• 감성과학
• /
• 제11권4호
• /
• pp.511-520
• /
• 2008

본 연구에서는 로봇디자인에 대한 선호 반응의 결과를 바탕으로 로봇 얼굴을 구성하는 조형요소의 조합 관계에 대한 특성을 분석하는 것이 기본적인 목적이다. 아울러 분석 결과로부터 선호도를 향상시키기 위한 디자인가이드의 제시 가능성을 고찰하고자 하였다. 이를 위하여 27가지의 로봇 얼굴 사진을 실험자극으로 선정하고, 선호 반응 및 연상 반응에 관한 실험을 진행하였다. 실험 로봇 얼굴의 형태 보다는 눈의 형태가 선호 반응에 많은 영향을 미치는 등 다양한 특성이 나타났다. 이러한 결과를 바탕으로 로봇 얼굴에 대한 선호반응에 긍정적 영향을 미칠 수 있는 각 조형요소의 특성 도출 및 기본적 디자인가이드라인을 제시할 수 있었다. 구체적으로 먼저, 눈의 형태는 세로의 길이가 가로 길이 보다는 긴(167%) 타원형을 적용하는 것이 필요하다. 그리고 눈 사이의 거리는 얼굴 폭의 35% 정도를 유지해야 한다. 또한 눈의 위치는 얼굴의 중심축으로부터 상향에 배치하여 시각적으로 안정감을 주는 것이 중요하다. 머리 전체의 형태는 원형을 이용한 구 타입이 바람직하다. 머리의 형태와 눈과의 조화는 로봇으로서 기본적으로 갖추어야 할 귀엽고 깜찍한 이미지를 구현하는 것이 필요하다.

• 제어로봇시스템학회논문지
• /
• 제11권1호
• /
• pp.50-57
• /
• 2005

We present a simple and effective method of face and facial feature detection under pose variation of user face in complex background for the human-robot interaction. Our approach is a flexible method that can be performed in both color and gray facial image and is also feasible for detecting facial features in quasi real-time. Based on the characteristics of the intensity of neighborhood area of facial features, new directional template for facial feature is defined. From applying this template to input facial image, novel edge-like blob map (EBM) with multiple intensity strengths is constructed. Regardless of color information of input image, using this map and conditions for facial characteristics, we show that the locations of face and its features - i.e., two eyes and a mouth-can be successfully estimated. Without the information of facial area boundary, final candidate face region is determined by both obtained locations of facial features and weighted correlation values with standard facial templates. Experimental results from many color images and well-known gray level face database images authorize the usefulness of proposed algorithm.

• 전기전자학회논문지
• /
• 제24권1호
• /
• pp.293-301
• /
• 2020

Consultation with the patient and doctor is very important in the examination. However, if the consultation cannot be done directly, such as corona virus, it is difficult for the doctor to determine the patient's condition more accurately. Recently, an image counseling system has been developed based on the Internet, but in the case of heart disease, remote medical counseling cannot be performed because it is not possible to stethoscope the heart sounds remotely. In order to solve this problem, it is necessary to develop an interactive mobile robot capable of remote medical consultation, and a doctor and a patient should be able to set a planting sound during consultation and transmit it in real time. In this paper, we developed a robot that can remotely control a medical counseling robot to move to a hospital room where patients are hospitalized, and to consult a patient in the room remotely from a doctor's office. A remote medical imaging stethoscope system for real-time heart sound transmission is presented. The proposed system is a kind of P2P communication that transmits video information, audio information, and control signal independently through webRTC platform, so that there is no data loss. Consults and sees doctors in real time and finds it more effective than traditional methods for patient security. The system implemented in this paper will be able to perform remote medical care in the place where the spread of diseases between humans like the recent corona 19 as well as the remote medical care of heart disease patients in the future.

• 전자공학회논문지
• /
• 제50권5호
• /
• pp.144-149
• /
• 2013

로봇 기술의 빠른 발전과 더불어 다양한 서비스를 탑재한 로봇 제품의 출시로 시장이 활성화되고 있다. 서비스 로봇은 사람과 로봇간 상호작용에 의한 서비스 제공이 주목적으로 이를 위해 HRI 대표 기술인 얼굴 인식 기술을 많이 활용하고 있다. 하지만 얼굴 인식 엔진이 탑재된 로봇의 성능이 소비자가 만족할만한 수준에 미치지 못하여 로봇 제품에 대한 신뢰도마저 저하되고 있다. 대부분 로봇의 얼굴 인식 성능시험은 제품 관점에서 평가가 아닌 인식 엔진 관점에서 평가로 로봇의 직접적인 성능을 반영하지 못한다. 이에 본 논문에서는 로봇 제품 관점에서 얼굴 인식 성능평가를 위해 실물 영상을 대신하여 LED 모니터의 이용 가능성을 검증하고자 한다. 이를 위해 실물 영상과 LED 모니터 영상의 인식룰 편차를 비교하고 타당성을 제시한다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2016년도 추계학술대회
• /
• pp.629-631
• /
• 2016

본 논문에서는 로봇을 주행하면서 얼굴을 인식하는 로봇에 대해서 다루었다. 로봇이 일반화 하는데 가장 기초적으로 수행되어야 하는 기능이다. 동시에 다양한 분야에서 활용 가능한 기술이라고 할 수 있다. 본 논문에서는 특정한 공간에서의 보안 방법으로의 생체인식 기술 중 얼굴인식을 모바일 로봇 상에서 작동하는 것을 구상했다.

• 로봇학회논문지
• /
• 제18권2호
• /
• pp.164-171
• /
• 2023

To control the spread of COVID-19, it is important to identify the infection in its incipient stages so that the infected persons can be dealt with accordingly. The currently used face to face sampling method may increase the risk of infection for medical professionals as it exposes them to the asymptomatic yet infectious patients. This can result in further increases in the load on the medical system and workload of the medical staff. As a solution to this problem, in this paper, we present a robotic system for rapid non-face-to-face automatic nasopharyngeal swab sample collection. The system consists of a custom designed 7-DoF manipulator equipped with a specially developed safety mechanism for restricting the maximum force applied by the tip of the swab. During the swab sampling process, the force applied by the tip of the swab is continuously monitored in real-time by a 3-axis force sensor in order to detect contact with the nasopharynx. The possibility of using this system for automaticnasopharyngeal swab sample collection is proven through experimentation with a phantom model.

• 제어로봇시스템학회논문지
• /
• 제20권5호
• /
• pp.520-525
• /
• 2014

Generally, feature area detection methods are widely used for face expression recognition by detecting the feature areas of human eyes, eyebrows and mouth. In this paper, we proposed a face expression recognition method using the histograms of the face, eyes and mouth for many applications including robot technology. The experimental results show that the proposed method has a new type of face expression recognition capability compared to conventional methods.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.49.1-49
• /
• 2001

The skin color model is a very important concept in face detection, face recognition and face tracking. Usually, this model is obtained by estimating a probability density function of skin color distribution. In many cases, it is assumed that the underlying density function follows a Gaussian distribution. In this paper, a new method for non-parametric estimation of the probability density function, by using feed-forward neural network, is used to estimate the underlying skin color model. By using this method, the resulting skin color model is better than the Gaussian estimation and substantially approaches the real distribution. Applications to face detection and face ...

• 로봇학회논문지
• /
• 제1권2호
• /
• pp.151-157
• /
• 2006

This paper is concerned with the template-based face recognition from robot camera images with illumination and distance variations. The approaches used in this paper consist of Eigenface, Fisherface, and Icaface which are the most representative recognition techniques frequently used in conjunction with face recognition. These approaches are based on a popular unsupervised and supervised statistical technique that supports finding useful image representations, respectively. Thus we focus on the performance comparison from robot camera images with unwanted variations. The comprehensive experiments are completed for a databases with illumination and distance variations.

• 한국생산제조학회지
• /
• 제21권1호
• /
• pp.123-129
• /
• 2012

Recently, interests on cleaning robots workable in pipes (termed as in-pipe cleaning robot) are increasing because Garbage Automatic Collection Facilities (i.e, GACF) are widely being installed in Seoul metropolitan area of Korea. So far research on in-pipe robot has been focused on inspection rather than cleaning. In GACF, when garbage is moving, the impurities which are stuck to the inner face of the pipe are removed (diameter: 300 mm or 400 mm). Thus, in this paper, by using TRIZ (Inventive Theory of Problem Solving in Russian abbreviation), an in-pipe cleaning robot of GACF with the 6-link sliding mechanism will be proposed, which can be adjusted to fit into the inner face of pipe using pneumatic pressure(not spring). The proposed in-pipe cleaning robot for GACF can have forward/backward movement itself as well as rotation of brush in cleaning. The robot body should have the limited size suitable for the smaller pipe with diameter of 300 mm. In addition, for the pipe with diameter of 400 mm, the links of robot should stretch to fit into the diameter of the pipe by using the sliding mechanism. Based on the conceptual design using TRIZ, we will set up the initial design of the robot in collaboration with a field engineer of Robot Valley, Inc. in Korea. For the optimal design of in-pipe cleaning robot, the maximum impulsive force of collision between the robot and the inner face of pipe is simulated by using RecurDyn(R) when the link of sliding mechanism is stretched to fit into the 400 mm diameter of the pipe. The stresses exerted on the 6 links of sliding mechanism by the maximum impulsive force will be simulated by using ANSYS$^{(R)}$ Workbench based on the Design Of Experiment(in short DOE). Finally the optimal dimensions including thicknesses of 4 links will be decided in order to have the best safety factor as 2 in this paper as well as having the minimum mass of 4 links. It will be verified that the optimal design of 4 links has the best safety factor close to 2 as well as having the minimum mass of 4 links, compared with the initial design performed by the expert of Robot Valley, Inc. In addition, the prototype of in-pipe cleaning robot will be stated with further research.