• 구강회복응용과학지
• /
• 제23권4호
• /
• pp.359-371
• /
• 2007

Recently, many studies were reported accurate analysis of facemask effect due to the development of the personal computers and computer programs. The aim of this study is appropriate protraction direction of facemask using finite element study with computer aided design and computer aided measurement. The construction of the three dimensional FEM was based on the computer tomography(CT) scans of 13.5 year-old male subject. Protraction force of 500 mg was applied at 0, 30, 60 and 90 degrees downwards to the Frankfort horizontal plane, and maxillary displacement and stress distribution were measured. When 60 degree force was applied, it showed forward movement of premolar roots area and downward movement of anterior nasomaxillary area, and others showed clockwise rotation movement of the nasomaxillary complex. Finally, we can produce the protraction of maxillary bone without rotation of maxilla about 60 degrees.

• Imaging Science in Dentistry
• /
• 제46권1호
• /
• pp.33-38
• /
• 2016

Purpose: Facial asymmetry has been measured by the severity of deviation of the menton (Me) on posteroanterior (PA) cephalograms and three-dimensional (3D) computed tomography (CT). This study aimed to compare PA cephalograms and 3D CT regarding the severity of Me deviation and the direction of the Me. Materials and Methods: PA cephalograms and 3D CT images of 35 patients who underwent orthognathic surgery (19 males and 16 females, with an average age of $22.1{\pm}3.3years$) were retrospectively reviewed in this study. By measuring the distance and direction of the Me from the midfacial reference line and the midsagittal plane in the cephalograms and 3D CT, respectively, the x-coordinates ($x_1$ and $x_2$) of the Me were obtained in each image. The difference between the x-coordinates was calculated and statistical analysis was performed to compare the severity of Me deviation and the direction of the Me in the two imaging modalities. Results: A statistically significant difference in the severity of Me deviation was found between the two imaging modalities (${\Delta}x=2.45{\pm}2.03mm$, p<0.05) using the one-sample t-test. Statistically significant agreement was observed in the presence of deviation (k=0.64, p<0.05) and in the severity of Me deviation (k=0.27, p<0.05). A difference in the direction of the Me was detected in three patients (8.6%). The severity of the Me deviation was found to vary according to the imaging modality in 16 patients (45.7%). Conclusion: The measurement of Me deviation may be different between PA cephalograms and 3D CT in some patients.

• 디지털산업정보학회논문지
• /
• 제9권2호
• /
• pp.111-119
• /
• 2013

Face recognition has recently become one of the most popular research areas in the fields of computer vision, machine learning, and pattern recognition because it spans numerous applications, such as access control, surveillance, security, credit-card verification, and criminal identification. In this paper, we propose a simple descriptor called an ECSP(Extended Center-Symmetric Pattern) for illumination-robust face recognition. The ECSP operator encodes the texture information of a local face region by emphasizing diagonal components of a previous CS-LBP(Center-Symmetric Local Binary Pattern). Here, the diagonal components are emphasized because facial textures along the diagonal direction contain much more information than those of other directions. The facial texture information of the ECSP operator is then used as the input image of an image covariance-based feature extraction algorithm such as 2D-PCA(Two-Dimensional Principal Component Analysis). Performance evaluation of the proposed approach was carried out using various binary pattern operators and recognition algorithms on the Yale B database. The experimental results demonstrated that the proposed approach achieved better recognition accuracy than other approaches, and we confirmed that the proposed approach is effective against illumination variation.

• Archives of Plastic Surgery
• /
• 제39권5호
• /
• pp.556-560
• /
• 2012

Zygomatic fractures are the second most common facial bone fractures encountered and treated by plastic surgeons. Stable fixation of fractured fragments after adequate exposure is critical for ensuring three-dimensional anatomic reduction. Between January 2008 and December 2010, 17 patients with zygomatic fractures were admitted to our hospital; there were 15 male and 2 female patients. The average age of the patients was 41 years (range, 19 to 75 years). We exposed the inferior orbital rim and zygomatic complex through a lateral brow, intraoral, and subciliary incisions, which allowed for visualization of the bone, and then the fractured parts were corrected using the Carroll-Girard T-bar screw. Postoperative complications such as malar asymmetry, diplopia, enophthalmos, and postoperative infection were not observed. Lower eyelid retraction and temporary ectropion occurred in 1 of the 17 patients. Functional and cosmetic results were excellent in nearly all of the cases. In this report, we describe using the Carroll-Girard T-bar screw for the reduction of zygomatic fractures. Because this instrument is easy to use and can rotate to any direction and vector, it can be used to correct displaced zygomatic bone more accurately and safely than other devices, without leaving facial scars.

• 패션비즈니스
• /
• 제24권6호
• /
• pp.120-134
• /
• 2020

Recently, the beauty industry has implemented personalized services based on skin big data. To increase competitiveness in the beauty industry, systematic data measurement and evaluation indicators are necessary to select data and obtain necessary knowledge. In response, this study sought to stably enhance the accuracy of skin diagnosis based on satisfaction and reliability. To this end, the research was conducted through focus group interviews (FGI), a case study of brands, and analysis of prior research results. In particular, as a result of analyzing keywords that classify skin types by brand, common survey items for skin types were oiliness and using moisturizer, cosmetic use and vascular of skin, external stimulus and blemish & freckles, facial wrinkle, outside activities, self-consciousness, and smoke. In additioin to the common questions of the preceding study and the brand survey items, the questions concerning complex skin types, seasonal change, facial color, wrinkles and elasticity were added, and the questions were presented in a total of 40 items. In particular, it suggested that skin measurement could be conducted by focusing on elasticity and pigmentation items by reflecting the results of prior research and the opinions of FGI, and based on this, a customized service with high satisfaction and high accuracy of beauty care based on this could be proposed. We hope that this study will facilitate active self-care by providing more satisfying skin stones and personalized cosmetics proposals, thus laying the foundation for the further development of the cosmetics industry.

• 한국멀티미디어학회논문지
• /
• 제25권10호
• /
• pp.1535-1545
• /
• 2022

Sign language has completely different meaning depending on the direction of the hand or the change of facial expression even with the same gesture. In this respect, it is crucial to capture the spatial-temporal structure information of each movement. However, sign language translation studies based on Sign2Gloss2Text only convey comprehensive spatial-temporal information about the entire sign language movement. Consequently, detailed information (facial expression, gestures, and etc.) of each movement that is important for sign language translation is not emphasized. Accordingly, in this paper, we propose Spatial-temporal Keypoints Centered Sign2Gloss2Text Translation, named STKC-Sign2 Gloss2Text, to supplement the sequential and semantic information of keypoints which are the core of recognizing and translating sign language. STKC-Sign2Gloss2Text consists of two steps, Spatial Keypoints Embedding, which extracts 121 major keypoints from each image, and Temporal Keypoints Embedding, which emphasizes sequential information using Bi-GRU for extracted keypoints of sign language. The proposed model outperformed all Bilingual Evaluation Understudy(BLEU) scores in Development(DEV) and Testing(TEST) than Sign2Gloss2Text as the baseline, and in particular, it proved the effectiveness of the proposed methodology by achieving 23.19, an improvement of 1.87 based on TEST BLEU-4.

• Journal of Acupuncture Research
• /
• 제37권3호
• /
• pp.161-166
• /
• 2020

Background: The purpose of this study was to investigate the characteristics and direction of treatment for peripheral facial palsy (PFP) based on medical collaboration between Western and Korean medicine departments. Methods: There were 195 outpatients with PFP identified retrospectively by examining electronic medical records. These patients were treated with Korean and Western medicine from January 1^st, 2018 to December 31^st, 2018 at the Kyung Hee University hospital. Records were analyzed according to the patients' demographic characteristics and clinical features of the collaborative combined treatment. Results: According to the collaborative treatment pathway, the number of patients consulted from Western medicine departments was more than consulted from Korean department for the first time. The time taken by the Western medicine departments to consult with the patients at the Korean center for the first time was 14.9 days from the onset of symptoms. Acupuncture was the most frequently used Korean medicine treatment. The total treatment period for Korean medicine sessions and intervals were 91.9 days, 23 times and 3.6 days, respectively. When the Korean medicine center consulted with Western medicine departments, the time taken until the first consultation was 8.5 days from the onset of symptoms. Medication was the most used treatment, prescribed after 3.1 days. The most frequently used clinical test was an electromyogram, and this was performed after 20.5 days. The total treatment period, sessions and intervals were 21.2 days, 2.8 times and 5 days, respectively. Conclusion: The clinical status of collaborative treatment for PFP was determined including the timing and interval of consultation according to treatments.

• 대한치과의사협회지
• /
• 제44권12호통권451호
• /
• pp.816-829
• /
• 2006

The purpose of this study was to determine the level of perception and preference between dentists and lay people to altered facial profile. The assessors consisted of 40 dentists and 54 lay people, the survey was performed using questionnaire asking the order of perception and preference. The profiles presented in the questionnaire were based on the profile of one man and one woman, each morphed according to anterior or posterior direction of maxilla and mandible. The results were as follows. 1. In antero-posterior change of man and woman s profile, both dentists and lay people were sensitive to relatively skeletal profile (convex profile) changes than skeletal profile (concave profile) changes. 2. At least dentists needed to be perceived a 2 mm change in convex profile and a 3 mm change in concave profile and lay people needed to be perceived a 2 mm change in convex profile and a 3 mm change in concave profile for profile view. 3. Dentists are more sensitive in perception of man s profile change than lay people, but there is no significant differences between dentists and lay people in sensitivity of detection for woman s profile changes . 4. It seems that there is a general concordance between dentists and lay people in there perception of man s and woman s facial profile. This information might be clinician in comprehensive perception and preference of dentists and lay people to altered facial profile.

• 전자공학회논문지S
• /
• 제35S권8호
• /
• pp.55-67
• /
• 1998

본 논문에서는 컬러 비디오 시퀀스 상에서 눈과 입에 해당하는 얼굴 특징점을 고속으로 추출하는 방법을 제안한다. 자유로운 움직임을 갖는 얼굴 영역을 안정적으로 추출하기 위해 얼굴 색상 분포를 이용한 색상 변환 영상에 움직임 검출 기법을 적용하여 움직이는 살색 부분만을 효율적으로 검출하는 색상 움직임 개념을 사용하였다. 움직임 정보는 살색의 가능성 정도에 따라 가중치가 주어지며 화소 단위의 움직임 여부를 결정하는 문턱값도 살색의 가능성 정도에 따라 적응적으로 결정된다. 눈의 색상분포와 형태소 연산자를 사용한 움직임 살색 영역에서 눈 후보 영역을 추출하고 눈과 눈썹의 상호 위치 관계를 이용하여 눈의 영역을 최종 결정한다. 입의 영역은 눈의 위치를 기준으로 입 후보 영역을 정하고 색상 히스토그램을 이용하여 입의 영역을 검출한다. 찾아진 눈과 입의 영역에서 정확한 특징점의 위치를 구하기 위해 PCA (Principal Component Analysis)를 사용하였다. 실험 결과 복잡한 배경, 개인적인 편차, 얼굴의 방향과 크기 등에 영향을 받지 않고 고속으로 정확한 얼굴의 특징점을 추출할 수 있었다.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• 제34권1호
• /
• pp.34-40
• /
• 2012

Purpose: The study was performed to compare patients with anatomical variations in facial asymmetry with patients in the normal range using cone-beam computed tomography (CBCT) and to take the preoperative condition into consideration in the case of a sagittal split ramus osteotomy (SSRO). Methods: The study was conducted on 46 adult patients composed of 2 subdivided groups, an asymmetry group (n=26) and a symmetry group (n=20). The asymmetry group was divided between patients with hemimandibular hyperplasia (HH, n=8) and hemimandibular elongation (HE, n=18). Using cross-sectional computed tomography images, the thickness of cancelleous bone in the buccal area of the mandible, thickness of buccal cortex in the buccal aspect of the mandible, thickness of cancellous bone in the inferior aspect of the mandible, thickness of buccal cortex in the inferior aspect of the mandible, and cross-sectional surface area of the mandible were measured. Results: In the asymmetry group, the cross-sectional area of the mandible including the inferior alveolar nerve positioned on the affected side was significantly different from the symmetry group. Thickness of cancelleous bone in the buccal aspect of the mandible, thickness of cancelleous bone in the inferior aspect of the mandible, and cross-sectional surface area of the mandible in the affected site of hemimandibular hyperplasia was significantly smaller than in the symmetry group. Conclusion: The inferior alveolar nerve runs lower and in a more buccal direction and shows a smaller cross-sectional surface of the mandible in the hemimandibular hyperplasia patients with asymmetry.