• 대한한의학회지
• /
• 제36권3호
• /
• pp.98-110
• /
• 2015

Objectives: The purpose of this study was to analyze the medical cost of facial paralysis in payer perspective and to estimate the practice pattern of patient using 2011 Health Insurance Review & Assessment Service-National Patients Sample(HIRA-NPS). Methods: Basic statistical system was used for descriptive analysis of NPS dataset. A table for general information (table20) was extracted by disease code, and social demographic characteristics, distribution of the use among inpatients and outpatients, utilization of each kind of medical care institutions, medical cost were analyzed. Subgroup analysis was conducted for assuming the practice pattern of korean medicine and western medicine. Results: A total of 8,219 people and 64,345 claims data were identified as having facial paralysis. Proportion of outpatient was 95.23%, inpatient 0.84% and patient using both services 3.93%. Mean patient charges was 44,229 won per outpatient, 178,886 won per inpatient and 523,542 won per patient using both services. Utilization of korean medical care institutions was 68.81%(claims), 40.46%(patients), utilization of western medical care institutions was 31.19%(claims), 59.54%(patients). The amount charged by korean medical care institutions was 52.61% and western medical care institutions was 47.39%. Cost per claim was higher than those of the korean treatment and cost per patient of western treatment was lower than those of the korean treatment. Conclusions: The research assessed the medical cost and practice pattern associated with facial paralysis. These findings could be used in health care policy and subsequent studies.

• 한국컴퓨터정보학회논문지
• /
• 제15권4호
• /
• pp.47-55
• /
• 2010

본 논문은 실시간 카메라 영상으로부터 얼굴을 검출하고 얼굴 표정을 인식하여 웃음 치료훈련을 할 수 있는 시스템을 제안한다. 제안된 시스템은 카메라 영상으로부터 Haar-like 특징을 이용하여 얼굴 후보 영역을 검출한 다음, SVM분류기를 이용하여 얼굴 후보 영역이 얼굴 영상인지 아닌지를 검증한다. 그 다음에는 검출된 얼굴 영상에 대해, 조명의 영향을 최소화하기 위한 방법으로 히스토그램 매칭을 이용한 조명 정규화를 수행한다. 표정 인식 단계에서는 PCA를 사용하여 얼굴 특징 벡터를 획득한 후 다층퍼셉트론 인공신경망을 이용해 실시간으로 웃음표정을 인식하였다. 본 논문에서 개발된 시스템은 실시간으로 사용자의 웃음 표정을 인식하여 웃음 양을 화면에 표시해 줌으로써 사용자 스스로 웃음 훈련을 할 수 있게 해 준다. 실험 결과에 따르면, 본 논문에서 제안한 방법은 SVM 분류기를 통한 얼굴 후보 영역 검증과 히스토그램 매칭을 이용한 조명정규화를 이용하여 웃음 표정 인식률을 향상시켰다.

• Annals of Clinical Neurophysiology
• /
• 제9권1호
• /
• pp.5-10
• /
• 2007

Background: Bell's palsy (BP) is a self-limited rapid onset facial palsy that is non-life-threatening and has a generally favorable prognosis. Facial paralysis can be caused by numerous conditions, all of which should be excluded before the diagnosis of BP is reached. The etiopathogenesis and clinical course of BP are uncertain. So we analyzed the epidemiology and clinical course of BP patients. Methods: The subjects include 100 cases of BP examined during the period of 18 months. Careful clinical history, neurologic examinations, laboratory tests, electrophysiologic studies, and brain imaging were performed. Follow-up examinations were done once a week during the first month and subsequently once a month until normal function was restored or for up to 3 months. Facial nerve function was assessed by House-Brackman (HB) facial nerve grading scale and electrophysiologic studies. Results: Except 13 recurrent BP patients, we analyzed 87 BP patients. Forty-four (50.6%) were men and 43(49.4%) were women and the mean age was 51.0(${\pm}16.6$) years. Three (3.4%) patients showed a familial tendency. The initial examination within 1 week after attack revealed 35.2% was below HB grade 4 and 64.8% was above grade 3. The associated symptoms are as follows; postauricular pain, increase tear flow, taste change, hyperacusis and drooling. The initial facial nerve conduction study and blink reflex within 1 week after attack showed abnormal findings in 12.6% and 100%, respectively. Brain MRI was performed in 59(67.8%) patients and showed abnormal enhancement of affected nerve in 57(96.6%). Follow-up examination showed that 78.2% of the patients partially improved within 4 weeks and completely improved within 3 months. Finally 80.5% of the total patients obtained normal function in 3 months. Conclusions: We report epidemiologic, clinical, electrophysiologic and radiologic characteristics of BP patients.

• 한국산학기술학회논문지
• /
• 제15권5호
• /
• pp.2671-2677
• /
• 2014

현대인들은 매운 음식을 선호하며 매운 음식을 섭취함으로써 스트레스 해소를 위해 매운맛을 찾는 사람들이 증가하고 있다. 그러나, 매운 음식을 먹었을 경우, 사람마다 차이는 있지만 얼굴색이 빨갛게 변하는 것을 시각적으로 확인할 수 있다. 따라서 본 논문에서는 매운 음식을 섭취했을 경우, 사상체질에 따라 얼굴 영역별 색상 변화를 측정하고 이를 비교, 분석하는 실험을 수행하였다. 이를 위해 체질감별 설문 검사지를 통해 사상체질별로 피실험자 집단을 구성하고 대표적인 매운 음식인 청양고추 1개씩 섭취하기 전과 후의 얼굴 영상을 기반으로 Lab색 체계를 적용한 영상신호분석 실험을 통해 사상체질별 매운 음식과 얼굴 색상과의 상관성 분석 연구를 수행하였다.

• 한국멀티미디어학회논문지
• /
• 제23권12호
• /
• pp.1464-1475
• /
• 2020

Due to the spread of COVID-19, the online lecture has become more prevalent. However, it was found that a lot of students and professors are experiencing lack of communication. This study is therefore designed to improve interactive communication between professors and students in real-time online lectures. To do so, we explore deep learning approaches for automatic recognition of students' facial expressions and classification of their understanding into 3 classes (Understand / Neutral / Not Understand). We use 'BlazeFace' model for face detection and 'ResNet-GRU' model for facial expression recognition (FER). We name this entire process 'Degree of Understanding (DoU)' algorithm. DoU algorithm can analyze a multitude of students collectively and present the result in visualized statistics. To our knowledge, this study has great significance in that this is the first study offers the statistics of understanding in lectures using FER. As a result, the algorithm achieved rapid speed of 0.098sec/frame with high accuracy of 94.3% in CPU environment, demonstrating the potential to be applied to real-time online lectures. DoU Algorithm can be extended to various fields where facial expressions play important roles in communications such as interactions with hearing impaired people.

• 전기전자학회논문지
• /
• 제26권3호
• /
• pp.430-436
• /
• 2022

본 논문에서는 다중 체온 감지용 지능형 카메라를 제안한다. 제안하는 카메라는 광학(4056*3040) 및 열화상(640*480) 2종의 카메라로 구성되고 획득된 영상으로부터 사람의 표정 및 체온을 분석하여 이상 증상을 감지한다. 광학 및 열화상카메라는 동시에 운영되며 광학 영상에서 객체를 검출한 후 얼굴영역을 도출하여 표정분석을 수행한다. 열화상카메라는 광학카메라에서 얼굴영역으로 판단한 좌표 값을 적용하고 해당영역의 최고 온도를 측정하여 화면에 표출한다. 이상 징후 감지는 분석된 표정 3가지(무표정, 웃음, 슬픔)와 체온 값을 활용하여 판단하며 제안된 장비의 성능을 평가하기 위해 광학영상 처리부는 Caltech, WIDER FACE, CK+ 데이터셋을 3종의 영상처리 알고리즘(객체검출, 얼굴영역 검출, 표정분석)에 적용하였다. 실험결과로 객체검출률, 얼굴영역 검출률, 표정분석률 각각 91%, 91%, 84%을 도출하였다.

• 대한치과교정학회지
• /
• 제11권2호
• /
• pp.85-100
• /
• 1981

Serial lateral cephalometric radiographs of 40 Korean children(25 males, 15 females) ranging in age from 6 to 13 years were studied by means of computer morphometrics and statistical analysis. As a result of this study, the following conclusions can be made: 1. In both sexes, the mean growth patterns of the face were very stable and the growth directions of the face were more prominent both forward and down-ward away from the cranial base(S-N). 2. In the mandible, the rotation and the 'wave-like' manner of migration were observed. 3. The size of the lateral faces in males was larger than females at 6 and 13 years of age, and the forms of the lateral faces in males were slightly more squares than females at 13 years of age. 4. The sex differences and practical means in the growth increments and growth rates during 7 years of the growth period were as follows: (1) In the total face, there was a significant sex difference in the growth increments(males $26.21cm^2$, females $23.24cm^2$) and growth rates(males $42.02\%$, females $39.28\%$). (2) In the facial surface 1, there was a significant sex difference in the growth increments(males $21.30cm^2$, females $19.19cm^2$) but there was no significant sex difference in the growth rates(males $41.35\%$, females $39.10\%$). (3) In the anterior total facial height(N-Ne), there was no significant sex difference in the growth increments(males 18.23mm, females 17.45mm) and the growth rates(males $18.44\%$, females $18.19\%$). (4) In the posterior total facial height(S-Go), there was a significant sex difference in the growth increments(males 14.61mm, females 12.98mm) but there was no significant sex difference in the growth rates(males $23.78\%$, females $22.25\%$). 5. The percentages of anterior upper facial height to anterior total facial height in both sexes were very stable in spite of the age increase. 6. The percentage of total facial height to standing height was reduced by the age increase, and the reduced rate of anterior total facial height(males $13.26\%$, females $13.75\%$) was larger than the posterior total facial height(males $9.95\%$, females $11.70\%$). 7. The correlations of lateral facial surfaces to the standing height and the weight were higher in males than females, but the level of correlation in males was in the moderate range.

• Journal of Acupuncture Research
• /
• 제24권4호
• /
• pp.209-223
• /
• 2007

Objectives : Facial Nerve Paralysis is one kind of common diseases and it can be treated by natural therapy and the efficiency of treatment is relatively high. In clinical trial, it is not difficult to find patients who were not completely recovered from Facial Nerve Paralysis, so the symptoms are fixed permanently. This leads many doctors and patients to have interests in the progress and prognosis of the disease, so this study was to analyze clinical prognosis factors and verify the effects of Electrodiagnostic Test. Methods : The 378 subjects were chosen from 987 patients who were suffering from Peripheral Facial Palsy, diagnosed with Bell's palsy and Ramsay Hunt Syndrome and had admission treatment. They got Oriental-Western Medicine Treatment within two weeks after outbreaks of the disease and treated at least over 3 weeks using Oriental-Western Medicine Treatment. Results : 1. There was a significant difference in the results of treatment according to gender, age, types of Facial Palsy, existence of Post Auricular Pain, existence of Labyrinth Symptom, HBGS, and existence of onsets of recovery as clinical prognosis factors of Peripheral Facial Palsy, However, a statistically significant difference was not shown in the results of treatment according to the position of Facial Palsy(left or right), existence of a relapse, and diabetes, hypertension. 2. As a result of overall treatment, 77.2% of patients were recovered almost entirely and 22.8% were not, and the quelae of incomplete recovery were Synkinesis, facial contracture, facial spasm, crocodile tears and scheroma in order of frequency. 3. The results of electrodiagnostic test represented useful correlation to predict the final effects of treatment. Conclusion : Based on the above results, the prognosis factors, the degree of recovery, and the sequelae of incomplete recovery were analysed and the effects of electrodiagnostic test was verified.

• 대한치과교정학회지
• /
• 제31권3호
• /
• pp.301-309
• /
• 2001

교정치료를 받고자 하는 많은 사람들이 관심을 갖는 중요한 동기중의 하나가 미적 안모의 추구이기 때문에, 미적 안모를 평가하는 기준이 성별이나 환자가 속해있는 문화권에 따라서 달라진다면, 이에 대한 정확한 이해가 치료목표의 설정에 있어서 중요한 역할을 한다고 할 수 있다. 본 연구에서는 성별이나 문화가 매력적인 측모를 판단하는데 영향력을 발휘하는지를 알아보기 위해 4개의 평가 군으로 하여금 133명의 일반인 사진 중에서 좋은 측모를 가진 사람의 사진을 채점방식에 의해 선택하게 하였고, 좋은 측모 군을 평가하는 경향이나 평가점수의 차이를 이용하여, 4평가 군 사이에 좋은 측모를 선정하는데 있어서 차이가 있는지를 Bonferroni's multiple comparison과 randomized block designed ANOVA를 통하여 통계적으로 검증하였다. 4개의 평가 군은 한국에 거주하는 10명의 20대 남자 군과 10명의 20대 여자 군, 10명의 20대 재미한국인 남자 군, 그리고 10명의 20대 재미한국인 여자 군으로 구성되었으며, 선택된 좋은 안모 군의 연조직 형태는 두부방사선 사진의 투사도를 사용하여 선계측, 각계측, 그리고 비율계측을 함으로써 비교 분석하였고, 이를 통해서 다음의 결과를 얻었다. 1. 심미적인 측모를 판별하는데 있어서의 개인적인 차이 여부를 통계적으로 입증한 결과, 아름다움에 대한 개념이 지극히 주관적이라는 통념과 일치하는 것으로 사료 된다. 2. 동일한 문화권에 살고있는 한국인에서, 성별의 차이는 심미적 측모의 평가에 영향을 주지 않았다. 3. 다른 문화권에서 생활하는 같은 민족적 동질성을 가진 두 집단의 한국인간에 심미적 측모를 선택하는데 서로 다른 양상을 보였으며, 이는 미의 기준을 설정하는 데에 있어서 문화가 더 큰 변수임을 입증하고 있다. 4. 좋은 안모 군과 좋지 않은 안모 군에서의 연조직 분석에서 하안면부 수직 고경의 비율, 안면 돌출도 및 상하순의 전후방적 위치 관계에서 특징적인 차이를 나타내었다.

• 한국멀티미디어학회논문지
• /
• 제25권2호
• /
• pp.215-220
• /
• 2022

Emotion recognition is one of the most important and challenging areas of computer vision. Nowadays, many studies on emotion recognition were conducted and the performance of models is also improving. but, more research is needed on emotion recognition and sentiment analysis of video viewers. In this paper, we propose an emotion analysis system the includes a sentiment analysis model and an interest prediction model. We analyzed the emotional patterns of people watching popular and unpopular videos and predicted the level of interest using the emotion analysis system. Experimental results showed that certain emotions were strongly related to the popularity of videos and the interest prediction model had high accuracy in predicting the level of interest.