• Science of Emotion and Sensibility
• /
• v.11 no.4
• /
• pp.511-520
• /
• 2008

The fundamental goal of this study is to analyze characteristics of combined relations of formative element factors that compose robot's face based on a result of preference response from robot's design. Also, in order to improve preference from the analysis result, this study intended to inquire into possibilities of suggesting design guideline. For these, pictures of 27 different kinds of robot faces were selected as experimental stimuli, and experiments of preference response and association response were performed. As a result of the experiments, various characteristics were achieved such as robot's eye shape having greater influences than facial structure, etc. Based on the result, formative element factor characteristics that could positively influence preference response on robot's face could be drawn and a basic design guideline could also be suggested. An eye should be oval so that the length-to-width ratio may be 1.67:1. The distance between both eyes should be 35% of the facial width. Also, eyes should be above the central latitude of the face so that they may be visually stable. It is advisable to round the face generally. Eyes should be harmonious with the face so that the robot may seem cute and charming.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.1
• /
• pp.80-90
• /
• 2011

The purposes of this study are clarifying the characteristics of women's hair style in the late Joseon Dynasty by inquiring into that hair style and, by extension, having a new understanding of the aesthetic consciousness of women in those times. The typical hair style of married Joseon women was Ungeonmeori and Jjokmeori, with Ungeonmeori being much more popular. Regardless of socioeconomic status, women used a big Gache as long as conditions permitted. Meanwhile, some women who led the trend or followed the national policy did Jjokmeori and wore Jokdoori. The Joseon Dynasty had a strict clothing system. However, giseangs were free from this restriction and they were free at attire. Therefore, they led the fashion trend. Both noble and common women followed the trend, imitating giseangs' attire. Women's hair style was used as a tool to express one's personality in the late Joseon Dynasty when the hierarchy was already weakened. In fact, it seems that women in those times cared more about hair style trend than clothing trend. This means that those women already had such a high quality of aesthetic consciousness that they showed their hair which is the closest to the face to advantage.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.4
• /
• pp.399-405
• /
• 2010

In this paper, the movement faces the problem of the difficult points upon the gaze of the user that corrective action is needed to solve the identification system offers a new perspective. Using the Kalman filter using the position information of the current head position estimated the future. In order to determine the authenticity of the face features of the face structural element information and the processing time is relatively fast horizontal and vertical histogram analysis method to detect the elements of the face. and people grow and infrared bright pupil effect obtained by constructing a real-time pupil detection, tracking and pupil - geulrinteu vectors are extracted.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.6 no.6
• /
• pp.973-980
• /
• 2011

In this paper, we gaze upon the movement faces the problem points are difficult to identify a user based on points and that corrective action is needed to solve the identification system is proposed a new eye. Kalman filter, the current head of the location information was used to estimate the future position in order to determine the authenticity of the face facial features and structural elements, the information and the processing time is relatively fast horizontal and vertical elements of the face using the histogram analysis to detect. And an infrared illuminator obtained by constructing a bright pupil effect in real-time detection of the pupil, the pupil was tracked - geulrinteu vectors are extracted.

• Journal of the Korea Computer Industry Society
• /
• v.5 no.1
• /
• pp.157-166
• /
• 2004

Consequently substantial research has been done on the development of the bio-metric recognition method as well as technical research in the field of authentication. As a method of bio-metric recognition, personal and unique information such as fingerprints, voice, face, Iris, hand-geometry and vein-pattern are used. The face image system in bio-metric recognition and information authentication reduces the denial response from the users because it is a non-contact system the face image system operates through a PC camera attached to a computer base this makes the system economically viable as well as user friendly. Conversely, the face image system is very sensitive to illumination, hair style and appearance and consequently creates recognition errors easily, therefore we must build a stable authentication system which is not too sensitive to changes in appearance and light. In this study, I proposed user authentication protocol to serve a confidentiality and integrity and to obtain a least Equal Error Rate to minimize the wrong authentication rate when it authenticates the user.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.11
• /
• pp.465-472
• /
• 2022

In this paper, the style synthesis network is trained to generate style-synthesized video through the style synthesis through training Stylegan and the video synthesis network for video synthesis. In order to improve the point that the gaze or expression does not transfer stably, 3D face restoration technology is applied to control important features such as the pose, gaze, and expression of the head using 3D face information. In addition, by training the discriminators for the dynamics, mouth shape, image, and gaze of the Head2head network, it is possible to create a stable style synthesis video that maintains more probabilities and consistency. Using the FaceForensic dataset and the MetFace dataset, it was confirmed that the performance was increased by converting one video into another video while maintaining the consistent movement of the target face, and generating natural data through video synthesis using 3D face information from the source video's face.

• Proceedings of the KIEE Conference
• /
• 2002.11c
• /
• pp.126-129
• /
• 2002

도우미로봇은 혼자 힘으로 걷기 어려운 노약자를 보조하는 보행 보조 기능과 다양한 오락 기능을 수행하는 로봇이다. 이 로봇은 음원 위치 추정기법에 의해서 어느 방향에서 소리가 발생하였는지 알아내고 그 방향으로 머리를 회전한다. 로봇의 머리에는 CCD카메라가 장착되어 있어서 카메라로부터 들어오는 영상에서 사람의 얼굴을 찾고 그 사람이 있는 곳까지 자율 주행기능에 의해서 장애물을 회피하며 이동한다. 사용자의 앞까지 이동하면 로봇은 이동을 멈추고 사용자로부터 명령을 받을 때까지 대기한다. 노약자는 로봇의 전반부에 부착되어 있는 터치스크린을 이용하여 로봇에게 다양한 명령을 내릴 수 있다. 로봇은 명령에 따라 보행 보조 작업을 수행하거나 전자메일, 음악, 영화 등 다양한 엔터테인먼트 서비스를 수행하게 된다.

• Korean journal of applied entomology
• /
• v.56 no.4
• /
• pp.435-436
• /
• 2017

Subgena and clypeus are a continuous plate, so should be collectively called as peristoma. Subsequently, subgenal sulcus is revised into peristomal sulcus or cranio-stomal sulcus. Ptilinal suture on dipteran adult head is revised into ptilinal fissure. Notal and pleural wing processes are revised into notal and pleural process, respectively. The lower plate of abdomen is ventum, while that of thorax is sternum.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.30 no.4
• /
• pp.563-575
• /
• 2003

The purpose of this study was to investigate differences in craniofacial characteristics of professional sportsmen who have practiced since their prepubertal periods. From the standardized lateral and P-A cephalograms of 137 sportsmen, 7 angular, 19 linear, 4 ratio, and 2 index measurements were measured and evaluated by means of statistical methods. The samples were divided into three groups: Group 1; ice hockey(n=17), foot-ball(n=27), basketball(n=16) Group 2; baseball(n=16), gymnastics(n=13), and Group 3; judo(n=18), ssireum(n=10), weight lift(n=20). The results were as follows: It seemed obvious that the cephalic indices of the 3 groups exhibited brachycephalic headform (Group 1; $0.85{\pm}0.04$, Group 2; $0.84{\pm}0.04$, Group 3; $0.83{\pm}0.06$) and there was no statistical difference among the groups (p>0.05). The facial indices of the Group 1 ($0.93{\pm}0.05$) and Group 2 ($0.93{\pm}0.04$) exhibited definite leptoprosopic facial forms while the Group 3 ($0.90{\pm}0.04$) showed more or less euryprosopic facial form, and there appeared significant difference between the Group 1 and 3 (p<0.05), and also between the Group 2 and 3 (p<0.05). There appeared strong relationships between the facial indices and the facial axis angle, mandibular plane angle, total craniofacial height, total facial height, upper anterior dental height, lower anterior dental height, mandibular length, lower anterior facial height ratio, and especially with lower anterior facial height (p<0.001). It seemed that most of the vertical facial measurements of the Group 1 and 2 appeared to be larger than those of the Group 3.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.1
• /
• pp.17-23
• /
• 2005

In this paper, we propose face recognition method using embedded data in super states segmentalized that is specification region exist to face region, hair, forehead, eyes, ears, nose, mouth, and chin. Proposed method defines super states that is specification area in normalized size (92×112), and embedded data that is extract internal factor in super states segmentalized achieve face recognition by PCA algorithm. Proposed method can receive specification data that is less in proposed image's size (92×112) because do orignal image to learn embedded data not to do all loaming. And Showed face recognition rate in image of 92×112 size averagely 99.05%, step 1 99.05%, step 2 98.93%, step 3 98.54%, step 4 97.85%. Therefore, method that is proposed through an experiment showed that the processing speed improves as well as reduce existing face image's information.