• Journal of Information Science Theory and Practice
• /
• 제7권2호
• /
• pp.32-39
• /
• 2019

A convolutional neural network (CNN) has been widely used in facial expression recognition (FER) because it can automatically learn discriminative appearance features from an expression image. To make full use of its discriminating capability, this paper suggests a simple but effective method for CNN based FER. Specifically, instead of an original expression image that contains facial appearance only, the expression image with facial geometry visualization is used as input to CNN. In this way, geometric and appearance features could be simultaneously learned, making CNN more discriminative for FER. A simple CNN extension is also presented in this paper, aiming to utilize geometric expression change derived from an expression image sequence. Experimental results on two public datasets (CK+ and MMI) show that CNN using facial geometry visualization clearly outperforms the conventional CNN using facial appearance only.

• Journal of Genetic Medicine
• /
• 제10권1호
• /
• pp.57-61
• /
• 2013

Acromegaloid Facial Appearance syndrome is a very rare syndrome combining acromegaloid-like facial appearance, thickened lips and oral mucosa and acral enlargement. Progressive facial dysmorphism is characterized by a coarse facies, a long bulbous nose, high-arched eyebrows, and thickening of the lips, oral mucosa leading to exaggerated rugae and frenula, furrowed tongue and narrow palpebral fissures. We report a case of acromegaloid facial appearance syndrome in a 19-year-old male patient who presented with all the characteristic features of the syndrome along with previously unreported anomalies like dystrophic nails, postaxial polydactyly and incisal notching of teeth.

• Archives of Plastic Surgery
• /
• 제40권6호
• /
• pp.715-720
• /
• 2013

Background Many people have an interest in the correction of facial scars or deformities caused by trauma. The increasing ability to correct such flaws has been one of the reasons for the increase in the popularity of facial plastic surgery. In addition to its roles in communication, breathing, eating, olfaction and vision, the appearance of the face also plays an important role in human interactions, including during social activities. However, studies on the importance of the functional role of facial appearance. As a function of the face are scare. Therefore, in the present study, we evaluated the importance of the functions of the face in Korea. Methods We conducted an online panel survey of 300 participants (age range, 20-70 years). Each respondent was administered the demographic data form, Facial Function Assessment Scale, Rosenberg Self-Esteem Scale, and standard gamble questionnaires. Results In the evaluation on the importance of facial functions, a normal appearance was considered as important as communication, breathing, speech, and vision. Of the 300 participants, 85% stated that a normal appearance is important in social activities. Conclusions The results of this survey involving a cross-section of the Korean population indicated that a normal appearance was considered one of the principal facial functions. A normal appearance was considered more important than the functions of olfaction and expression. Moreover, a normal appearance was determined to be an important facial function for leading a normal life in Korea.

• 반도체디스플레이기술학회지
• /
• 제18권1호
• /
• pp.97-101
• /
• 2019

Understanding and classification of the human's emotion play an important tasks in interacting with human and machine communication systems. This paper proposes a novel emotion recognition method by extracting facial keypoints, which is able to understand and classify the human emotion, using active Appearance Model and the proposed classification model of the facial features. The existing appearance model scheme takes an expression of variations, which is calculated by the proposed classification model according to the change of human facial expression. The proposed method classifies four basic emotions (normal, happy, sad and angry). To evaluate the performance of the proposed method, we assess the ratio of success with common datasets, and we achieve the best 93% accuracy, average 82.2% in facial emotion recognition. The results show that the proposed method effectively performed well over the emotion recognition, compared to the existing schemes.

• 한국전자통신학회논문지
• /
• 제8권8호
• /
• pp.1201-1206
• /
• 2013

영상에서 얼굴 및 얼굴 특징을 추출하기 위한 기법으로 active appearance model(AAM)이 있다. 본 논문에서는 두 개의 AAM을 이용하여 얼굴 특징을 추출하는 multiple active appearance model(MAAM) 기법을 제안한다. 두 개의 AAM은 학습 데이터에 대한 파라미터를 조절하여 상반되는 장단점을 가지도록 생성하고, 서로의 단점을 보완할 수 있도록 한다. 제안된 방법의 성능을 평가하기 위해 100장의 영상에 대해서 얼굴 특징추출 실험을 하였다. 실험 결과 기존의 AAM 하나만을 사용하는 기법에 비해 적은 횟수의 피팅만으로도 정확도 높은 결과를 얻을 수 있었다.

• 로봇학회논문지
• /
• 제8권2호
• /
• pp.104-115
• /
• 2013

For natural human-robot interaction, we need to know location and shape of facial feature in real environment. In order to track facial feature robustly, we can use the method combining particle filter and active appearance model. However, processing speed of this method is too slow. In this paper, we propose two ideas to improve efficiency of this method. The first idea is changing the number of particles situationally. And the second idea is switching the prediction model situationally. Experimental results is presented to show that the proposed method is about three times faster than the method combining particle filter and active appearance model, whereas the performance of the proposed method is maintained.

• 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.

• 대한전자공학회논문지SP
• /
• 제47권3호
• /
• pp.54-60
• /
• 2010

얼굴 인식 방법 중에 한 얼굴 영상을 분할하여 분할한 각 부분마다 통계적 방법을 적용해 특징추출을 수행한 다음 각 부분마다 분류를 수행하고 이러한 분류결과를 모아서 voting등의 방법으로 얼굴 인식을 수행 하는 방법을 국부 외형 기반 방법(local appearance-based method) 이라고 한다. 기존에 제안된 국부 외형 기반 얼굴 인식은 얼굴 영상을 일정한 크기로 단순분할하고, 그 부분들을 모두 인식에 사용한다. 본고에서는 인식에 상대적으로 중요한 부분만을 사용하여 얼굴 인식을 수행하는 새로운 국부 외형 기반 얼굴 인식 방법을 제안한다. 본고에서는 단순 분할 방법 대신에 눈, 코, 입 등 인물 간의 차이가 잘 나타나는 얼굴 부분들을 support vector machine (SVM) 을 이용하여 검출한 후, 검출한 각 부분에 주성분 분석 (PCA) 을 적용하고 이를 통합하여 얼굴 인식을 수행하였다. 실험을 통해 제안한 방법과 기존 방법의 성능을 비교한 결과, 제안한 방법이 기존의 국부 외형 기반 방법의 장점을 지니는 동시에 성능을 개선시킴을 확인하였다.

• 대한치과교정학회지
• /
• 제45권5호
• /
• pp.253-260
• /
• 2015

Objective: The aim of this study was to evaluate the facial dimensions of young adult women with a preferred facial appearance and compare the results with those from the general population. Methods: Twenty-five linear, nine angular, and three area measurements were made and four ratios were calculated using a sample of standardized frontal and lateral photographs of 46 young adult women with a preferred facial appearance (Miss Korea group) and 44 young adult women from the general population (control group). Differences between the two groups were analyzed using multivariate analysis of variance (MANOVA). Results: Compared with the control group, the Miss Korea group exhibited a significantly greater facial height, total facial height (TFH; trichion-menton), facial width (tragus right-tragus left), facial depth (tragus-true vertical line), and trichion-nasion/TFH ratio and smaller subnasale-menton/TFH and facial width/TFH ratios. Furthermore, the control group had smaller intercanthal and interpupillary widths. Conclusions: The Miss Korea group exhibited longer, wider, and deeper faces compared with those from the general population. Furthermore, the Miss Korea group had larger eyes, longer but less protruded noses, longer and more retruded lower lips and chins, larger lip vermilion areas, and smaller labiomental angles. These results suggest that the latest trends in facial esthetics should be considered during diagnosis and treatment planning for young women with dentofacial abnormalities.

• 한국멀티미디어학회논문지
• /
• 제17권9호
• /
• pp.1076-1083
• /
• 2014

We propose an emotional facial avatar that portrays the user's facial expressions with an emotional emphasis, while achieving visual and behavioral realism. This is achieved by unifying automatic analysis of facial expressions and animation of realistic 3D faces with details such as facial hair and hairstyles. To augment facial appearance according to the user's emotions, we use emotional templates representing typical emotions in an artistic way, which can be easily combined with the skin texture of the 3D face at runtime. Hence, our interface gives the user vision-based control over facial animation of the emotional avatar, easily changing its moods.