• Maxillofacial Plastic and Reconstructive Surgery
• /
• 제38권
• /
• pp.37.1-37.5
• /
• 2016

Background: The dimensions and shape of the forehead determine the esthetics of the upper third of the face. Korean young people consider a broad and smooth, rounded forehead more attractive. As a result, frontal augmentation becomes more popular in patients with dentofacial deformities. Various surgical procedures and materials have been used in frontal augmentation surgery, with associated advantages and disadvantages. Silicone is a good candidate for frontal augmentation. The author presents two cases of esthetic frontal augmentation with a prefabricated silicone implant in female patients with dentofacial deformities. Case presentation: In case 1, a 24-year-old female patient underwent frontal augmentation surgery with simultaneous maxillomandibular and zygomatic osteotomies to correct facial asymmetry. A silicone implant was fabricated preoperatively using a positive template stone mold of her forehead. In case 2, a 23-year-old female patient underwent total facial contouring surgery including frontal augmentation for improved facial esthetics. A computed tomography (CT)-guided rapid prototype (RP) model was used to make the silicone implants. The operative procedure was safe and simple, and the silicone implants were reliable for a larger degree of frontal augmentation. Six months later, both patients had recovered from the surgery and were satisfied with their frontal shape and projection. Conclusions: Frontal augmentation with silicone implants can be an effective adjuvant strategy to improve facial esthetics in patients with a flat and narrow forehead who undergo orthognathic reconstruction or total facial contouring surgery.

• Journal of Electrical Engineering and Technology
• /
• 제13권1호
• /
• pp.485-492
• /
• 2018

In this paper, we propose facial expression recognition using CNN (Convolutional Neural Network), one of the deep learning technologies. The proposed structure has general classification performance for any environment or subject. For this purpose, we collect a variety of databases and organize the database into six expression classes such as 'expressionless', 'happy', 'sad', 'angry', 'surprised' and 'disgusted'. Pre-processing and data augmentation techniques are applied to improve training efficiency and classification performance. In the existing CNN structure, the optimal structure that best expresses the features of six facial expressions is found by adjusting the number of feature maps of the convolutional layer and the number of nodes of fully-connected layer. The experimental results show good classification performance compared to the state-of-the-arts in experiments of the cross validation and the cross database. Also, compared to other conventional models, it is confirmed that the proposed structure is superior in classification performance with less execution time.

• 대한치과교정학회지
• /
• 제20권1호
• /
• pp.23-45
• /
• 1990

It is the aim of this study to determine the effects of facial denervation on physiological properties of facial muscles and facial bones in growing rabbits. Experimental animals of fifty two Oryctolagus cuniculus rabbits were employed. Unilateral dissection of facial nerve was carried out on twelve rabbits, bilateral dissection of facial nerve was made on another twelve rabbits and the other twenty rabbits were on unilateral dissection of facial nerve for the histochemical analyses. Six rabbits on the bilateral surgical sham operations and six rabbits of non-intervention served the control groups. EMG records of the orbicularis oris, buccinator and masseter muscles as well as lateral and dorsoventral cephalometric films were taken and analyzed at 0, 1, 2, 5 and 8 weeks respectively. The orbicularis oris, buccinator and masseter muscles of both sides were removed from the animals of the histochemistry group and muscle fibers were classified on the basis of histochemical staining for $\alpha$-GPD, NADH-D and myosin ATPase. EMG activities of orbicularis oris and buccinator muscles were vanished immediately after denervation. Recovery of activities were detected one week after denervation in buccinator and five weeks in orbicularis oris muscles. Histochemical properties of masseter muscles remained as fast glycolytic through the experimental period. Orbicularis oris muscle fibers showed the gradual diminution of size and ratio of the slow oxidative fibers accompanied with atrophy, phagocytosis and vacuolation as well as the augmentation of fast oxidative glycolytic fibers. The buccinator muscle manifested the augmentation of fast oxidative glycolytic fibers at five weeks of experiment. Visual changes in morphology of craniofacial area were not evident, however it variety of subtle changes were apparent from statistical analysis of cephalometric measurements. It is concluded facial nerve regulates the physiological properties of facial muscles and interrelation between the function of the facial muscles and changes of facial bones would be in some degrees.

• 방송공학회논문지
• /
• 제22권2호
• /
• pp.162-172
• /
• 2017

본 논문에서는 딥러닝 기술 중의 하나인 CNN(Convolutional Neural Network)을 이용한 얼굴 표정 인식 기법을 제안한다. 기존의 얼굴 표정 데이터베이스의 단점을 보완하고자 질 좋은 다양한 데이터베이스를 이용한다. 제안한 기법에서는 '무표정', '행복', '슬픔', '화남', '놀람', 그리고 '역겨움' 등의 여섯 가지 얼굴 표정 data-set을 구축한다. 효율적인 학습 및 분류 성능을 향상시키기 위해서 전처리 및 데이터 증대 기법(data augmentation)도 적용한다. 기존의 CNN 구조에서 convolutional layer의 특징지도의 수와 fully-connected layer의 node의 수를 조정하면서 여섯 가지 얼굴 표정의 특징을 가장 잘 표현하는 최적의 CNN 구조를 찾는다. 실험 결과 제안하는 구조가 다른 모델에 비해 CNN 구조를 통과하는 시간이 가장 적게 걸리면서도 96.88%의 가장 높은 분류 성능을 보이는 것을 확인하였다.

• 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.

• 대한두개안면성형외과학회지
• /
• 제12권1호
• /
• pp.43-47
• /
• 2011

Purpose: Romberg's disease manifests as progressive hemifacial atrophy of the skin, soft tissue and bone, which usually begins in the first or second decade of life. When present, atrophy may originate from the cutaneous stigmata and may become so sharply delimited by the midline. Methods: A 10-year-old girl, who had suffered from right mandibular area atrophy for 3 years, visited us and was diagnosed with Romberg's disease. The depressed lesion of the face was augmented successfully using a deepithelialized groin free flap. The superficial circumflex iliac vessels were used as the donor pedicle and the facial artery and vein were used as the recipient vessels. Results: After surgery, the flap survived well and she was satisfied with the result. Although there are various methods of facial augmentation using free flaps, this flap has some advantages. First, there is a considerable amount of fat tissue components for augmentation. Second, flap elevation with thinning is possible. Third, the donor site can be hidden. Conclusion: The groin dermo-fat free flap is a good method for the facial augmentation of Romberg's disease.

• 방송공학회논문지
• /
• 제27권6호
• /
• pp.944-947
• /
• 2022

최근 코로나바이러스로 인한 마스크 착용이 급증함에 따라 마스크 착용에 대응할 수 있는 기술의 중요성이 증가하고 있다. 얼굴 자세 추정 분야는 운전자 주의, 얼굴 정면화, 시선 감지 등의 다양한 활용성에도 불구하고 마스크 착용에 따른 성능 저하 문제를 해결할 수 있는 연구가 거의 수행되지 않았다. 본 논문은 마스크 착용 유무에 따른 얼굴 자세 추정의 성능 저하에 대한 분석을 토대로, 마스크가 없는 얼굴 이미지의 크기 및 자세를 분석하여 마스크 이미지를 합성할 수 있는 데이터 증강 기법을 제안한다. 제안하는 얼굴에 특화된 증강 기법을 활용한 학습은 마스크 착용 여부와 관계없이 얼굴 자세 추정 벤치마크 데이터 세트인 BIWI에서 강인한 성능을 보이며, 특정 모델에 국한되지 않기 때문에 다양한 얼굴 자세 추정 모델에 적용될 수 있다.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• 제45권4호
• /
• pp.192-198
• /
• 2019

Objectives: Oral and maxillofacial surgeons must gain mastery of various approaches to the midface due to the increasing incidence, complexity, and severity of presenting midfacial fractures. Unlike in the case of other body parts, the need to preserve facial aesthetics makes it more difficult for the surgeon to select an approach for managing the facial injuries. The midfacial degloving (MFD) approach is a combination of intraoral and intranasal incisions made to access the midface without any external incision. The aim of the present study was to evaluate the efficacy of MFD in maxillofacial surgery and to assess its advantages and complications. Materials and Methods: The MFD approach was used in five cases, with three cases treated with open reduction and internal fixation and two cases operated on for posttraumatic deformity. Nasal dorsum augmentation was completed in three cases and nasal osteotomy was performed in one case. The bicoronal flap technique was combined with MFD for frontal bone augmentation in one case. The intraoperative time required for flap completion and the ease of performing the planned procedures were noted. Postoperative evaluation was done for reduction, aesthetics, function, and complications. Results: Access was excellent for performing all planned procedures. Average time spent for flap elevation and exposure of the midface was 63 minutes. Complications like postoperative swelling, infraorbital nerve paresthesia, and intranasal crusting were all transient. No long-term complications like stenosis of the nose, sneer deformity, or weakness of the facial muscles were noticed. Additionally, no complications were noted when MFD was combined with bicoronal flap. Conclusion: Though the MFD approach is technically demanding and takes more time than other facial approaches, it should be learned and applied by maxillofacial surgeons in selective cases, as it provides complete exposure of the midface without facial scarring.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• 제32권4호
• /
• pp.344-350
• /
• 2010

A progressive hemifacial atrophy is characterized by progressive atrophy of subcutaneous fat and rarely muscle and bone. Its contour follows the underlying muscle. Unilateral involvement is common. The treatment goal has been focused on the augmentation of the soft tissue. Many materials such as implants, collagen, fat graft, fat injection, dermal fat graft, filler and vascualized autogenous graft have been used. Although these materials have been used, the best treatment hasn't been achived. In severe cases underlying soft tissue, muscle and bone may be atrophied and massive soft tissue graft, implant and orthognathic surgery must be used. The author used the dermal-fat tissue for the pupose of soft tissue augmentation. We can get the massive soft tissue by the dermolipectomy procedure through the mini-abdominoplsty. The facial augmentation was done by augmentation of the dermal-fat tissue. The progressive hemifacial atrophy is hard to treat by only one procedure and many modalites must be considered.

• Archives of Plastic Surgery
• /
• 제50권1호
• /
• pp.42-48
• /
• 2023

Background The temporalis muscle flap transfer with fascia lata augmentation (FLA) is a promising method for smile reconstruction after facial palsy. International literature lacks a detailed anatomical analysis of the temporalis muscle (TPM) combined with fascia lata (FL) augmentation. This study aims to describe the muscle's properties and calculate the length of FL needed to perform the temporalis muscle flap transfer with FLA. Methods Twenty nonembalmed male (m) and female (f) hemifacial cadavers were dissected to investigate the temporalis muscle's anatomy. Results The calculated minimum length of FL needed is 7.03cm (f) and 5.99cm (m). The length of the harvested tendon is 3.16cm/± 1.32cm (f) and 3.18/± 0.73cm (m). The length of the anterior part of the temporalis muscle (aTPM) is 4.16/± 0.80cm (f) and 5.30/± 0.85cm (m). The length of the posterior part (pTPM) is 5.24/± 1.51cm (f) and 6.62/± 1.03cm (m). The length from the most anterior to the most posterior point (aTPMpTPM) is 8.60/± 0.98cm (f) and 10.18/± 0.79cm (m). The length from the most cranial point to the distal tendon (cTPMdT) is 7.90/± 0.43cm (f) and 9.79/± 1.11cm (m). Conclusions This study gives basic information about the temporalis muscle and its anatomy to support existing and future surgical procedures in their performance. The recommended minimum length of FL to perform a temporalis muscle transfer with FLA is 7.03cm for female and 5.99cm for male, and minimum width of 3 cm. We recommend harvesting some extra centimeters to allow adjusting afterward.