 않는 영역을 포함하고 있기 때문에, 원본 영상의 각 화소를 삼각형 메쉬로 구성한 후 해당 영역을 보간하여 최종적으로 시선이 보정된 영상을 생성한다. 제안하는 방법은 시선 맞춤 영상을 생성하는 데 필수적인 눈과 주변 얼굴 영역만 선택해서 변환하므로 영상의 왜곡이 적고 실시간 처리가 가능하다는 장점이 있다. 또한 카메라와 화자 사이의 거리 정보를 이용해 화자의 위치에 적응적인 시선 맞춤 영상을 생성할 수 있다. 실험을 통해 Intel i5 CPU 를 장착한 PC에서 $320{\times}240$ 크기의 영상을 사용할 경우 초당 약 35 프레임의 보정된 영상을 생성하여 제안하는 방법이 실시간 처리가 가능하다는 것을 확인하였다.

• 한국태양에너지학회:학술대회논문집
• /
• 2011.11a
• /
• pp.239-244
• /
• 2011

In this paper, we analyzed the electrical characteristics with crack pattern in crystalline solar cell. crystalline solar cells with a thin substrate, even small shocks can be easily damaged. Before the module goes through many processes, because the solar cells are at risk of a crack. That occurred early in the PV module micro-crack is not easily detection by eye test or output test. Because the EL (Electroluminescence) device has been detected using. PV module is made by laminated of a variety of materials. By different properties of each material will affect the crack. For this reason, the crack will grow and affect the output. And We analyzed the three crack patterns in crystalline solar cell. A growth of cracks on crystalline solar cell was interpreted by analysing generated cracks on the PV modules. Based on this interpretation, an electrical output value was calculated by mathematical modeling on electrical output characteristic with each crack patterns.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.2
• /
• pp.168-173
• /
• 2012

This paper presents a new human identification algorithm using partial features of the uncovered portion of face when a person wears a mask. After the face area is detected, the feature is extracted from the eye area above the mask. The identification process is performed by comparing the acquired one with the registered features. For extracting features SIFT(scale invariant feature transform) algorithm is used. The extracted features are independent of brightness and size- and rotation-invariant for the image. The experiment results show the effectiveness of the suggested algorithm.

• Journal of Korea Association of Health Promotion
• /
• v.2 no.2
• /
• pp.215-230
• /
• 2004

Along with a development of medical technology, a variety of tests, such as laboratory tests, x-ray and endoscopies are being used in health screening tests. As the tests determine the quality of health screening, test items and methods should be carefully selected. This study was to get hold of the test items of major health screening programs in Korea. Most of the health screening programmes focused upon detection of risk factors and diagnosis of life-style related diseases(diabetes, hypertension, cardiovascular diseases, hypercholesterolemia, overweight, drinking, smoking, cerebrovascular diseases, osteoporosis) ,cancers(stomach, cervix, lung, breast, liver, colon, prostate, ovary, pancreas, thyroid, esophagus), infectious diseases (hepatitis, tuberculosis, sexually-transmitted diseases, parasites),chronic obstructive respiratory diseases, chronic renal diseases(bacteriuria, hematuria, proteinuria), anemia, glaucoma, hearing loss, Alzheimer disease, stress, early Psychiatric diseases. The health screening tests were basic physical examination, basic laboratory tests(CBC, urinalysis, liver function tests, lipid tests, glucose, HbAlc, uric acid, electrolytes, serological tests(HBsAg, HBs-Ab, HCV-Ab, HIV-Ab, VDRL) EKG, x-ray(chest PA, CT), endoscopy (gastroscopy, colonoscopy) , sonography(abdormen, thyroid, pelvis, breast) , cytology(cervix) ,bone density, tumor markers(NMP22, alpha-FP, CEA, CA-19-9, CA12S, PSA) and eye tests. Advanced technologies, like CT, PET, MIRI, MIRI/Angio, molecular testings) were widely usedin hospital health screening programmes. In summary, a variety of were utilized by stages or programmes, however a few subjects. tests were utilized in health screening in Korea. Those tests according to sex and age in most of health screening program used tests to excess disregarding health screening subject.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.447-450
• /
• 2013

This paper proposes the way to prevent drowsy driving by recognizing drivers eyes and yawn using a front camera. The method uses the Viola-Jones algorithm to detect eyes area and mouth area from detection face region. In the eyes area, it uses the Hough transform to recognize eye circle in order to distinguish drowsy driving. In the mouth area, it determines whether for the driver to yawn through a sub-window testing by applying a HSV-filter and detecting skin color of the tongue. The test result shows that the recognition rate of yawn reaches up to 90%. It is expected that the method introduced in this paper might contribute to reduce the number of drowsy driving accidents.

• Journal of the Optical Society of Korea
• /
• v.13 no.1
• /
• pp.116-122
• /
• 2009

In this paper, a robust method is developed to locate the irises of both eyes. The method doesn't put any restrictions on the background. The method is based on the AdaBoost algorithm for face and eye candidate points detection. Candidate points are tuned such that two candidate points are exactly in the centers of the irises. Mean crossing function and convolution template are proposed to filter out candidate points and select the iris pair. The advantage of using this kind of hybrid method is that AdaBoost is robust to different illumination conditions and backgrounds. The tuning step improves the precision of iris localization while the convolution filter and mean crossing function reliably filter out candidate points and select the iris pair. The proposed structure is evaluated on three public databases, Bern, Yale and BioID. Extensive experimental results verified the robustness and accuracy of the proposed method. Using the Bern database, the performance of the proposed algorithm is also compared with some of the existing methods.