• 대한의용생체공학회:의공학회지
• /
• 제42권4호
• /
• pp.186-192
• /
• 2021

In this paper, we evaluated prediction accuracy of Euler angle spectrograph classification method using a convolutional neural networks (CNN) for hand gesture recognition in augmented reality (AR) cognitive rehabilitation system based on Leap Motion Controller (LMC). Hand gesture recognition methods using a conventional support vector machine (SVM) show 91.3% accuracy in multiple motions. In this paper, five hand gestures ("Promise", "Bunny", "Close", "Victory", and "Thumb") are selected and measured 100 times for testing the utility of spectral classification techniques. Validation results for the five hand gestures were able to be correctly predicted 100% of the time, indicating superior recognition accuracy than those of conventional SVM methods. The hand motion recognition using CNN meant to be applied more useful to AR cognitive rehabilitation training systems based on LMC than sign language recognition using SVM.

• 대한인간공학회지
• /
• 제26권4호
• /
• pp.143-146
• /
• 2007

Due to the expansion of cities and the increasing number of large-scale and complex public spaces, there is an increase in public signage. Moreover, the information described on these signs tends to be diverse and complicated. Complex signs that contain multiple destinations or other information must be considered to determine not only the proper size, color, etc. but also the most effective arrangement of design elements. In the previous research, the cognitive utility of complex public signs was estimated using computer simulation software. In the current research, we focused on the objective estimation of the effectiveness of the results obtained in the previous research utilizing an eye mark recording system. Two cognitive engineering experiments clarified five points for improvement in the usability of complex signs, as follows: 1) Parallel construction of characters and pictograms is more efficient. 2) Grouping elements result in rapid recognition of information chunks. 3) Visual characters and pictograms are effective, along with proper density of information. 4) Specific arrangement of sign arrows is effective. 5) Figures on signs influence the sequence of information searches.

• 한국통신학회논문지
• /
• 제31권11C호
• /
• pp.1071-1076
• /
• 2006

본 논문에서는 수화 인식을 위한 얼굴 및 손 추적시스템을 제안한다. 제안된 시스템은 검출 및 추적 단계로 구분된다. 검출 단계에서는 신호의 주체인 얼굴과 손에 위치한 피부 특징을 이용하였다. CbCr 공간에서의 타원 모델을 구성하여 피부 색상을 검출하고 피부 영역을 분할한다. 그리고 크기와 얼굴 특징을 이용하여 얼굴과 손 영역을 정의한다. 추적 단계에서는 동작 추정을 위하여 첫 번째 손 영역으로 예측된 다음의 손위치를 연산함으로써 두 번째 손의 영역을 유도해낸다. 그러나 갑작스런 움직임의 속도 변화가 있을 경우 연속된 프레임에서 추적된 위치는 부정확하였다. 이러한 점을 해결하고자 손 영역에 대하여 반복적인 재연산을 수행하여 적응적으로 영역을 찾음으로써 오차를 보정하도록 하였다. 실험 결과 제안된 방법은 기존의 방법보다 4%의 처리 시간이 증가된 반면, 예측 오차는 96.87%까지 감소시킬 수 있었다.

• 한국멀티미디어학회논문지
• /
• 제16권12호
• /
• pp.1393-1402
• /
• 2013

Hand gesture is one of the most popular communication methods in everyday life. In human-computer interaction applications, hand gesture recognition provides a natural way of communication between humans and computers. There are mainly two methods of hand gesture recognition: glove-based method and vision-based method. In this paper, we propose a vision-based hand gesture recognition method using Kinect. By using the depth information is efficient and robust to achieve the hand detection process. The finger labeling makes the system achieve pose classification according to the finger name and the relationship between each fingers. It also make the classification more effective and accutate. Two kinds of gesture sets can be recognized by our system. According to the experiment, the average accuracy of American Sign Language(ASL) number gesture set is 94.33%, and that of general gestures set is 95.01%. Since our system runs in real-time and has a high recognition rate, we can embed it into various applications.

• Journal of Trauma and Injury
• /
• 제20권2호
• /
• pp.144-148
• /
• 2007

Purpose: The management of hemorrhagic shock is critical for trauma patients. To assess hemorrhagic shock, the clinician commonly uses a change in positional blood pressure, the shock index, an estimate of the diameter of inferior vena cava based on sonography, and an evaluation of hypoperfusion complex shown on a CT scan. To add the finding for the hypoperfusion complex, the 'halo sign' was introduced recently. To our knowledge, this 'halo sign' has not been evaluated for its clinical usefulness, so we designed this study to evaluate its usefulness and to find the useful CT signs for hypoperfusion complex. Methods: The study was done from January 2007 to May 2007. All medical records and CT images of 124 patients with trauma were reviewed, of which 103 patients were included. Exclusion criteria was as follows: 1) age < 15 year old and 2) head trauma score of AIS ${\geq}$ 5. Results: The value of kappa, to assess the inter-observer agreement, was 0.51 (p < 0.001). The variables of the halo-sign-positive group were statistically different from those of the halo-sign-negative group. The rate of transfusion for the halo-sign-positive group was about 10 times higher than that of the halo-sign-negative group and the rate of mortality was about 6 times higher. Conclusion: In the setting of trauma, early abdominal CT can show diffuse abnormalities due to hypoperfusion complex. Recognition of these signs is important in order to prevent an unwanted outcome in hemorrhagic shock. We conclude that the halo sign is a useful one for hypoperfusion complex and that it is useful for assessing the degree of hemorrhagic shock.

• 한국전자통신학회논문지
• /
• 제16권4호
• /
• pp.699-708
• /
• 2021

본 논문에서는 2개의 비전 센서와 딥 러닝을 이용한 자율주행 차량의 속도제어 알고리즘을 제시하였다. 비전 센서 A로부터 제공되는 도로 속도 표지판 영상에 딥 러닝 프로그램인 텐서플로우를 이용하여 속도 표지를 인식한 후, 자동차가 인식된 속도를 따르도록 하는 자동차 속도 제어 알고리즘을 제시하였다. 동시에 비전 센서 B부터 전송되는 도로 영상을 실시간으로 분석하여 차선을 검출하고 조향 각을 계산하며 PWM 제어를 통해 전륜 차축을 제어, 차량이 차선을 추적하도록 하는 조향 각 제어 알고리즘을 개발하였다. 제안된 조향 각 및 속도 제어 알고리즘의 유효성을 검증하기 위해서 파이썬 언어, 라즈베리 파이 및 Open CV를 기반으로 하는 자동차 시작품을 제작하였다. 또한, 시험 제작한 트랙에서 조향 및 속도 제어에 관한 시나리오를 검증함으로써 정확성을 확인할 수 있었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1788-1793
• /
• 2003

The present of state is situation that is realized by necessity of maintenance of public security about great many information is real condition been increasing continually in knowledge info-age been situating in wide field of national defense, public peace, banking, politics, education etc. Also, loss or forgetfulness, and peculation by ID for individual information and number increase of password in Internet called that is sea of information is resulting various social problem. By alternative about these problem, including Biometrics, several authentication systems through sign(Signature), Smart Card, Watermarking technology are developed. Therefore, This paper shows that extract factor that efficiency can get into peculiar feature in physical features for good fingerprint recognition algorithm implementation with old study finding that take advantage of special quality of these fingerprint.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1996년도 춘계학술대회 논문집
• /
• pp.670-674
• /
• 1996

In automated search of a design database to support mechanical design, it is necessaryto recognize a shape pattern which represents a design object. This paper introduces the concept of a surface relation graph (SRG) for recognizing shape patterns from a 3D boundary representation scheme of a solid model(a B-rep model). In SRG, the nodes and arcs correspond to the faces and edges shared by two adjacent faces, respectively. An attribute assigned to an arc is given by an integer which discriminates the relationship between two adjacent faces. The + sign of the integer represents the geometric convexity of the solid, and the -sign the concivity at the shared edge. The input shape is recognized by comparison with the predefined features which are subgraphs of the SRG. A hierarchyof the database for upporting the design is presented. A search for the design database is also discussed. The usefulness of this method is illustrated by some application results.

• 한국통신학회논문지
• /
• 제22권3호
• /
• pp.401-409
• /
• 1997

기존의 방향성 패턴 스펙트럼에 비하여 보다 정확하게 방향성 정보를 나타낼 수 있는 패턴 스펙트럼 성분 함수를 도입하고 그 성질을 분석하였다. 그리고 패턴 스펙트럼 성분 함수에 의하여 잡음성 형상을 식별하고자 적응 거리 함수를 제안하였다. 제안한 패턴 스펙트럼 성분 함수를 주의 교통 표지 식별에 실제 응용하여 적응 거리 함수에 의하여 평가한 본 결과 방향성 패턴 스펙트럼에 비하여 보다 만족할 만한 결과를 얻을 수 있었다.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2019년도 제60차 하계학술대회논문집 27권2호
• /
• pp.271-272
• /
• 2019

현재 4차 산업혁명으로 인해 많은 이들의 삶의 질이 이전보다 개선되었음에도 불구하고, 소외된 계층을 위한 개발은 타 분야에 비해서 더뎌지고 있는 실정이다. 현대의 청각 장애인과 언어 장애인들은 시각 언어인 수화를 이용하여 의사소통을 한다. 그러나 수화는 진입 장벽이 높기 때문에, 이를 사용하지 않는 사람들은 청각 장애인 및 언어 장애인과 의사소통을 하는데 어려움을 겪는다. 본 논문은 이러한 불편함을 줄이기 위해 서포트 벡터 머신(Support Vector Machine, SVM) 기반의 HOG(Histogram of Oriented Gradients) 특징 벡터를 이용하여 수화의 기본인 숫자를 분류할 수 있는 시스템을 구현하여 수화를 번역할 수 있는 가능성을 제안한다.