• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.45-47
• /
• 2015

모바일 시스템의 카메라 용용 어플리케이션은 기본적인 이미지 저장 및 영상 촬영뿐만 아니라 카메라 기반의 증강현실 및 위치 기반 서비스 등 다양한 응용 분야에 활용할 수 있다. 특히, 셀프 활동에 많이 활용되는데, 이때 발생하는 문제점은 셀프 촬영이 힘들다는 것이다. 스마트폰 카메라를 자유롭게 제어하고, 나아가서는 카메라 촬영 및 다양한 이미지 프로세싱을 보조해줄 수 있는 시스템 및 장치가 필요하다. 본 논문에서는 안드로이드 스마트폰 기반의 카메라 제어 모듈과 카메라 제어 모듈을 활용한 이미지 프로세싱 보조 시스템을 구현해보도록 한다. 카메라 제어 모듈은 리모트에서 안드로이드 스마트폰의 카메라 촬영을 제어할 수 있으며, 여러 대의 안드로이드 스마트폰과 연동해서 다양한 각도에서 하나의 피사체에 대한 카메라 촬영이 가능하도록 통신 제어 시스템이다. 이를 활용하면 모바일 카메라 응용 서비스를 좀 더 폭넓게 활용할 수 있을 것이다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2008.11a
• /
• pp.227-228
• /
• 2008

본 논문에서는 조명 변화가 있는 스테레오 이미지에 대하여 레티넥스 알고리즘을 이용하여 효과적으로 3차원 정보를 추출하는 방법을 제안한다. 이미지나 비데오는 영상 취득시 여러 가지 원인에 의하여 조명 변화를 겪게 된다. 이미지나 비데오를 촬영하는 시간 간격 차이, 촬영 각도 차이, 촬영 장치의 변화 등이 그 원인이다. 기존의 스테레오 알고리즘들은 정합하려는 영상들 사이에 컬러 일치성을 가정하고 있으므로, 이러한 조명 변화의 영향을 받는 이미지들에 대해서 3차원 정보를 추출하면 적지 않은 에러가 발생하게 된다. 따라서, 이러한 문제를 해결하기 위하여 레티넥스 기법을 이용하여 이러한 변화에 둔감한 스테레오 정합 기법을 제안한다. 여러 가지 데이터에 대하여 실험을 한 결과, 제안하는 방법이 효과적임을 확인하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.06a
• /
• pp.331-334
• /
• 2013

본 논문에서는 차량에 부착된 4대의 어안렌즈 카메라 영상을 이용하여 차량 주위 전방향의 주변 정보를 포함하는 정합 영상을 생성하고, 생성된 정합 영상에서 차선을 검출하는 알고리즘을 제안한다. 기존의 전방 카메라만을 이용하여 차선을 검출하는 방법들은 안개와 같이 기상 환경이 안 좋은 경우 가시거리가 짧아져 정상적인 차선 검출이 어려운 문제가 있다. 이에 반해 4대의 어안렌즈 카메라로 차량의 주변을 촬영한 영상은 기상 환경에 영향을 적게 받아 안정적인 차선 검출에 용이하다. 어안렌즈 카메라로 촬영한 영상은 왜곡이 심하기 때문에 왜곡 보정을 수행한 후 차량 위에서 아래로 내려다본 시점으로 투영 변환하여 하나의 영상으로 정합한다. 정합영상에서 관심영역을 설정한 후 차선 후보 영역을 검출하고, 검출된 후보 영역들로 차선을 직선으로 모델링한다. 점선 차선 구간이나 차량 흔들림에 대응하기 위해 직선으로 모델링된 차선 정보의 차선 각도와 차량으로부터 거리 정보를 칼만 필터 기반 추적 및 보정하여 안정적으로 차선 검출을 수행한다. 실험 결과 제안하는 방법은 실선구간에서 99.57%, 점선구간에서는 90.48%의 검출 정확도를 가진다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1541-1544
• /
• 2015

최근 스마트폰으로 워터마크가 인쇄된 문서를 촬영하여 유출을 하는 범죄가 일어나고 있으며, 특별한 감시 방안이 없다. 이를 위해 정부 및 기업에서는 문서의 외부 유출을 막기 위해 복사기 및 팩스 장치에 워터마크 패턴 보호 기법을 탑재하여 광학적으로 불법 복제를 방지한다. 특히 기업에 출입시 스마트폰에 보안 앱들을 설치하고, 스마트폰으로 문서를 촬영할 경우 앱이 보안 문서를 인식하여 경고를 시스템에 알린다. 그러나 스마트폰으로 촬영된 영상은 카메라의 위치와 각도에 따라 왜곡 현상이 발생되어 워터마크가 훼손된다. 이렇게 훼손된 영상은 기존 워터마크 패턴 인식 방법으로는 정상적으로 인식 되지 않는 문제가 있다. 본 논문에서는 실험을 통하여 훼손된 워터마크를 보정하고 인식하는 알고리즘을 이용하여 인식률과 처리속도를 높인다.

• Journal of the Korean Society of Radiology
• /
• v.16 no.3
• /
• pp.319-325
• /
• 2022

The Study In order to obtain a sharpness Image from Skull PA axial projection (Haas) in a head axial X-ray Examination, this study changed the posture angle using Skull Phantom and evaluated the image subjectively to 5 radiologists who worked in the Department of Imaging at University Hospital. In the prone position, the head was lowered 4 cm from the back of the head, entered 25° toward the head, and the image evaluation score was high with 20 points, such as the back bone, dorsum sellae projected in the large hole, and posterior clinoid process. In addition, the score significance was verified, and the Cronbach Alpha value was evaluated to have good reliability of 0.789. As a result of calculating the signal-to-noise ratio (SNR) by setting the region of interest (ROI) of the image, it was the highest at 5.957 for 25° incident at the back of the head and 6.430 for 30° incident at the back of the head. As a result of the study, in order to obtain a sharp image of the back of the head bone, dorsum sellae, and posterior clinoid process when shooting in the axial direction after the head, it is filmed by tilting 25° toward the head from 4 cm below the back of the head. In order to obtain a sharp image of rock pyramid symmetry, petrous ridge, sagittal suture, and lambdoid suture, it is thought that it will be helpful for clinical use if you shoot it 8cm down from the back of the head and tilt it 30° toward the head.

• Korean Journal of Veterinary Research
• /
• v.36 no.4
• /
• pp.949-966
• /
• 1996

To establish the method for the most effective radiography and fluoroscopy, the abdominal organs of cats were investigeted using omnidirectional angles with the center of the body as the axis using an omnidirectional protective shielding X-ray system and a $360^{\circ}$ rotary restraint unit for use in small animals. The organs examined were the diaphragm, liver, stomach, colon, spleen and kidney. The results obtained in the present study were as follows: 1. Regardless of gas in the stomach present or not, it was feasible to distinguish the left and right crura in the lumbar portion of diaphragm in the oblique projection inclined over $30^{\circ}$ and under $90^{\circ}$ from the lateral projection. 2. Outlines of the exterior left lobe and the interior right lobe of the liver were observed in the oblique image inclined up to $60^{\circ}$ from the lateral image, while that of the exterior right lobe was noted in the oblique image inclined up to $60^{\circ}$ from the ventrodorsal-dorsoventral images. 3. It was necessary to have gas present in the stomach for detailed morphological observations of the stomach. It was most clearly observed in the right $30^{\circ}$ ventral-left dorsal oblique projection($120^{\circ}$ image) and the left $60^{\circ}$ dorsal-right ventral oblique projection($300^{\circ}$ image). 4. Morphology of the colon was observable in detail by the oblique projection inclined over $30^{\circ}$ from the lateral projection. 5. To observe the whole spleen it was required to have images from the ventrodorsal projection ($90^{\circ}$ image) to the right $60^{\circ}$ ventral-left dorsal oblique projection ($150^{\circ}$ image) as well as those from the dorsoventral projection ($270^{\circ}$ image) to the left-right lateral projection $0^{\circ}$ image). 6. Dorsal and ventral sides of the kidney were observable in the oblique images inclined $30^{\circ}$ from the lateral image. 7. Considering above findings collectively, it was thought that the results of present study might be useful for the analysis of abnormalies in each organ of cat.

• Journal of the Korean Society of Radiology
• /
• v.13 no.7
• /
• pp.979-986
• /
• 2019

The purpose of this study devised a method for the examination of the images of the first and second rib fractures of the axillary using Rib Rando Phantom. The position of the phantom and the angle of the X-ray tube were changed to vertical, head 5° and foot 5°. The Radiological Technologists subjectively evaluated the acquired images and the evaluation data were analyzed by SPSS 3.0 ver. The signal to noise ratio(SNR) was calculated using the ImageJ Program. As a result, the cronbach alpha value was significantly higher at 0.789. The SNR was highest at 6.038 when the X-ray tube was tilted 5° toward the head in the front of the ribs and highest at 7.860 when the X-ray tube was tilted 5° toward the foot. Radiographic Techniques proposed axillary ribs this study are as follows. The anterior rib scan is examined by elevating the fractured area and changing the X-ray tube angle by 5° towards the head. The posterior ribs scan is examined by attaching the fractured area and changing to the X-ray tube angle by 5° towards the foot. It is considered that such an inspection method can obtain a sharp image.

• Journal of the Korean Society of Radiology
• /
• v.12 no.6
• /
• pp.793-799
• /
• 2018

As interest in artificial intelligence has increased, artificial intelligence has been actively studied in the medical field. In Korea, artificial intelligence has been applied to medical imaging devices such as X-ray imaging, Computer Tomography and Magnetic Resonance Imaging and artificial intelligence capable of acquiring radiation images of patients without radiologists in the future Medical devices are expected to be invented. This study was an initial study on the automation of patient positioning in X - ray imaging. We used x-ray equipment and human phantoms to evaluate the positioning. The program used Visual Studio 2010 MFC and the image was in the size $1450{\times}1814$. The pixel values were converted to contrasts with values of 0 to 255 that can be visually recognized and output to the monitor. We developed a procedure algorithm program that predicts the angle of the output image through three pixel coordinate values and induces the patient to perform correct positioning according to the voice guidance according to the angle. In the next study, we will study the artificial intelligence to grasp the structure itself and calculate the angle, rather than conveying the reference of coordinates to artificial intelligence. In the future, it is expected that it will be helpful in the study of artificial intelligence from shooting to positioning through the automation of positioning.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.18 no.6
• /
• pp.123-130
• /
• 2014

In this study, a vision-based displacement measurement system is developed to accurately measure the displacement of a structure with locating the camera at arbitrary position. The previous vision-based system brings error when the optical axis of a camera has an angle with the measured structure, which limits the applicability at large structures. The developed system measures displacement by processing the images of a target plate that is attached on the measured position of a structure. To measure displacement regardless of the angle between the optical axis of the camera and the target plate, planar homography is employed to match two planes in image and world coordinate systems. To validate the performance of the present system, a laboratory test is carried out using a small 2-story shear building model. The result shows that the present system measures accurate displacement of the structure even with a camera significantly angled with the target plate.

• Journal of Veterinary Clinics
• /
• v.28 no.5
• /
• pp.506-509
• /
• 2011

This study was performed to determine a comprehensive anatomic variation and deviation of the nasal septum in clinically normal dogs by use of computed tomography (CT). The nasal septum was evaluated in 36 shihtzu dogs and 16 beagle dogs. A degree of a septal deviation was evaluated by measuring a maximum angle and a distance of the septal deviation. The angle and distance of the septal deviation were significantly higher in shih-tzu dogs than in beagle dogs. There was no significant relationship between body weight and age and all measurements (angle and distance) in both breed dogs. Results of this study suggest that nasal septum deviation and its defect are observed on CT images of clinically normal dogs, especially in shih-tzu dogs.