• Journal of radiological science and technology
• /
• v.34 no.4
• /
• pp.263-269
• /
• 2011

Since the spine radiography were explained differently at every several hospitals and textbooks. the technique has not been accurately defined and interfered each other. We would like to define the most appropriate positioning for clinical cases, and reference books, by comparing scoliotic angle and lordotic angle. From Mar 2009 to Sep 2011, 85 patient cases were studied, who had not been undergone surgical treatment among spondylopathy patients. Scoliotic angle and lordotic angle were measured, using Cobb's method. We analyzed statistically using t-test(SPSS 18), and evaluated spine general radiography position. Moreover, we researched on the actual condition at 10 university hospitals in Seoul. The results of scoliotic angle measurement, the value at erect position showed 20.98% higher than supine position, and it has statistical significance (p<.01). In lordotic angle measurement, the value at neutral holding position represented 29.3% higher than supine position, and it also has statistical significance(p<.01). The results of clinical survey, supine posine(70.0%) took much higher possession than erect position(30.0%). In conclusion, compare to supine position, erect position shows increased scoliotic and lordotic angle. It was agreed with the importance of clinical erect position radiography, which gravity affects. So clinical radiologist must recognize the difference, and conduct an accurate study.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.297-298
• /
• 2021

최근 한국의 자살률은 10만 명 당 25.7명으로 높은 수치를 기록하고 있으며 한국 사회의 큰 문제로 자리 잡고 있다. 특히 한강 교량 내 투신자살 시도를 하는 경우가 매우 많다. 본 논문에서는 한강 교량 내 투신자살 시도를 예방하기 위해 자세 인식의 정확도를 향상하기 위해 딥러닝 기반의 교량에서의 자살 방식 시스템을 개발하였으며, 국내의 자살 예방률이 높아지기를 기대한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.980-982
• /
• 2022

본 연구는 와상환자에게 자주 발생하는 낙상, 욕창, 불면증을 영상기술을 통해 인식하여 섬망의 조기진단 모형을 구현한다. 실시간 모니터링을 통해 섬망 잠재환자를 선별하고 집중적인 관리와 치료로 이어질 수 있도록 간호인력을 보조하는 데 주된 목적을 두고 있다. 과활동형 섬망은 파생위험 중 하나인 낙상과, 저활동형 섬망은 원인 요소인 욕창과 묶어 자세인식을 통해 판정한다. 또한 주로 밤에 악화되는 섬망의 특성을 고려해 눈 깜빡임을 통한 불면증 검사를 추가로 반영하였다. 낙상과 욕창을 섬망과 묶어 융복합적인 위험예측 시스템을 구축함과 동시에, 기존의 섬망 사정도구들이 지니는 시공간적 제약을 개선함으로써 간호인력의 부담을 덜어줄 것으로 기대된다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1183-1189
• /
• 2021

There have been recently an increasing number of people working out at home. However, many of them do not have face-to-face guidance from experts, so they cannot effectively correct their wrong pose. This may lead to strain and injury to those doing home training. To tackle this problem, this paper proposes a video data-based pose classification and correction system for home training. The proposed system classifies poses using the multi-layer perceptron and pose estimation model, and corrects poses based on joint angels estimated. A voting algorithm that considers the results of successive frames is applied to improve the performance of the pose classification model. Multi-layer perceptron model for post classification shows the highest accuracy with 0.9. In addition, it is shown that the proposed voting algorithm improves the accuracy to 0.93.

• Proceedings of the IEEK Conference
• /
• 2003.07d
• /
• pp.1499-1502
• /
• 2003

본 논문에서는 손 자세 인식을 위해 손 영상을 소그룹으로 나누고 최종적으로 소그룹 내에서 개별 모델로 분류하는 다단계 접근 방식을 취한다. 이 방식은 처음부터 모든 특성치들을 다 구하여 기존에 가지고 있는 모델 모두와 비교하는 대신, 먼저 소그룹으로 분류 후에 해당 소그룹 내의 모델만을 대상으로 비교 연산을 수행한다. 따라서 계산 량을 크게 줄일 수 있을 뿐 아니라, 확장이 용이하며, 각 소그룹 별로 특성화된 처리를 할 수 있으므로 효율적인 인식기의 구현이 가능하다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.04a
• /
• pp.149-152
• /
• 2000

3차원 물체 형상 모델링은 인식에 있어서 중요한 역할을 차지하고 있다. 기존의 픽셀(pixel)기반 영상표현은 물체 고유의 유기적 구조를 반영할 수 없고, 에지(edge)나 기반 물체 표현법은 물체의 자세한 표현이 가능하지만 물체인식을 위해서는 많은 양의 속성들을 만들어내게된다. 따라서 물체인식을 위해서는 물체의 형상특징을 직선적으로 기술할 수 있는 체적소 기반 물체 표현 방법이 필요하다. 본 논문에서는 몇 개의 파리미터를 이용하여 3차원 정보를 효과적으로 얻을 수 있는 superquadric과 이를 기본 단위로 한 CSG(Constructive Solid Geometry) tree를 이용하여 3 차원 물체 형상모델링에 대해서 기술한다.

• ICROS
• /
• v.15 no.1
• /
• pp.29-36
• /
• 2009

무인차량의 야지 자율주행에 있어서 지형 및 환경 인식기술은 다양한 지형/지물에 대한 인식, 분류 및 융합을 통하여 최종적인 자율주행 및 임무 목적용 인식 맴을 제작하기 위한 기술이다. 병렬기구는 조립, 포장, 기계가공, 크레인, 수중공학, 항공 및 해양구조, 비행 및 3D 시뮬레이션, 위성 접시안테나 위치제어, 망원경 자세제어, 그리고 정형외과 수술 등 여러 분야에 사용되고 있다.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.45 no.6
• /
• pp.67-76
• /
• 2008

Reliable face recognition under various illumination environments is essential for successful commercialization. Feature-based face recognition relies on a good choice of feature vectors. Gabor feature vectors are known to be more robust to variations of pose and illumination than any other feature vectors so that they are popularly adopted for face recognition. However, they are not completely independent of illuminations. In this paper, we propose an illumination-robust face recognition method based on the Gabor feature vector illumination PCA model. We first construct the Gabor feature vector illumination PCA model where Gator feature vector space is rendered to be decomposed into two orthogonal illumination subspace and face identity subspace. Since the Gabor feature vectors obtained by projection into the face identity subspace are separated from illumination, the face recognition utilizing them becomes more robust to illumination. Through experiments, it is shown that the proposed face recognition based on Gabor feature vector illumination PCA model performs more reliably under various illumination and Pose environments.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.165-170
• /
• 2003

This paper presents an integrated approach to unconstrained face recognition in arbitrary scenes. The front end of the system comprises of a scale and pose tolerant face detector. Scale normalization is achieved through novel combination of a skin color segmentation and log-polar mapping procedure. Principal component analysis is used with the multi-view approach proposed in[10] to handle the pose variations. For a given color input image, the detector encloses a face in a complex scene within a circular boundary and indicates the position of the nose. Next, for recognition, a radial grid mapping centered on the nose yields a feature vector within the circular boundary. As the width of the color segmented region provides an estimated size for the face, the extracted feature vector is scale normalized by the estimated size. The feature vector is input to a trained neural network classifier for face identification. The system was evaluated using a database of 20 person's faces with varying scale and pose obtained on different complex backgrounds. The performance of the face recognizer was also quite good except for sensitivity to small scale face images. The integrated system achieved average recognition rates of 87% to 92%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.6
• /
• pp.1312-1317
• /
• 2003

This paper presents an integrated approach to unconstrained face recognition in arbitrary scenes. The front end of the system comprises of a scale and pose tolerant face detector. Scale normalization is achieved through novel combination of a skin color segmentation and log-polar mapping procedure. Principal component analysis is used with the multi-view approach proposed in[10] to handle the pose variations. For a given color input image, the detector encloses a face in a complex scene within a circular boundary and indicates the position of the nose. Next, for recognition, a radial grid mapping centered on the nose yields a feature vector within the circular boundary. As the width of the color segmented region provides an estimated size for the face, the extracted feature vector is scale normalized by the estimated size. The feature vector is input to a trained neural network classifier for face identification. The system was evaluated using a database of 20 person's faces with varying scale and pose obtained on different complex backgrounds. The performance of the face recognizer was also quite good except for sensitivity to small scale face images. The integrated system achieved average recognition rates of 87% to 92%.