• 대한한의학회지
• /
• 제44권4호
• /
• pp.136-149
• /
• 2023

Objectives: Facial diagnosis is an important part of clinical diagnosis in traditional East Asian Medicine. In this paper, we proposed a model to quantitatively classify cold sensitivity using a fully automated facial image analysis system. Methods: We investigated cold sensitivity in 452 subjects. Cold sensitivity was determined using a questionnaire and the Cold Pattern Score (CPS) was used for analysis. Subjects with a CPS score below the first quartile (low CPS group) belonged to the cold non-sensitivity group, and subjects with a CPS score above the third quartile (high CPS group) belonged to the cold sensitivity group. After splitting the facial images into train/validation/test sets, the train and validation set were input into a convolutional neural network to learn the model, and then the classification accuracy was calculated for the test set. Results: The classification accuracy of the low CPS group and high CPS group using facial images in all subjects was 76.17%. The classification accuracy by sex was 69.91% for female and 62.86% for male. It is presumed that the deep learning model used facial color or facial shape to classify the low CPS group and the high CPS group, but it is difficult to specifically determine which feature was more important. Conclusions: The experimental results of this study showed that the low CPS group and the high CPS group can be classified with a modest level of accuracy using only facial images. There was a need to develop more advanced models to increase classification accuracy.

• 대한약침학회지
• /
• 제20권2호
• /
• pp.100-106
• /
• 2017

Objectives: This study aimed to assess a Qi Blood Yin Yang evaluation method systematically and objectively and to identify the correlation between the Qi Blood Yin Yang deficiency pattern (QBYYDP) and facial color. Methods: Thirty-seven participants (17 males, 20 females) were enrolled in this study. Twenty-four (10 males, 14 females) had ages from 40 to over 60, and 13 (7 males and 6 females) were in their twenties. After sufficient rest, facial images were taken with a camera. Based on the results from a questionnaire survey, we divided the participants into five groups: the normal and the Qi-, Blood-, Yin-, and Yang-deficient groups, after which the relationships between the L, 'a', and 'b' values in the Lab color system and the characteristics of the participants in each of the deficient groups were elucidated using a facial color analysis program. Results: The color analysis for Qi-deficient (QD) participants revealed that the L value was fairly decreased in comparison with the normal participants, but the 'a' and 'b' values were almost the same. A comparison between the normal and the Yang-deficient (YaD) groups revealed that the L values were somewhat lower compared to the normal group, but the 'a' and 'b' values were not statistically different. For the Yin-deficient (YiD) group, the L value was slightly lower compared to the normal group, but the 'a' and 'b' values were almost the same and the R values were slightly increased. For the Blood-deficient (BD) group, the L values were slightly increased compared to the normal group, but the 'a' and 'b' values were decreased slightly. Conclusion: This study obtained objective, reliable data for judging the QBYYDP by using facial images and a color analysis program. However, further study with at least 10 or more subjects in each of the deficient groups is necessary to confirm our findings.

• Archives of Plastic Surgery
• /
• 제42권4호
• /
• pp.407-410
• /
• 2015

The aim of this study is to review the protective effect of a bicycle helmet on each facial location systematically. PubMed was searched for articles published before December 12, 2014. The data were summarized, and the odds ratio (OR) between the locations of facial injury was calculated. A statistical analysis was performed with Review Manager (The Nordic Cochrane Centre). Bicycle helmets protect the upper and middle face from serious facial injury but do not protect the lower face. Non-wearers had significantly increased risks of upper facial injury (OR, 2.07; P<0.001) and of middle facial injury (OR, 1.97; P<0.001) as compared to helmet users. In the case of lower facial injury, however, only a slightly increased risk (OR, 1.42; 95% confidence interval (CI), 0.67-3.00, P=0.36) was observed. The abovementioned results can be attributed to the fact that a helmet covers the head and forehead but cannot cover the lower face. However, helmets having a chin cap might decrease the risk of lower facial injury.

• Journal of Acupuncture Research
• /
• 제18권1호
• /
• pp.50-60
• /
• 2001

In order to review the studies related to the facial pain by acupuncture, we have referred to a PubMed site by using MeSH searching word of "facial pain and acupuncture". 12 journals with 20 papers were reported on the facial pain and acupuncture. Among them, 4 papers were appeared in Am J Chin Med, 3 in Acupunct Electrother Res, 2 in Br. Dent J, J Orofac Pain and Swed Dent J respectively, and 1 in 7 journals respectively. According to the classification of the patterns, 15 papers were done by clinical studies, 2 by review and meta-analysis respectively, and 1 by experimental study. TMD was the most disease that related to facial pain and CMD, neurogenic facial pain (trigeminal neuralgia, postherpetic pain), dental pain and MPS were also appeared. Most of the studies didn't mention the acupuncture points, L14 Habkok in 4 papers and ST36 Chogsamni in a paper were only mentioned. Various modalities were applied in the trials such as classical acupuncture, electroacupuncture, TENS, SSP and auricular acupuncture. By the above results, we concluded that various acupuncture techniques are used with effectiveness on the facial pain. It would be needed further research on the acupuncture point specific and therapeutic techniques as well.

• The Korean Journal of Pain
• /
• 제7권1호
• /
• pp.43-48
• /
• 1994

Twenty seven patients with hemifacial spasm were treated by facial nerve block at the foramen stylomastoideum and O'Brien block from January 1992 to March 1994. There were 16 female and ll male patients, a 1.5:1 ratio respectively. Most patients were 40~60 years old. Among the 27 patients treated by nerve blocks, 26 responded well to the facial nerve block, including two cases of O'Brien block. One patient failed to respond to the facial nerve block. Induced facial palsy disappeared within one or two months within the majority of patients. Among the 26 patients who received nerve block, 6 patients required a second block within 3 to 9 months. After successful nerve block, all patients were free of spasm for 1 to 16 months. Although the follow-up period was short in duration, these results suggest that facial nerve block is a satisfactory and reliable method in the treatment of facial spasm.

• ETRI Journal
• /
• 제32권5호
• /
• pp.784-794
• /
• 2010

Automatic facial expression recognition has many potential applications in different areas of human computer interaction. However, they are not yet fully realized due to the lack of an effective facial feature descriptor. In this paper, we present a new appearance-based feature descriptor, the local directional pattern (LDP), to represent facial geometry and analyze its performance in expression recognition. An LDP feature is obtained by computing the edge response values in 8 directions at each pixel and encoding them into an 8 bit binary number using the relative strength of these edge responses. The LDP descriptor, a distribution of LDP codes within an image or image patch, is used to describe each expression image. The effectiveness of dimensionality reduction techniques, such as principal component analysis and AdaBoost, is also analyzed in terms of computational cost saving and classification accuracy. Two well-known machine learning methods, template matching and support vector machine, are used for classification using the Cohn-Kanade and Japanese female facial expression databases. Better classification accuracy shows the superiority of LDP descriptor against other appearance-based feature descriptors.

• 한국컴퓨터그래픽스학회논문지
• /
• 제24권4호
• /
• pp.1-9
• /
• 2018

본 논문은 얼굴의 표정 변화를 통해 감정을 분석하는 방법으로 조현병의 초기 증상을 스스로 인지할 수 있는 감정 트레이닝 프레임워크를 제안한다. 먼저, Microsoft의 Emotion API를 이용하여 캡처된 얼굴 표정의 사진으로부터 감정값을 얻고, 피크 분석 기반 표준편차로 시간에 따라 변화하는 얼굴 표정의 미묘한 차이를 인식해 감정 상태를 각각 분류한다. 그리하여 Ekman이 제안한 여섯 가지 기본 감정 상태에 반하는 감정들의 정서 및 표현능력이 결핍된 부분에 대해 분석하고, 그 값을 이미지 색상 변환 프레임워크에 통합시켜 사용자 스스로 감정의 변화를 쉽게 인지하고 트레이닝 할 수 있도록 하는 것이 최종목적이다.

• 대한두개안면성형외과학회지
• /
• 제15권3호
• /
• pp.109-116
• /
• 2014

Background: Infants with deformational plagiocephaly (DP) usually present with cranial vault deformities as well as facial asymmetry. The purpose of this study was to use three-dimensional anthropometric data to evaluate the influence of cranial deformities on facial asymmetry. Methods: We analyzed three-dimensional computed tomography data for infants with DP (n=48) and without DP (n=30, control). Using 16 landmarks and 3 reference planes, 22 distance parameters and 2 angular parameters were compared. This cephalometric assessment focused on asymmetry of the orbits, nose, ears, maxilla, and mandible. We then assessed the correlation between 23 of the measurements and cranial vault asymmetry (CVA) for statistical significance using relative differences and correlation analysis. Results: With the exception of few orbital asymmetry variables, most measurements indicated that the facial asymmetry was greater in infants with DP. Mandibular and nasal asymmetry was correlated highly with severity of CVA. Shortening of the ipsilateral mandibular body was particularly significant. There was no significant deformity in the maxilla or ear. Conclusion: This study demonstrated that the cranial vault deformity in DP is associated with facial asymmetry. Compared with the control group, the infants with DP were found to have prominent asymmetry of the nose and mandible.

• 전기학회논문지
• /
• 제63권6호
• /
• pp.813-819
• /
• 2014

The purpose of this study was to extract accurate parameters of facial movement features using 3-D motion capture system in speech recognition technology through lip-reading. Instead of using the features obtained through traditional camera image, the 3-D motion system was used to obtain quantitative data for actual facial movements, and to analyze 11 variables that exhibit particular patterns such as nose, lip, jaw and cheek movements in monosyllable vocalizations. Fourteen subjects, all in 20s of age, were asked to vocalize 11 types of Korean vowel monosyllables for three times with 36 reflective markers on their faces. The obtained facial movement data were then calculated into 11 parameters and presented as patterns for each monosyllable vocalization. The parameter patterns were performed through learning and recognizing process for each monosyllable with speech recognition algorithms with Hidden Markov Model (HMM) and Viterbi algorithm. The accuracy rate of 11 monosyllables recognition was 97.2%, which suggests the possibility of voice recognition of Korean language through quantitative facial movement analysis.

• 치과방사선
• /
• 제24권2호
• /
• pp.413-423
• /
• 1994

The purpose of this study was to clarify the spatial relationship in presurgical examination and to aid surgical planning and postoperative evaluation of patients with facial bone injury. For this study, three-dimensional images of facial bone fracture were reconstructed by computed image analysis system and three-dimensional reconstructive program integrated in computed tomography. The obtained results were as follows: 1. Serial conventional computed tomograms were value in accurately depicting the facial bone injuries and three-dimensional reconstructive images demonstrated an overall look. 2. The degree of deterioration of spatial resolution was proportional to the thickness of the slice. 3. Facial bone fractures were the most distinctly demonstrated on inferoanterior views of three-dimensional reconstructive images. 4. Although three-dimensional reconstructive images made diagnosis of fracture lines, it was difficult to identify maxillary fractures. 5. The diagnosis of zygomatic fractures could be made equally well with computed image analysis system and three-dimensional reconstructive program integrated in computed tomography. 6. The diagnosis of mandibular fractures could be made equally well with computed image analysis system and three-dimensional reconstructive program integrated in computed tomography.