• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제2권2호
• /
• pp.120-133
• /
• 2008

This paper presents a novel approach for facial motion tracking and facial expression cloning to create a realistic facial animation of a 3D avatar. The exact head pose estimation and facial expression tracking are critical issues that must be solved when developing vision-based computer animation. In this paper, we deal with these two problems. The proposed approach consists of two phases: dynamic head pose estimation and facial expression cloning. The dynamic head pose estimation can robustly estimate a 3D head pose from input video images. Given an initial reference template of a face image and the corresponding 3D head pose, the full head motion is recovered by projecting a cylindrical head model onto the face image. It is possible to recover the head pose regardless of light variations and self-occlusion by updating the template dynamically. In the phase of synthesizing the facial expression, the variations of the major facial feature points of the face images are tracked by using optical flow and the variations are retargeted to the 3D face model. At the same time, we exploit the RBF (Radial Basis Function) to deform the local area of the face model around the major feature points. Consequently, facial expression synthesis is done by directly tracking the variations of the major feature points and indirectly estimating the variations of the regional feature points. From the experiments, we can prove that the proposed vision-based facial expression cloning method automatically estimates the 3D head pose and produces realistic 3D facial expressions in real time.

• 한국전자통신학회논문지
• /
• 제19권1호
• /
• pp.309-316
• /
• 2024

얼굴 인식 기술은 다양한 분야에서 활용되고 있지만, 이는 사진 스푸핑과 같은 위조 공격에 취약하다는 문제를 가지고 있다. 이를 극복하기 위한 여러 연구가 진행되고 있지만, 대부분은 멀티모달 카메라와 같은 특별한 장비를 장착하거나 고성능 환경에서 동작하는 것을 전제로 하고 있다. 본 연구는 얼굴 인식 위조 공격 문제를 해결하기 위해, 특별한 장비 없이 일반적인 웹캠에서 동작할 수 있는 LH-FAS v2를 제안한다. 제안된 방법에서는, 머리 자세 추정에는 FSA-Net을, 얼굴 식별에는 ArcFace를 활용하여 사진 스푸핑 여부를 판별한다. 실험을 위해, 사진 스푸핑 공격 비디오로 구성된 VD4PS 데이터셋을 제시하였으며, 이를 통해 LH-FAS v2의 균형 잡힌 정확도와 속도를 확인하였다. 본 방법은 향후 사진 스푸핑 방어에 효과적일 것으로 기대한다.

• 제어로봇시스템학회논문지
• /
• 제7권4호
• /
• pp.309-318
• /
• 2001

In this paper, we describe methods that analyze a human gesture. A human interface(HI) system for analyzing gesture extracts the head and hand regions after taking image sequence of and operators continuous behavior using CCD cameras. As gestures are accomplished with operators head and hands motion, we extract the head and hand regions to analyze gestures and calculate geometrical information of extracted skin regions. The analysis of head motion is possible by obtaining the face direction. We assume that head is ellipsoid with 3D coordinates to locate the face features likes eyes, nose and mouth on its surface. If was know the center of feature points, the angle of the center in the ellipsoid is the direction of the face. The hand region obtained from preprocessing is able to include hands as well as arms. For extracting only the hand region from preprocessing, we should find the wrist line to divide the hand and arm regions. After distinguishing the hand region by the wrist line, we model the hand region as an ellipse for the analysis of hand data. Also, the finger part is represented as a long and narrow shape. We extract hand information such as size, position, and shape.

• 대한치과교정학회지
• /
• 제13권1호
• /
• pp.105-114
• /
• 1983

the author studied the corelativity between the head and face and the maxillary arch in Korean. This study was undertaker in 336 persons at age from 9 to 19 years who had normal occlusion by means of angle's classification. The following results were obtained. 1. The corelative coefficient between the Height of Head and Face (H.H.F.) and the Arch Length (A.L.) was 0.203-0.543, 2. The corelative coefficient between the Bizygomatic width (Z.W.) and the Bicanine width (C-C) was 0.203-0.543. 3. The corelative coefficient between the Bizygomatic width (Z.W.) and the Bimolar width (M-M) was 0.206-0.600. 4. The corelative coefficient between the Face shape (Index a) and Maxillaxy arch shape (In-dex c) was 0.232-0.404. 5. The corelative coefficient between the Face shape (Index a) and Maxillary arch shape (Index d) was 0.221-0.401. 6. There was no corelativity between the Anterior-posterior width of head (A.P.W.) and Arch Length A.L.), Head shape (Index b) and Maxillary arch shape (Index c, Index d).

• 방송공학회논문지
• /
• 제27권6호
• /
• pp.944-947
• /
• 2022

최근 코로나바이러스로 인한 마스크 착용이 급증함에 따라 마스크 착용에 대응할 수 있는 기술의 중요성이 증가하고 있다. 얼굴 자세 추정 분야는 운전자 주의, 얼굴 정면화, 시선 감지 등의 다양한 활용성에도 불구하고 마스크 착용에 따른 성능 저하 문제를 해결할 수 있는 연구가 거의 수행되지 않았다. 본 논문은 마스크 착용 유무에 따른 얼굴 자세 추정의 성능 저하에 대한 분석을 토대로, 마스크가 없는 얼굴 이미지의 크기 및 자세를 분석하여 마스크 이미지를 합성할 수 있는 데이터 증강 기법을 제안한다. 제안하는 얼굴에 특화된 증강 기법을 활용한 학습은 마스크 착용 여부와 관계없이 얼굴 자세 추정 벤치마크 데이터 세트인 BIWI에서 강인한 성능을 보이며, 특정 모델에 국한되지 않기 때문에 다양한 얼굴 자세 추정 모델에 적용될 수 있다.

• 대한전자공학회논문지SP
• /
• 제40권6호
• /
• pp.31-40
• /
• 2003

대부분의 얼굴인식 시스템은 현재 2차원 영상을 기반으로 많은 분야에 응용되고 있다. 그러나 2차원 얼굴인식 시스템은 심하게 변화된 얼굴 포즈에 강인한 얼굴인식이 매우 어렵다. 이에 얼굴 포즈 추정은 정면 영상이 아닐 경우 인식률 향상을 위한 필수적인 과정이라 할 수 있다. 그러므로, 본 논문은 3차원 얼굴인식을 위한 새로운 얼굴 포즈 추정 방식을 제안한다 먼저 3차원 거리(range) 영상이 입력될 때 얼굴 곡선에 기반한 자동 얼굴 특징점 추출 기법을 적용한다. 추출된 특징점을 바탕으로 오류 보상 특이치 분해를 적용 한 새로운 3차원 얼굴 포즈 추정 방식을 제안한다. 특이치 분해를 이용하여 초기 회전각을 획득한 후 존재하는 오류를 보다 세밀하게 보상한다. 제안 알고리즘은 정규화된 3차원 얼굴 공간에서 추출된 특징점의 기하학적 위치를 이용하여 수행된다. 또한 3차원 얼굴인식을 위하여 3차원 최근접 이웃 분류기를 이용한 데이터베이스내에서 후보 얼굴을 선택하는 방식을 제안한다. 실험 결과를 통해 다양한 얼굴 포즈에 대하여 제안 알고리즘의 효율성과 타당성을 검증하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.421-424
• /
• 1999

Automatic human face detection in a complex background is one of the difficult problems In this paper. we propose an effective automatic face detection system that can locate the face region in natural scene images when the system is used as a pre-processor of a face recog- nition system. We use two natural and powerful visual cues, the color and the human head shape. The outline of the human head can be generally described as being roughly elliptic in nature. In the first step of the proposed system, we have tried the approach of fitting the best Possible ellipse to the outline of the head In the next step, the method based on the human skin color space by selecting flesh tone regions in color images and histogramming their r(＝R/(R＋G＋B)) and g(＝G/R＋G＋B)) values. According to our experiment. the proposed system shows robust location results

• 스마트미디어저널
• /
• 제7권4호
• /
• pp.61-69
• /
• 2018

Multi-tracking of general objects and specific faces is an important topic in the field of computer vision applicable to many branches of industry such as biometrics, security, etc. The rapid development of deep neural networks has resulted in a dramatic improvement in face recognition and object detection problems, which helps improve the multiple-face tracking techniques exploiting the tracking-by-detection method. Our proposed method uses face detection trained with a head dataset to resolve the face deformation problem in the tracking process. Further, we use robust face features extracted from the deep face recognition network to match the tracklets with tracking faces using Hungarian matching method. We achieved promising results regarding the usage of deep face features and head detection in a face tracking benchmark.

• 로봇학회논문지
• /
• 제5권2호
• /
• pp.152-159
• /
• 2010

Finding a head of a person in a scene is very important for taking a well composed picture by a robot photographer because it depends on the position of the head. So in this paper, we propose a robust head tracking algorithm using a hybrid of an omega shape tracker and local binary pattern (LBP) AdaBoost face detector for the robot photographer to take a fine picture automatically. Face detection algorithms have good performance in terms of finding frontal faces, but it is not the same for rotated faces. In addition, when the face is occluded by a hat or hands, it has a hard time finding the face. In order to solve this problem, the omega shape tracker based on active shape model (ASM) is presented. The omega shape tracker is robust to occlusion and illuminationchange. However, whenthe environment is dynamic,such as when people move fast and when there is a complex background, its performance is unsatisfactory. Therefore, a method combining the face detection algorithm and the omega shape tracker by probabilistic method using histograms of oriented gradient (HOG) descriptor is proposed in this paper, in order to robustly find human head. A robot photographer was also implemented to abide by the 'rule of thirds' and to take photos when people smile.

• 산업공학
• /
• 제15권2호
• /
• pp.199-208
• /
• 2002

This study was performed to measure the various dimensions of the head and face for Korean adults. Three hundred and eighteen males and two hundred and sixty females, age ranged 18 to 60, participated for this study. Thirty-six dimensions were selected to measure. Subjects were divided into three age groups - 18 to 29, 30 to 39, and 40 to 60 - for each sex. The data were analyzed ta see the differences between the age groups and sex using SAS program. Also, the results of this study were compared to the data of Japanese and US. army. The results showed that the 'ear length', 'bigonial breadth' and 'bitragion submandibular arc' increased as the age increased(p<0.01). However, not much of differences were shown between the age groups in most of other dimensions. Males were significantly bigger than females in every dimensions. The comparison between Korea and Japanese showed significant differences in many dimensions. Due to this reason, it is considered that more caution has to be exercised in using Japanese data for the Korean. The Americans showed to be significantly bigger than Korean in most dimensions. It showed that Koreans have more roundish face and wider nose ridge than Americans. The results of this study can be used to design the products that related to the head and face.