• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.29-32
• /
• 2007

최근 영상 처리 기술이 발달함에 따라 다양한 응용시스템에 영상 처리 기술을 접목하려는 시도가 나타나고 있다. 특히 영상 내의 얼굴을 객체로 다루는 인식 기술의 발전으로 얼굴 정보를 이용한 기술의 응용 분야는 게임 및 카메라 둥 다양한 분야에서 사용되고 있다. 본 논문에서는 오프라인 회의 보조 시스템에서 화자를 구분하기 위한 기법을 제시한다. 제안된 기법은 얼굴 객체 정보에서 화자 구별을 위한 특징 값을 제시하고, 이를 이용하여 얻어진 입 주변 엣지(Edge)를 이루는 픽셀들의 분산 값으로 화자 여부를 판단한다.

• Information and Communications Magazine
• /
• v.32 no.8
• /
• pp.38-44
• /
• 2015

본고에서는 자동차의 자율주행이라는 최종의 목표를 위해 필요한 여러 가지 필수 기술 중 하나라고 할 수 있는 자동차의 자기 위치 인식을 위한 측위 기술에 대해 소개하고 그와 관련된 여러 연구 개발 동향을 살펴보고자 한다. 또한, 지능형 운전보조 시스템(ADAS, Advanced Driver Assistance System)에서 필수적인 고정밀 전자 지도(High Precision Map)가 자동차의 자기 위치 인식 정확도 향상에 어떤 방법으로 활용되는 지에 대해서도 알아 보고자 한다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1995.10b
• /
• pp.293-299
• /
• 1995

본 논문은 컴퓨터 시각을 이용하여 동적 제스쳐를 인식하기 위한 효율적인 지식 표 현 기법의 개발을 목표로 한다. 제스쳐란 시각적인 언어로서 소리를 대신하여 몸짓이나 손 짓을 통하여 자신의 생각이나 의도를 전달하는 보조적인 의사 전달 수단이다. 제안된 기법 은 여러 다양한 지식을 통합하여 총체적으로 표현하기에 적합한 프레임 구조를 기반으로 한 다. 프레임 지식을 물체의 특성을 표현하는 객체 지식, 물체의 움직임을 표현하는 행동 지 식, 그리고 객체 지식과 행동 지식의 순서화 된 집함으로써 동적인 제스쳐를 표현하는 스키 마로 분류한다.

• Journal of The Korean Association of Information Education
• /
• v.10 no.1
• /
• pp.155-161
• /
• 2006

Robots evolve from tools to information media since they generates information by interacting with human. As studies on robot-aided education are still in a starting phase, attempts need to be made to use robots for educational purposes and to investigate the effects of the use. It was showed that robot-aided learning was friendlier than other media assisted learning, and especially effective for motivating children. We developed the prototype robot Jenny that can help teachers as a educational media in class(i.e. as a T.A. robot, it can present robot contents on its chest to screen and explain about it when teacher asks). is a schoolmate for 5th or 6th grade children or an elder schoolmate for the rest. We performed the field trial at an elementary school. We carried out 9 classes for three subjects(english, korean, music) with -students in $4th{\sim}5th$ grade. They thought Jenny who was 13 years old as an elder schoolmate in 6th grade. Also, a significant difference was found in the interest and concentration of experimental groups from controlled groups.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.72-75
• /
• 2022

야외 환경을 카메라로 촬영한 일반 영상에서 텍스트 이미지를 검출하고 인식하는 기술은 로봇 비전, 시각 보조 등의 기반이 되는 기술로 활용될 수 있어 매우 중요한 기술이다. 하지만 저해상도의 텍스트 이미지의 경우 텍스트 이미지에 포함된 노이즈나블러 등이 더 두드러지기 때문에 텍스트 내용을 인식하는 것이 어렵다. 이에 본 논문은 일반 영상에서의 저해상도 한글 및 영어 텍스트에 대한 이미지 초해상화를 통해 텍스트 인식 정확도를 개선하였다. 트랜스포머에 기반한 모델로 한글 및 영어 텍스트에 대한 이미지 초해상화를 수행하였으며, 영어 및 한글 데이터셋에 대해 제안한 초해상화 방법을 적용했을 때 그렇지 않을 때보다 텍스트 인식 성능이 개선되는 것을 확인하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.497-498
• /
• 2023

많은 인구가 몰리면 군중 추돌 현상과 도미노 현상이 발생하여 압사 사고가 일어나 이에 대한 해결책이 요구된다. 본 논문에서는 위 문제를 개선하고자 보행자 상황 인식을 이용한 재난 경고 시스템을 구현하였다. 이 시스템은 재난관리기관에서 기존에 운영하고 있는 것과 같은 CCTV영상을 이용하여 딥러닝 영상인식 기술을 사용하여 보행자 안전 규정에 따른 보행자 상황을 인식해 재난 상황을 표시해주고, 경고를 한다. 보행자 상황 인식하기 위해 엣지컴퓨터에서 연결된 카메라 영상을 받아 상황인식을 하고, 인식된 상황과 영상을 서버로 전송하여 정보를 저장하고, 상황을 경고 한다. 상황인식을 위해 보행자 데이터는 직접 수집하여 학습시킨 weights 파일을 사용하였다. 보행자 인식은 YOLOv4-tiny를 사용하였고, 위험 단계는 총 4단계로 설정하였다. 이를 활용하여 기존의 CCTV영상을 활용하여 관리자를 보조하여 보행자 재난 상황시에 신속하게 재난을 인식하여 구호 조치를 할 수 있다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.1
• /
• pp.83-90
• /
• 2010

Cancelable biometrics is a robust and secure biometric recognition method using revocable biometric template in order to prevent possible compromisation of the original biometric data. In this paper, we present a new cancelable bits extraction method for the facial data. We use our previous cancelable feature template for the bits extraction. The adopted cancelable template is generated from two different original face feature vectors extracted from two different appearance-based approaches. Each element of feature vectors is re-ordered, and the scrambled features are added. With the added feature, biometric bits string is extracted using helper data based method. In this technique, helper data is generated using statistical property of the added feature vector, which can be easily replaced with straightforward revocation. Because, the helper data only utilizes partial information of the added feature, our proposed method is a more secure method than our previous one. The proposed method utilizes the helper data to reduce feature variance within the same individual and increase the distinctiveness of bit strings of different individuals for good recognition performance. For a security evaluation of our proposed method, a scenario in which the system is compromised by an adversary is also considered. In our experiments, we analyze the proposed method with respect to performance and security using the extended YALEB face database

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.11 no.2
• /
• pp.147-156
• /
• 2017

The white cane, walking assistive device of visually impaired person, has disadvantages for acquiring the information by contacting obstacles directly and detecting low obstacle on the ground. Recently, new devices have been developing to solve these problems, but these were not widely used due to high price and appearance. Therefore, in this study, we developed two types of walking assistive shoes which were manufactured with infrared sensors, pressure sensors and vibrating motors. Two types of shoes were classified with single sensor (SS) and double sensor (DS) type according to the number of infrared sensor. To evaluate the effectiveness, we compared required time and number of collisions during walking with walking assistive shoes and white cane on obstacle area. As the results, required time was increased than white cane while number of collisions was decreased when walking with developed walking assistive shoes. In addition, required time and number of collisions was more reduced when using walking assistive device than white cane. Therefore, we suggests that developed walking assistive shoes can a great help to provide safe walking condition and reducing time to adapt new types of walking assistive shoes.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.26 no.3
• /
• pp.85-96
• /
• 2023

This study developed and evaluated a safe route guidance service for electric personal assistive mobility device used mainly by the mobility impaired people to improve their mobility. Thirteen underlying factors affecting the mobility of electric personal assistive mobility device have been derived through a survey with the mobility impaired people and employees in related organizations in Busan Metropolitan City. After assigning safety scores to individual factors and identifying the relevant factors along routes of interest with an object detection AI model, the safe route for electric personal assistive mobility device was provided through an optimal path-finding algorithm. As a result of comparing the general route of T-map and the recommended route of this study for the identical routes, the latter had relatively fewer obstacles and the gentler slope than the former, implicating that the recommended route is safer than the general one. As future works, it is necessary to enhance the function of a route guidance service based on the real-time location of users and to conduct spot investigations to evaluate and verify its social acceptability.

• Journal of dental hygiene science
• /
• v.12 no.1
• /
• pp.23-29
• /
• 2012

The purpose of this study was to investigate the image and the awareness of dental hygienists in dental hygiene and non-dental hygiene students. The subjects in this study were 414 students who were in the three-year-course department of dental hygiene and in another four-year-course non-dental hygiene department in G college in the city of Gwangju. After a survey was conducted, the collected data were analyzed. The findings of the study were as follows: 1. As a result of general awareness about dental hygienists, the dental hygiene students knew 97.5% and non-dental hygiene students knew 80.6% about dental hygientist as a job. There were significant differences(p<0.001). In regard of awareness about status in medical law, medical technician was the highest in the dental hygiene students(52.8%), and medical assistant was the highest in the non-dental hygiene students(48.8%) 2. As a result of awareness about the main tasks of dental hygienists X-ray and scaling were the highest in the dental hygiene students(42.3%), and treatment assistance was the highest in the non-dental hygiene students(32.9%). 3. In regard to awareness about image of dental hygienists, both groups were the highest in professionalism and were the lowest in negative image. All variable were differences statistically between dental hygiene and non-dental hygiene students(p<0.05).