• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.399-402
• /
• 2003

This paper deals with the making avatar like a caricature from human face image which is made by web camera. Generally, the Image made by web camera is not low quality but also, there are always various lights and backgrounds. So, It is impossible to recognize a human face's contour by some methods which only find some feature points of a image. Therefore, In this paper, we propose a new method for overcoming defeat of that methods. First, we got the area of human face roughly by color information. And then, we could find the exact human face's contour by using B-spline Snake.

• 대한한의진단학회지
• /
• 제22권1호
• /
• pp.19-31
• /
• 2018

For the purpose of the basic educated-establishment on the diagnostic methods of "facial color and shape which reflect human's spiritual essence and personality", we study on the diagnostic value and application of the human face. The study's domain is divided the form and color of human face. And the form and color of human face is respectively observed the diagnostic value and contents. The form of human face reflect plenty the information of the mankind, and the observation of the face is applied to the "Physiognomie" refering to the external features of humans. Therefore the diagnosis on the form of human face is the primary factor in the grouping of five-element human, the discrimination of the Sasang constitution, and the classification of Hyunsang type. The color of human face reflect the physical information of internal organs and the pathological change of disease, therefore we examine the region, character and grade of disease by the inspection of complexion including the changes of color and luster of the facial skin. The inspection on the color is also the primary factor in the grouping of five-element human, the classification of Hyunsang and the differentiation of syndromes. The value of the inspection of complexion including the changes of color and form of the face is widely known. In the future, we think, we need to study more about the theory of the diagnostic value and application of the human face.

• 대한임베디드공학회논문지
• /
• 제12권1호
• /
• pp.35-41
• /
• 2017

We propose a face recognition and notification system that can transform visual face information into tactile signals in order to help visually impaired people. The proposed system consists of a glasses type camera, a mobile computer and an electronic cane. The glasses type camera captures the frontal view of the user, and sends this image to mobile computer. The mobile computer starts to search for human's face in the image when obstacles are detected by ultrasonic sensors. In a case that human's face is detected, the mobile computer identifies detected face. At this time, Adaboost and compressive sensing are used as a detector and a classifier, respectively. After the identification procedures of the detected face, the identified face information is sent to controller attached to a cane using a Bluetooth communication. The controller generates motor control signals using Pulse Width Modulation (PWM) according to the recognized face labels. The vibration motor generates vibration patterns to inform the visually impaired person of the face recognition result. The experimental results of face recognition and notification system show that proposed system is helpful for visually impaired people by providing person identification results in front of him/her.

• 대한두개안면성형외과학회지
• /
• 제13권2호
• /
• pp.85-94
• /
• 2012

The world's first face transplantation was performed in France, in 2005. Since then, 21 cases of face transplantation have been performed. Face transplantation is one of the most prominent part of composite tissue allotransplantation (CTA) along with hand transplantation. Since these fields are not deal with life-saving organs, there are many arguments about immunosuppression therapy. Recent paradigm of face transplantation shows that surgical ranges are expanded from partial face transplantation to full face transplantation. Most immunosuppression protocols are triple therapy, which consists of tacrolimus (FK-506), mycophenolate mofetil and prednisolone. Anatomical researches, immunosuppression, and immunotolerance take great parts in the researches of CTA. The medical fields directly related to face transplantation are microsurgery, immunology, and transplantation. Nowadays, each field is performed widely. Therefore people, even medical teams think face transplantation could be easily realized, sooner or later. But there are lots of things that should be prepared for not only practice and immunosuppression therapy but also for the cooperation with relevant fields. That's the reason why only 21 cases of face transplantation have been done, while more than 70 cases of hand transplantation have been done in the past years. Especially in Korea, brain death patients are not enough even for organ transplantation and furthermore there are some troubles in taking part in the society of transplantation. Face transplantation has lots of problems concerning variable medical fields, administration, society, ethics, and laws. Therefore, for the realization of face transplantation in Korea, not only medical skills but also political powers are needed.

• Archives of Plastic Surgery
• /
• 제44권3호
• /
• pp.251-256
• /
• 2017

The most important environment of human being is the human being itself. So we have been sensitive to the appearance of ours and others at the same time. This writing aims for locating origins of the face and discerning differences [1] between the face of humans and those of other animals [2]. The face assumes a substantial significance not merely as a body function, but, above all, a means of expressions and features being looked at. The face is an important means of communication to humans as social animals. Knowledges about the various faces of the face are useful to become a efficient specialist as an extensive generalist because the face is a regular patron to the plastic surgery. The face in Korean consists of two elements of eol (the soul or the mind) and gul a residing place). When Wittgenstein says "the face is the soul of the body," his semantics corresponds to the Korean meaning. The meaning of the face in Korean is summed up in five ways. (1) the head or the front of the face with the eye, the nose and the mouth, (2) reputation or honor, (3) the general description of the psychological state, such as "the face of sadness", (4) a figure person representing a particular area, such as "Sun Dong-yul is the face of the Korean baseball community," (5) the primary imagery of the things and the event, such as "He is the face of the 4.19 Revolution." As such, the word "face", referring to a body part, extends its usages in a wide variety of contexts. What image do you convoke when you think of a person? With rare exceptions, you are most likely to invoke the face of the person. The face has come to be a byword for one's reputation or honor, and a pronoun for an expression of the essence of the thing and the event. This is presumably true of other languages. That is because human beings are equipped with the universal rule of language. A comprehensive understanding of the face is a must for cosmetic surgeons whose main responsibility is to sculpt and repair the face (Fig. 1).

• 한국정보전자통신기술학회논문지
• /
• 제4권3호
• /
• pp.202-208
• /
• 2011

최근 들어 인간과 컴퓨터의 상호작용을 통해 컴퓨터 시스템을 제어하는 기술에 관한 연구가 진행되고 있다. 이러한 응용분야의 대부분은 얼굴검출을 통해 사용자의 위치를 파악하고 사용자의 제스처를 인식하는 방법을 포함하고 있으나, 얼굴검출 성능은 아직 미흡한 실정이다. 사용자의 위치가 안정적으로 검출되지 못 하는 경우에는 제스처 인식 등의 인터페이스 성능은 현격하게 저하된다. 따라서 본 논문에서는 피부색과 얼굴검출의 누적 분포를 이용하여 동영상에서 안정적으로 얼굴을 검출할 수 있는 알고리즘을 제안하고, 실험을 통해 알고리즘의 유용성을 증명하였다. 제안한 알고리즘은 대응행렬 분석을 적용하여 사람을 추적하는 분야에 응용이 가능하다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권6호
• /
• pp.817-828
• /
• 2004

본 논문에서는 몽타주 기법과 음영합성 기법을 이용한, 디자이너(예술가)의 감각을 살린 벡터 기반의 얼굴 생성 시스템을 제안한다. 제안하는 시스템은 사진으로부터 얼굴의 특징정보를 추출하여 사람의 얼굴과 유사한 얼굴을 자동으로 생성해 주는 시스템이며, 윤곽선만을 사용하던 기존의 얼굴 생성 시스템과 달리 컬러 기반이며, 음영을 사진으로부터 추출하여 이를 이목구비 이미지와 합성하여 생성하는 방식이다. 따라서 실사형에 좀 더 근접한 얼굴을 생성할 수 있다는 장점을 갖는다. 또, 벡터를 기반으로 하기 때문에 사이즈에 제한 얼이 자유로운 변형이 가능할 뿐만 아니라 디자이너 또는 그림 작가의 느낌을 결과물에 그대로 유지할 수 있도록 한다는 점에서 타 접근방식과의 차별성을 갖는다. 또, 2D 아바타에 자유로운 표정을 적용하는 데에도 쉽게 적용이 가능하다.

• 산업공학
• /
• 제19권3호
• /
• pp.174-180
• /
• 2006

This paper deals with the robot system of recognizing human's expression from a detected human's face and then showing human's emotion. A face detection method is as follows. First, change RGB color space to CIElab color space. Second, extract skin candidate territory. Third, detect a face through facial geometrical interrelation by face filter. Then, the position of eyes, a nose and a mouth which are used as the preliminary data of expression, he uses eyebrows, eyes and a mouth. In this paper, the change of eyebrows and are sent to a robot through serial communication. Then the robot operates a motor that is installed and shows human's expression. Experimental results on 10 Persons show 78.15% accuracy.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2009년도 춘계학술대회 논문집
• /
• pp.605-606
• /
• 2009

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2001년도 추계학술대회 학술발표 논문집
• /
• pp.203-207
• /
• 2001

In this Paper, we propose the neural network based emotion recognition method for intelligently recognizing the human's emotion using CCD color image. To do this, we first acquire the color image from the CCD camera, and then propose the method for recognizing the expression to be represented the structural correlation of man's feature Points(eyebrows, eye, nose, mouse) It is central technology that the Process of extract, separate and recognize correct data in the image. for representation is expressed by structural corelation of human's feature Points In the Proposed method, human's emotion is divided into four emotion (surprise, anger, happiness, sadness). Had separated complexion area using color-difference of color space by method that have separated background and human's face toughly to change such as external illumination in this paper. For this, we propose an algorithm to extract four feature Points from the face image acquired by the color CCD camera and find normalization face picture and some feature vectors from those. And then we apply back-prapagation algorithm to the secondary feature vector. Finally, we show the Practical application possibility of the proposed method.