• 전자공학회논문지B
• /
• 제33B권8호
• /
• pp.114-123
• /
• 1996

In this paper, we propose an automatic recognition algorithm using the object centroid of a facial image. First, we separate the facial image from the background image using the chroma-key technique and we find the centroid of the separated facial image. Second, we search nose in the facial image based on knowledge of human faces and the coordinate of the object centroid and, we calculate 17 feature parameters automatically. Finally, we recognize the facial image by using feature parameters in the neural networks which are trained through error backpropagation algorithm. It is illustrated by experiments by experiments using the proposed recogniton system that facial images can be recognized in spite of the variation of the size and the position of images.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제5권5호
• /
• pp.251-260
• /
• 2016

얼굴 인식은 얼굴 영상에서 특징을 추출하고, 이를 다양한 알고리즘을 통해 학습하여 학습된 데이터와 새로운 얼굴 영상에서의 특징과 비교하여 사람을 인식하는 기술로 인식률을 향상시키기 위해서 다양한 방법들이 요구되는 기술이다. 얼굴 인식을 위해 학습 단계에서는 얼굴 영상들로 부터 특징 성분을 추출해야하며, 이를 위한 기존 얼굴 특징 성분 추출 방법에는 선형판별분석(Linear Discriminant Analysis, LDA)이 있다. 이 방법은 얼굴 영상들을 고차원의 공간에서 점들로 표현하고, 클래스 정보와 점의 분포를 분석하여 사람을 판별하기 위한 특징들을 추출하는데, 점의 위치가 얼굴 영상의 화소값에 의해 결정되므로 얼굴 영상에서 불필요한 영역 또는 변화가 자주 발생하는 영역이 포함되는 경우 잘못된 얼굴 특징이 추출될 수 있으며, 특히 일반 카메라 영상을 사용하여 얼굴인식을 수행하는 경우 얼굴과 카메라간의 거리에 따라 얼굴 크기가 다르게 나타나 최종적으로 얼굴 인식률이 저하된다. 따라서 본 논문에서는 이러한 문제점을 해결하기 위해 일반 카메라를 이용하여 얼굴 영역을 검출하고, 검출된 얼굴 영역에서 Gabor Filter를 이용하여 계산된 얼굴 외곽선을 통해 불필요한 영역을 제거한 후 일정 크기로 얼굴 영역 크기를 정규화하였다. 정규화된 얼굴 영상을 선형 판별 분석을 통해 얼굴 특징 성분을 추출하고, 인공 신경망을 통해 학습하여 얼굴 인식을 수행한 결과 기존의 불필요 영역이 포함된 얼굴 인식 방법보다 약 13% 정도의 인식률 향상이 가능하였다.

• 제어로봇시스템학회논문지
• /
• 제13권4호
• /
• pp.371-376
• /
• 2007

This paper presents an emotion recognition and its expression system of an intelligent robot like a home robot or a service robot. Emotion recognition method in the robot is used by a facial image. We use a motion and a position of many facial features. apply a tracking algorithm to recognize a moving user in the mobile robot and eliminate a skin color of a hand and a background without a facial region by using the facial region detecting algorithm in objecting user image. After normalizer operations are the image enlarge or reduction by distance of the detecting facial region and the image revolution transformation by an angel of a face, the mobile robot can object the facial image of a fixing size. And materialize a multi feature selection algorithm to enable robot to recognize an emotion of user. In this paper, used a multi layer perceptron of Artificial Neural Network(ANN) as a pattern recognition art, and a Back Propagation(BP) algorithm as a learning algorithm. Emotion of user that robot recognized is expressed as a graphic LCD. At this time, change two coordinates as the number of times of emotion expressed in ANN, and change a parameter of facial elements(eyes, eyebrows, mouth) as the change of two coordinates. By materializing the system, expressed the complex emotion of human as the avatar of LCD.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1999년도 KOBA 방송기술 워크샵 KOBA Broadcasting Technology Workshop
• /
• pp.133-140
• /
• 1999

In this paper, we propose a method of image-based three-dimensional modeling for realistic facial expression. In the proposed method, real human facial images are used to deform a generic three-dimensional mesh model and the deformed model is animated to generate facial expression animation. First, we take several pictures of the same person from several view angles. Then we project a three-dimensional face model onto the plane of each facial image and match the projected model with each image. The results are combined to generate a deformed three-dimensional model. We use the feature-based image metamorphosis to match the projected models with images. We then create a synthetic image from the two-dimensional images of a specific person's face. This synthetic image is texture-mapped to the cylindrical projection of the three-dimensional model. We also propose a muscle-based animation technique to generate realistic facial expression animations. This method facilitates the control of the animation. lastly, we show the animation results of the six represenative facial expressions.

• 대한한의진단학회지
• /
• 제17권3호
• /
• pp.233-240
• /
• 2013

Objectives The objective and universal grading system for the facial nerve palsy is needed to the objectification of treatment in Oriental medicine. In this study, the facial nerve palsy grading was developed with combination of image processing technique and Nottingham scale. Methods The developed system is composed of measurement part, image processing part, facial nerve palsy evaluation part, and display part. With the video data recorded by webcam at measurement part, the positions of marker were measured at image processing part. In evaluation part, Nottingham scales were calculated in four different facial expressions with measured marker position. The video of facial movement, time history of marker position, and Nottingham scale were displayed in display part. Results & Conclusion The developed system was applied to a normal subject and a abnormal subject with facial nerve palsy. The left-right difference of Nottingham scores was large in the abnormal compared with the normal. In normal case, the change of the length between supraorbital point and infraorbital point was larger than that of the length between lateral canthus and angle of mouth. The abnormal case showed an opposite result. The developed system showed the possibilities of the objective and universal grading system for the facial nerve palsy.

• 한국컴퓨터정보학회논문지
• /
• 제12권2호
• /
• pp.21-28
• /
• 2007

얼굴모델링과 애니메이션에 대한 기술은 컴퓨터 그래픽스 분야에서 오랫 동안 연구되어 오고 있는 분야 중 하나이다. 얼굴모델링 기술은 가상현실, MPEG-4 등의 연구목적과 영화, 광고, 게임 등의 산업 분야에서 많이 활용되고 있다. 따라서 좀 더 사실적인 인터페이스의 구현을 위하여 컴퓨터 의인화를 통해 인간과 상호작용 할 수 있는 3D 얼굴모델 개발은 필수적이다. 본 연구에서는 임의의 정면 얼굴 이미지를 이용하여 간편한 조작으로 3D 얼굴모델을 생성하는 시스템을 개발하였다. 이 시스템은 한국인 표준 얼굴모델을 이용하여 메쉬상의 조정점을 얼굴 부위와 윤곽에 맞게 정합한 다음 유동적이고 탄력적으로 조정하여 3D 얼굴모델을 생성하며, 그 결과인 3D 얼굴모델을 이동, 확대, 축소, 회전시켜 가며 실시간으로 확인 및 수정할 수 있다. 개발한 시스템의 유용성을 검증하기 위해 $630{\times}630$의 크기를 가지는 30개의 임의의 정면 얼굴이미지를 가지고 실험했다.

• Journal of Information Processing Systems
• /
• 제6권2호
• /
• pp.261-268
• /
• 2010

Tracking human facial expression within a video image has many useful applications, such as surveillance and teleconferencing, etc. Initially, the Active Appearance Model (AAM) was proposed for facial recognition; however, it turns out that the AAM has many advantages as regards continuous facial expression recognition. We have implemented a continuous facial expression recognition system using the AAM. In this study, we adopt an independent AAM using the Inverse Compositional Image Alignment method. The system was evaluated using the standard Cohn-Kanade facial expression database, the results of which show that it could have numerous potential applications.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.57-59
• /
• 2005

In our study, the automatic tracking algorithm of a human face is proposed by utilizing the thermal properties and 2nd momented geometrical feature of an infrared image. First, the facial candidates are estimated by restricting the certain range of thermal values, and the spurious blobs cleaning algorithm is applied to track the refined facial region in an infrared image.

• 복식
• /
• 제64권3호
• /
• pp.62-76
• /
• 2014

The purpose of this study is to classify the facial images and analyze shape characteristics of Korean women in their 20s. Previous research and survey were used for the study, the surveys targeted 220 university students in their 20s. The subjects of the experiment were 20-24 year-old Korean women. SPSS 12.0 statistics program was used to analyze the results, and factor analysis, Cronbach's ${\alpha}$ reliability analysis, and multidimensional scaling(MDS) were executed. The results of the study are as follows: First, the facial image types of Korean women in their 20s were classified into 4 categories as 'Youthfulness', 'Classiness', 'Friendliness', and 'Activeness'. Second, the multi-dimensional scaling method was performed and two orthogonal dimensions for the facial image of the Korean women were suggested: strong - soft and classy-friendly. Third, by analyzing the basic statistics concerning the structural characteristics of facial image of Korean women, there were differences in structural characteristics that form the facial images. Especially, significant difference appeared in items related forehead, eyebrows, eyes and jaw.

• 대한전자공학회논문지TE
• /
• 제37권3호
• /
• pp.45-52
• /
• 2000

본 연구에서는 인체 상반신영상에서 얼굴부위를 분할하기 위한 영상분할 알고리즘을 제안하였다. 제안한 알고리즘은 HWT를 적용하여 영상의 경계를 이루는 차분영상인 고주파대역과 평균영상인 저주파대역으로 분리하고, 저주파대역에서 고립점과 돌출부위, 경계중복점을 제거하였다. 또한 제안한 경계검출 알고리즘으로 경계를 검출하고 단순화시켰으며, 1픽셀 단위의 세선화과정을 통하여 경계를 선명하게 하였다. 그리고 제안 한 폐곡선추적 알고리즘으로 얼굴부위 경계만을 추출한 뒤, 마스크를 구성하고 원영상과의 정합을 통하여 얼굴부위분할을 하였다. 제안한 알고리즘을 적용하여 얼굴부위 분할실험을 실행한 결과 95.88%의 분할값을 갖는 얼굴분할이 이루어졌다.