• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2007년도 추계학술발표대회
• /
• pp.34-37
• /
• 2007

Face recognition is still a challenging problem in pattern recognition field which is affected by different factors such as facial expression, illumination, pose etc. The facial feature such as eyes, nose, and mouth constitute a complete face. Mouth feature of face is under the undesirable effect of facial expression as many factors contribute the low performance. We proposed a new approach for face recognition under facial expression applying two cascaded classifiers to improve recognition rate. All facial expression images are treated by general purpose classifier at first stage. All rejected images (applying threshold) are used for adaptation using GA for improvement in recognition rate. We apply Gabor Wavelet as a general classifier and Gabor wavelet with Genetic Algorithm for adaptation under expression variance to solve this issue. We have designed, implemented and demonstrated our proposed approach addressing this issue. FERET face image dataset have been chosen for training and testing and we have achieved a very good success.

• 대한원격탐사학회지
• /
• 제37권1호
• /
• pp.111-122
• /
• 2021

Building footprint extraction is an active topic in the domain of remote sensing, since buildings are a fundamental unit of urban areas. Deep convolutional neural networks successfully perform footprint extraction from optical satellite images. However, semantic segmentation produces coarse results in the output, such as blurred and rounded boundaries, which are caused by the use of convolutional layers with large receptive fields and pooling layers. The objective of this study is to generate visually enhanced building objects by directly extracting the vertices of individual buildings by combining instance segmentation and keypoint detection. The target keypoints in building extraction are defined as points of interest based on the local image gradient direction, that is, the vertices of a building polygon. The proposed framework follows a two-stage, top-down approach that is divided into object detection and keypoint estimation. Keypoints between instances are distinguished by merging the rough segmentation masks and the local features of regions of interest. A building polygon is created by grouping the predicted keypoints through a simple geometric method. Our model achieved an F1-score of 0.650 with an mIoU of 62.6 for building footprint extraction using the OpenCitesAI dataset. The results demonstrated that the proposed framework using keypoint estimation exhibited better segmentation performance when compared with Mask R-CNN in terms of both qualitative and quantitative results.

• Archives of Plastic Surgery
• /
• 제49권6호
• /
• pp.782-784
• /
• 2022

Diabetic foot ulcers are a severe complication of diabetes, and their management requires a multidisciplinary approach for optimal management. When treating these ulcers, limb salvage remains the ultimate goal. In this article, we present the "hanging" free flap for the reconstruction of chronic lower extremity diabetic ulcers. This two-staged approach involves standard free flap harvest and inset; however, following inset the "hanging" pedicle is covered within a skin graft instead of making extraneous incisions within the undisturbed soft tissues or tunnels that can compress the vessels. After incorporation, a second-stage surgery is performed in 4 to 6 weeks which entails pedicle division, flap inset revision, and end-to-end reconstruction of the recipient vessel. Besides decreasing the number of incisions on diabetic patients, our novel technique utilizing the "hanging" pedicle simplifies flap monitoring and inset and allows reconstruction of recipient vessels to reestablish distal blood flow.

• 정보처리학회논문지B
• /
• 제15B권5호
• /
• pp.477-486
• /
• 2008

얼굴의 기하학적 특징이 변하여 생기는 표정은 얼굴 인식 시스템의 인식 결과에 다양한 영향을 끼친다. 얼굴 인식율을 개선하기 위해 본 연구에서는 인식 대상 얼굴과 참조 얼굴 사이의 표정 차이를 줄이는 방법으로 얼굴 표정 정규화를 제안한다. 본 연구에서는 대형의 이미지 데이터베이스를 구축하지 않고도 한 개의 정지 이미지에 일반적인 얼굴 근육 모델을 이용하는 접근 방식을 제시하여 얼굴 표정 모델링과 정규화를 처리한다. 첫 번째 방식은 본능적으로 변하는 얼굴 표정의 생물학적 모델을 구축하기 위해 선형 근육 모델의 기하학적 계수를 예측하는 것이다. 두 번째 방식은 RBF(Radial Basis Function)기반의 보간과 와핑을 통해 주어진 표정에 따라 얼굴 근육 모델을 무표정한 얼굴로 정규화한 것이다. 실험 결과, 기저얼굴 방식, 지역 이진 패턴 방식, 회색조 상관측정 방식과 같은 얼굴 인식 과정의 전처리 단계로 본 연구의 표정 정규화 과정을 적용하면 정규화를 거치지 않은 것보다 더 높은 인식율을 보인다.

• Radiation Oncology Journal
• /
• 제9권2호
• /
• pp.351-359
• /
• 1991

LINAC 뇌정위적 방사선 수술은 주로 multiple noncoplanar arc를 이용한 single isocenter를 이용하고 있다. 이러한 방법에 의하면 구형선량 분포를 얻게 되는데, 뇌동정맥 기형이나 뇌종양의 경우 구형이 아닌 임의의 형태를 가진 경우도 많다. 본 논문에서는 임의의 병소형태에 대하여 multiple isocenters를 이용하여 병소모양과 같은 형태의 선량분포를 얻는 방법에 대하여 논하고져 한다. 적당한 조사변수들을 처음에 잘 선정하는 것은, 빠른 시간내에 최적선량 계획을 수행하는데 중요하다. 긴 병소모양에 대하여 같은 형태의 선량분포를 얻기 위한 isocenter 간격 및 조사면에 대한 guideline이 만들어졌다. 특히, 3차원 선량분포를 이용한 multiple isocenters의 응용에 대하여 논하여진다.

• 대한기계학회논문집
• /
• 제19권7호
• /
• pp.1604-1618
• /
• 1995

In the process of mechanical assembly design, assembly modeling systems have been used mainly for the design verification before manufacturing by enabling to check the interference and/ or the dynamic and kinematic performance. However, the conventional assembly modeling systems have a shortcoming that they can not be used in the initial design stage but can be used only after the design is fully completed. In other words conventional assembly modeling systems provide bottom-up modeling which means that the detailed modeling of components must precede the definition of relationships between them. To resolve this problem, an assembly modeling system is proposed to provide a top-down modeling environment in which components and assembly can be modeled simultaneously. To this end, an assembly data structure suitable for top-down assembly modeling has been established. Feature positioning Module(FPM) using geometric constraints has been also developed. The Sekective Solving Method proposed for FPM is based on the priority between the constraint equations and enables the designer's intent expressed by geometric constraints to be maintained throughout the whole modeling process. Finally, the feature based modeling technique using two-level features has been developed. Two-level features include an abstract model and a detailed model in a merged form in non-manifold data frame.

• Archives of Plastic Surgery
• /
• 제37권6호
• /
• pp.775-778
• /
• 2010

Purpose: Reconstruction of soft tissue defects with osteomyelitis in the lower third of the leg represents a challenge to plastic surgeons. Moreover, it is more arduous in multimorbid patients. One excellent option for reconstruction of these defects is to use a delayed distally based sural flap. Methods: We successfully used delayed distally based sural flap with a two-step procedure. During the first operation, radical debridement and elevation of flap were performed. The raised flap was fixed again at the donor site. The delay period ranged from seven to ten days. Between August 2008 and July 2009, we underwent operations for five patients using this technique. The size of flap varied from $10{\times}6\;cm$ to $12{\times}14\;cm$. Results: All flaps successfully survived. Partial skin loss of the grafted site was seen in two patients but no further surgical procedure was required for wound healing. Complaints of hypoesthesia on the lateral part of the foot was observed. In a three month follow-up period, hypoesthesia was resolved spontaneously. Conclusion: Delayed procedure improves the viability of distally based sural flap in high risk, critically multimorbid patients. We recommend that, if a two-stage operative approach is required, the delayed procedure should be considered.

• 한국건설관리학회논문집
• /
• 제10권4호
• /
• pp.87-100
• /
• 2009

공공사업에서 사업초기단계의 개략공사비 예측은 발주자에게 향후 공사비에 대한 정보를 제공함으로써 효율적인 예산수립을 가능하게 한다. 하지만 사업초기단계는 획득 가능한 정보량이 부족하기 때문에 상대적으로 정확한 공사비 예측이 어렵다. 현재 국내 발주기관에서 활용하고 있는 도로공사 개략공사비 산정체계는 단순하게 단위길이 당 단가에 도로의 연장을 곱하는 선형적인 모델이기 때문에 공사비 예측에 오차가 크게 발생하는 것으로 나타났다. 또한 사업의 진행에 따라 가용정보의 수준이 달라지기 때문에 개략공사비 예측모델에는 이러한 가용정보의 특성이 반영되는 것이 중요하다. 본 연구에서는 사업 초기단계를 크게 기획단계와 설계 초기단계의 두 단계로 구분하여 각 단계의 가용정보 수준 및 공사비 예측의 목적을 고려한 개략공사비 산정모델을 제시하였다. 공사비 예측모델의 개발을 위하여 총 143건의 공사 데이터를 수집하여 활용하였으며, 이를 통해 각 단계의 가용정보 수준에 적합한 공사비 영향변수를 도출하였다. 제안된 기획단계 및 설계초기 단계의 개략공사비 산정모델은 검증과정을 통하여 각 단계에서 요구되는 정확도 수준을 확인하였으며, 이러한 가용정보 수준에 입각한 개략공사비 산정모델은 향후 예산 산정업무나 타당성 조사, 노선 대안 비교검토 등에 활용될 수 있을 것으로 기대된다.

• 동서간호학연구지
• /
• 제3권1호
• /
• pp.27-38
• /
• 1998

This study was carried out to understand the general conditions about management of hypertension and the differences in opinions between the Eastern-Western Nursing Sciences. In this context, this study was aimed to find out a possible integration of the Eastern-Western Nursing Sciences for the management of hypertension and to suggest a distinct frame of Korean nursing intervention method which is unique for the hypertensive patients by combining two hypertensive management systems originated from the Western type, "mainly classified by stage", and the Eastern type, "typically classified by form" as they are identified in the literature. From the research literature including both domestic and foreign, this study identified that exuberance of Yang of the Liver form mainly appeared to the patient who is at a border hypertension or the first stage of hypertension, Deficiency of Yin of the Liver and Kidneys form mostly appeared to the first stage and the second stage of Hypertension and Deficiency of the both of Yin and Yang form appeared to the third stage of Hypertension. These unifications of the types of Hypertension classified by stages and forms suggest the possibility not only of integration of the Eastern-western Medicine but also of establishment for the intervention of specific nursing management which is the united Eastern-western Nursing Science for the Hypertension. Hence, the new frame for the nursing management of Hypertensive patient is suggested as follows : 1) In case of the exuberance of Yang of the Liver form, as classified by form which is categorized to the border Hypertension or the first stage of Hypertension, nursing intervention should include general therapy, cooking meal and neutral care to restrain the condition of the exuberance of Yang of the liver. 2) In case of the deficiency of Yin of the liver and the Kidneys form, as classified by form which is categorized to the second stage of Hypertension, nursing intervention should include both the general and drug therapy and their use in combination with cooking meal and neural care to restrain the condition of the deficiency of Yin of the Li ver and Kidneys. 3) In case of the deficiency of both of Yin and Yang form, as classified by form which is categorized to he third stage of Hypertension should include both the general therapy and drug therapy and their use in combination with cooking meal and neural care to restrain the condition of deficiency of the both of Yin and Yang. In addition, using this basic frame of Hypertensive management, a specific way of nursing intervention, which is suitable for exuberance of Yang of the Liver form, deficiency of Yin of the Liver and Kidneys form, and deficiency of both of the Yin and Yang form and classified by Korean herbal medicine related to hypertension, should be pursued continuously in the future.

• 인터넷정보학회논문지
• /
• 제19권2호
• /
• pp.77-88
• /
• 2018

자궁경부암 예방을 위해 2016년 6월부터 만 12세 여아에 대한 자궁경부암 예방백신 무료접종이 실시되고 있다. 이 연구는 언론이 자궁경부암 예방백신 부작용이라는 리스크 정보에 대해 어떻게 보도하였는지 살펴보고, 정부의 위험 커뮤니케이션 및 정책홍보에의 함의를 제시하고자 하였다. 구체적으로 자궁경부암 예방백신 무료접종이 시작되기 전 6개월을 1기(정책결정 단계)로, 무료접종이 실시된 후 6개월을 2기(정책집행 단계)로 시기를 구분하여 자궁경부암 백신 부작용 및 안전성 관련 기사 314건을 분석하였다. 내용분석 및 네트워크 분석 결과, 1기보다 2기에 관련한 기사의 수가 증가하였으며, 질병관리본부에서 자궁경부암 백신의 안전성을 강조하고, 백신의 효과를 부각시키면서 접종을 권유한 내용이 언론보도의 한 축을 이루었다. 자궁경부암 백신의 부작용과 관련하여 1기에는 일본의 백신 접종 피해사례를 중심으로 보도되었고 이에 대한 학부모의 우려가 보도되었으나, 2기에는 일본 뿐만 아니라 유럽, 미국 등 세계 각국의 피해 사례가 빈번히 보도되었다. 향후 자궁경부암 예방백신 접종률을 높이기 위해서는 자궁경부암 백신 관련한 막연한 두려움이나 불안감이 증폭되지 않도록 전략적인 접근을 해야 할 시점이다.