• 한국의류산업학회지
• /
• 제22권6호
• /
• pp.826-833
• /
• 2020

When it is necessary to wear masks for long periods, such as during the current COVID-19 pandemic, the essential function of masks to prevent contamination (or transmission to others) as well as comfortableness are important. For this study, we used three-dimensional (3D) facial measurements of adult women to compile basic face shape data for designing comfortable and effective masks. This study analyzed the 3D facial data of 127 subjects in their 20s to 30s of the 6th Size Korea. Factor analysis of the survey data produced seven factors that formed the composition of adult female faces. These factors combined to produce three facial types: square (long face and a large lower middle face), oval (smallest central and lower body in the middle), and triangle (short face with a small central and lower large nose). These types reflect that the facial types of adult women show the differences in the nose angle, nose length, bitragion-subnasal arc, bitragion-menton arc. Therefore, properly fitting masks for fine dust particle filtration require 3D customization of a mask's breathing apparatus to fit differently shaped central and lower face parts that interfere with mask fit.

• 한국정보시스템학회지:정보시스템연구
• /
• 제32권2호
• /
• pp.87-108
• /
• 2023

Purpose The main purpose of this study is to improve fake news detection performance by using video information to overcome the limitations of extant text- and image-oriented studies that do not reflect the latest news consumption trend. Design/methodology/approach This study collected video clips and related information including news scripts, speakers' facial expression, and video metadata from YouTube to develop fake news detection model. Based on the collected data, seven combinations of related information (i.e. scripts, video metadata, facial expression, scripts and video metadata, scripts and facial expression, and scripts, video metadata, and facial expression) were used as an input for taining and evaluation. The input data was analyzed using six models such as support vector machine and deep neural network. The area under the curve(AUC) was used to evaluate the performance of classification model. Findings The results showed that the ACU and accuracy values of three features combination (scripts, video metadata, and facial expression) were the highest in logistic regression, naïve bayes, and deep neural network models. This result implied that the fake news detection could be improved by using video information(video metadata and facial expression). Sample size of this study was relatively small. The generalizablity of the results would be enhanced with a larger sample size.

• 대한전자공학회논문지SP
• /
• 제39권3호
• /
• pp.23-35
• /
• 2002

시선 위치 추적이란 모니터상에 사용자가 쳐다보고 있는 지점을 파악해 내는 기술이다 이 논문에서는 컴퓨터 비젼 방법을 이용하여 사용자가 모니터 상에 어느 지점을 쳐다보고 있는지를 파악(시선 위치 추적)하는 새로운 방법을 제안한다. 시선위치를 파악하기 위해 본 논문에서는 얼굴 영역 및 얼굴 특징점(양 눈, 양 콧구멍, 입술 끝점 등)을 2차원 카메라 영상으로부터 추출하였으며, 이들의 움직임으로부터 카메라 보정 및 매개변수 추정 방법등을 이용하여 초기 3차원 위치를 추정해 내었다. 이후 모니터 상의 한 지점을 쳐다보기 위해 사용자가 얼굴을 움직이는 경우 이러한 얼굴의 3차원 움직임 량 역시 자동으로 추정하였다. 이로부터 변화된 얼굴 특징점의 3차원 위치를 계산해 낼 수 있었으며, 이를 바탕으로 모니터 상의 시선 위치를 구하였다. 실험 결과, 19인치 모니터상의 임의의 지점을 사용자가 쳐다보았을 때, 약 2.01인치의 시선 위치에러 성능을 얻었다.

• 한국콘텐츠학회논문지
• /
• 제13권1호
• /
• pp.1-8
• /
• 2013

얼굴 영상 데이터베이스에서 제공하는 눈 좌표에 의존해서 부분 자동 얼굴 인식 알고리즘을 설계 구현하면 실 환경 얼굴 인식 시스템에서는 눈 좌표 추출 알고리즘의 정확도에 따라 인식 성능이 달라질 수 있다. 본 논문에서는 얼굴의 눈, 코, 입 및 윤곽선 정보를 바탕으로 설정한 특징점 기반의 얼굴 모델 그래프를 생성하여 얼굴 영상에 정합시키고 각 특징점에서 Gabor 및 LBP 피쳐를 추출해서 결합하는 방식의 완전 자동 얼굴 인식 알고리즘을 제안하였다. 본 알고리즘에서는 완전 자동으로 얼굴 영상에 얼굴 모델 그래프를 맞출 뿐만 아니라 기존의 Gabor 피쳐에 LBP 피쳐를 추가함으로써 인식 성능을 극대화 시킬 수 있도록 하였다. 제안한 알고리즘을 FERET 데이터베이스에 적용해 본 결과 1,000명 이상의 얼굴을 실시간으로 인식할 수 있었고 각 데이터 집합에 대해서 우수한 인식 성능을 얻을 수 있었다.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.1019-1029
• /
• 2020

In this paper, we propose a novel knowledge distillation algorithm to create an compressed deep ensemble network coupled with the combined use of local and global features of face images. In order to transfer the capability of high-level recognition performances of the ensemble deep networks to a single deep network, the probability for class prediction, which is the softmax output of the ensemble network, is used as soft target for training a single deep network. By applying the knowledge distillation algorithm, the local feature informations obtained by training the deep ensemble network using facial subregions of the face image as input are transmitted to a single deep network to create a so-called compressed ensemble DCNN. The experimental results demonstrate that our proposed compressed ensemble deep network can maintain the recognition performance of the complex ensemble deep networks and is superior to the recognition performance of a single deep network. In addition, our proposed method can significantly reduce the storage(memory) space and execution time, compared to the conventional ensemble deep networks developed for face recognition.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권6호
• /
• pp.1981-1995
• /
• 2021

When a person tries to conceal emotions, real emotions will manifest themselves in the form of micro-expressions. Research on facial micro-expression recognition is still extremely challenging in the field of pattern recognition. This is because it is difficult to implement the best feature extraction method to cope with micro-expressions with small changes and short duration. Most methods are based on hand-crafted features to extract subtle facial movements. In this study, we introduce a method that incorporates optical flow and deep learning. First, we take out the onset frame and the apex frame from each video sequence. Then, the motion features between these two frames are extracted using the optical flow method. Finally, the features are inputted into an improved MobileNetV2 model, where SVM is applied to classify expressions. In order to evaluate the effectiveness of the method, we conduct experiments on the public spontaneous micro-expression database CASME II. Under the condition of applying the leave-one-subject-out cross-validation method, the recognition accuracy rate reaches 53.01%, and the F-score reaches 0.5231. The results show that the proposed method can significantly improve the micro-expression recognition performance.

• 대한치과교정학회지
• /
• 제22권3호
• /
• pp.657-673
• /
• 1992

Orthodontic treatment of cleft patients is difficult as the growth is different from that of normal ones. So it is very important to know the characteristic features of the craniofacial morphology and growth pattern in unilateral cleft lip and palate patients. The materials for this study consisted of 55 normal males and 50 unilateral cleft lip and palate ones who received cheiloplasty and palatoplasty previously. The cleft subjects were divided into 4 groups according to their ages kto find out the growth pattern of hard and soft tissue, and to compare the features with those of normal ones. Each cephalogram analysed by McNamara method and others. The obtained results were as follows 1. In the unilateral cleft lip and palate subjects, forward growth of the maxilla was smaller than that of normal ones from 9 years old. So the maxilla was retruded. The maxillary incisors were severely retruded in all age groups. 2. The mandibular overall length and its anteroposterior position did not show any significant differences between two groups. But the height of ramus was very short and the mandible had vertical growth tendency to compensate for undergrowth of the maxilla in cleft subjects after 12 years of age. 3. Horizontal growth of the soft tissue in middle face was smaller than that of any other facial region from 9 years old. The vertical growth rate of upper lip was decreased as growing old. 4. In cleft subjects, the upper and lower facial component angle and the facial convexity angle were large. So their facial profile changed to straight or concave as growing old.

• 대한두개안면성형외과학회지
• /
• 제25권2호
• /
• pp.77-84
• /
• 2024

Background: The facial artery is an important blood vessel responsible for supplying the anterior face. Understanding the branching patterns of the facial artery plays a crucial role in various medical specialties such as plastic surgery, dermatology, and oncology. This knowledge contributes to improving the success rate of facial reconstruction and aesthetic procedures. However, debate continues regarding the classification of facial artery branching patterns in the existing literature. Methods: We conducted a comprehensive anatomical study, in which we dissected 102 facial arteries from 52 embalmed and formaldehyde-fixed Vietnamese cadavers at the Anatomy Department, University of Medicine and Pharmacy, Ho Chi Minh City, Vietnam. Results: Our investigation revealed eight distinct termination points and identified 35 combinations of branching patterns, including seven arterial branching patterns. These termination points included the inferior labial artery, superior labial artery, inferior alar artery, lateral nasal artery, angular artery typical, angular artery running along the lower border of the orbicularis oculi muscle, forehead branch, duplex, and short course (hypoplastic). Notably, the branching patterns of the facial artery displayed marked asymmetry between the left and right sides within the same cadaver. Conclusion: The considerable variation observed in the branching pattern and termination points of the facial artery makes it challenging to establish a definitive classification system for this vessel. Therefore, it is imperative to develop an anatomical map summarizing the major measurements and geometric features of the facial artery. Surgeons and medical professionals involved in facial surgery and procedures must consider the detailed anatomy and relative positioning of the facial artery to minimize the risk of unexpected complications.

• Journal of Dental Anesthesia and Pain Medicine
• /
• 제15권1호
• /
• pp.35-37
• /
• 2015

Atypical facial pain (AFP) is a type of facial pain which does not fulfill any other diagnosis. It has several features such as no objective signs, no obvious explanation of the cause and poor response to treatments. We report a case of a female patient with AFP on the left maxillary area. The pain was increased by cold innocuous stimulation and thermography showed that the temperature on the painful area was significantly decreased. The pain was successfully alleviated by stellate ganglion block (SGB). Therefore, SGB can be effectively used to treat AFP.

• 한국멀티미디어학회논문지
• /
• 제4권1호
• /
• pp.67-74
• /
• 2001

본 논문에서는 컬러 정지 영상에서 색상과 모양 정보를 이용한 얼굴 영역 검출 알고리즘을 제안한다. 제안된 알고리즘은 YCbCr 색공간에서 Cb와 Cr성분만을 이용하여 조명의 영향을 줄일 수 있다. 피부색 분할을 한후 얼굴 후보 영역들의 잡음 제거와 단순화를 위해 형태학적 필터와 기하학적 교정을 거친다. 입력 영상 내에 여러 사람이 존재할 경우에도 레이블링을 통해 각각의 얼굴 후보 영역들로 분리할 수 있고, 또한 2차 모멘트를 기반으로 한 타원 특징들을 추출하여 기울어진 얼굴 영역들도 성공적으로 검출할 수 있다.