• The Transactions of the Korea Information Processing Society
• /
• v.4 no.12
• /
• pp.3211-3218
• /
• 1997

This paper addresses an eye location algorithm which is essential process of human face tracking system for natural video-conferencing. In current video-conferencing systems, user's facial movements are restricted by fixed camera, therefore it is inconvenient to users. We Propose an eye location algorithm for automatic face tracking. Because, locations of other facial features guessed from locations of eye and scale of face in the image can be calculated using inter-ocular distance. Most previous feature extraction methods for face recognition system are approached under assumption that approximative face region or location of each facial feature is known. The proposed algorithm in this paper uses no prior information on the given image. It is not sensitive to backgrounds and lighting conditions. The proposed algorithm uses the valley representation as major information to locate eyes. The experiments have been performed for 213 frames of 17 people and show very encouraging results.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.33 no.6
• /
• pp.549-558
• /
• 2011

The latissimus dorsi myocutaneous flap (LDMF) was initially described at the turn of the century by Tansini et al, and latissimus dorsi myocutaneous free flap (LDMFF) was also first described for the coverage of a chronically infected scalp by Maxwell et al. As a pedicled flap, LDMF has been often used for breast reconstruction and for soft tissue replacement near the shoulder and the lower reaches of the head and neck. LDMFF is a flat and broad soft tissue flap with large-caliber thoracodorsal vessels for microvascular anastomosis. A skin paddle of the LDMFF can be more than $20{\times}40$ cm, so very large defects in the oral cavity and outer facial region can be covered by this LDMFF. Other advantages include consistent vascular anatomy, acceptable donor site morbidity and the ability to perform simultaneous flap harvest with tumor resection. For a better understanding of LDMFF as a routine reconstructive procedure in large defects of the oral cavity and facial legion, anatomical findings must be learned and memorized by young doctors during the special curriculum periods for the Korean national board of oral and maxillofacial surgery. This review article discusses the anatomical basis of LDMFF with Korean language.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.6
• /
• pp.89-101
• /
• 2014

In this paper, we proposed a new local micro pattern, Signed Local Directional Pattern(SLDP). SLDP uses information of edges to represent the face's texture. This can produce a more discriminating and efficient code than other state-of-the-art methods. Each micro pattern of SLDP is encoded by sign and its major directions in which maximum edge responses exist-which allows it to distinguish among similar edge patterns that have different intensity transitions. In this paper, we divide the face image into several regions, each of which is used to calculate the distributions of the SLDP codes. Each distribution represents features of the region and these features are concatenated into a feature vector. We carried out facial expression recognition with feature vectors and SVM(Support Vector Machine) on Cohn-Kanade and JAFFE databases. SLDP shows better classification accuracy than other existing methods.

• Archives of Craniofacial Surgery
• /
• v.20 no.6
• /
• pp.388-391
• /
• 2019

Schwannoma is a slow-growing, well-demarcated, benign soft tissue tumor of the peripheral nerve sheath. It commonly develops in the head and neck region, usually in the parapharyngeal space. In this case, a 42-year-old woman visited the outpatient department to manage a painless mass on her left cheek. She had no history of concern and no neurological symptoms were observed. In the enhanced computed tomography scan, a 2.8×2.8×1.8 cm, heterogeneously enhanced tumor was detected in the left masseter muscle. A tumor resection under general anesthesia was planned. For the resection, a facelift incision was chosen; branches of the facial nerve were identified and retrogradely dissected. A well-marginated, yellowish, solid mass was found in the left masseter muscle. The mass was excised and given a histopathological diagnosis of schwannoma. A definite diagnosis of schwannoma, originating in the masseter muscle, is difficult to arrive at with radiographic findings alone; it is often misdiagnosed as intramuscular hemangioma. Histopathological examinations, including fine-needle aspiration or histological biopsy after surgery, are necessary. Using a facelift incision with retrograde facial nerve dissection, tumor resection in an intramasseteric lesion can be performed efficiently, without nerve damage, or leaving conspicuous scars on the face.

• Journal of Biomedical Engineering Research
• /
• v.37 no.2
• /
• pp.68-74
• /
• 2016

In this study, we investigated the rotational characteristics which were comprised of directionality and linearity of target registration error (TRE) as a study in advance to enhance the accuracy of contour-based registration in neuronavigation. For the experiment, two rigid head phantoms that have different faces with specially designed target frame fixed inside of the phantoms were used. Three-dimensional coordinates of facial surface point cloud and target point of the phantoms were acquired using computed tomography (CT) and 3D scanner. Iterative closest point (ICP) method was used for registration of two different point cloud and the directionality and linearity of TRE in overall head were calculated by using 3D position of targets after registration. As a result, it was represented that TRE had consistent direction in overall head region and was increased in linear fashion as distance from facial surface, but did not show high linearity. These results indicated that it is possible for decrease TRE by controlling orientation of facial surface point cloud acquired from scanner, and the prediction of TRE from surface registration error can decrease the registration accuracy in lesion. In the further studies, we have to develop the contour-based registration method for improvement of accuracy by considering rotational characteristics of TRE.

• Journal of Broadcast Engineering
• /
• v.26 no.5
• /
• pp.608-620
• /
• 2021

Recent deep learning-based face super-resolution (FSR) works showed significant performances by utilizing facial prior knowledge such as facial landmark and dictionary that reflects structural or semantic characteristics of the human face. However, most of these methods require additional processing time and memory. To solve this issue, this paper propose an efficient FSR models using knowledge distillation techniques. The intermediate features of teacher network which contains dictionary information based on major face regions are transferred to the student through adversarial multi-scale features distillation. Experimental results show that the proposed model is superior to other SR methods, and its effectiveness compare to teacher model.

• Korean Journal of Forensic Psychology
• /
• v.12 no.2
• /
• pp.99-120
• /
• 2021

This study examined the differences in facial emotion processing related to psychopathic traits. On the basis of the Psychopathic Personality Inventory-Revised (Lee & Park, 2008), students were divided into psychopathic trait (n=15) and control (n=15) groups. Participants performed two tasks consisted of negative(angry, fear, sad) and neutral faces. Event-related potentials(EPRs) were recorded when participants categorized gender in the implicit task and emotion in the explicit task. We analyzed the late positive potentials(LPP) amplitude to investigate differences in emotion processing between psychopathic trait group and control group. In the implicit task, there was no significant difference in both groups. However, there was a significant interaction between emotion and group at the frontocentral region in the explicit task. The psychopathic trait group showed greater LPP amplitudes for the neutral faces than for the negative faces, whereas the control group showed similar LPP amplitudes for the neutral and negative faces at the frontocentral site. These results might reflect the abnormalities in emotional processing in individuals with psychopathic traits.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.141-147
• /
• 2024

Recently, there has been growing interest in personalized services tailored to an individual's preferences. This has led to ongoing research aimed at recognizing and leveraging an individual's personality traits. Among various methods for personality assessment, the OCEAN model stands out as a prominent approach. In utilizing OCEAN for personality recognition, a multi modal artificial intelligence model that incorporates linguistic, paralinguistic, and non-linguistic information is often employed. This paper examines the impact of the margin value set for extracting facial areas from video data on the accuracy of a personality recognition model that uses facial expressions to determine OCEAN traits. The study employed personality recognition models based on 2D Patch Partition, R2plus1D, 3D Patch Partition, and Video Swin Transformer technologies. It was observed that setting the facial area extraction margin to 60 resulted in the highest 1-MAE performance, scoring at 0.9118. These findings indicate the importance of selecting an optimal margin value to maximize the efficiency of personality recognition models.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.5
• /
• pp.125-133
• /
• 2008

As society develops, the importance of safety for individuals and facilities in public places is getting higher. Not only the areas such as the existing parking lot, bank and factory which require security or crime prevention but also individual houses as well as general institutions have the trend to increase investment in guard and security. This study suggests face feature extract and the method to simply divide face region and head region that are import for face recognition by using color transform. First of all, it is to divide face region by using color transform of Y image of YIQ image and head image after dividing head region with K image among CMYK image about input image. Then, it is to extract features of face by using labeling after Log calculation to head image. The clearly divided head and face region can easily classify the shape of head and face and simply find features. When the algorism of the suggested method is utilized, it is expected that security related facilities that require importance can use it effectively to guard or recognize people.

• The Journal of the Korean dental association
• /
• v.47 no.11
• /
• pp.750-757
• /
• 2009

Purpose : The purpose of this study is to evaluate the clinical availability of submentoplasty for esthethic improvement of the cervico-facial region of patients with obtuse chin-neck angle. Materials and methods : Case 1. We evaluate the changes of submental line length and chin-neck angle of 35-year-old woman with skeletal Class III and mandibular excess with excessive submental fat before and after surgery: Bilateral sagittal split ramus osteotomy(BSSRO) setback(5mm), Mandibular Angle Reduction, Reduction Malarplasty and Submentoplasty. In this case, It was done simultaneously with orthognathic surgery. Case 2. The changes of submental line length and chin-neck angle of 20-year-old man with skeletal class III and maxillary defiency were evaluated before surgery, at first surgery : Lefort I osteotomy(6mm posterior Impaction), BSSRO setback(9mm), Paranasal Augmentation and at second surgery: genioplasty(6mm advanced) with submentoplasty. In this case, submentoplasty and advancement genioplasty were done after 2 months post-operative periods. Results : Case 1. In case of the Skeletal Class III mandibular excess with submental fat deposit, It showed the improvement of submental angle and length of submental line after simultaneous submentoplasty. Submental angle is changed from $177^{\circ}$ (pre-op) to $151^{\circ}$ (post-op) and submental line length is changed from 8mm(pre-op) to 36mm(post-op). Case 2. The improvement of submental angle and length of submental line after delayed submentoplasty was aquired in case of the skeletal class III maxillary defiency. Submental angle is changed from $154^{\circ}$ (pre-op) to $161^{\circ}$ (first surgery) and to $153^{\circ}$ (second surgery) and submental line length is changed from 25mm(pre-op) to 19mm(first surgery) and to 23mm(second surgery). Conclusion : The results suggest that Submentoplasty is useful surgical procedure for esthethic improvement of the cervicofacial region of patients with obtuse chin-neck angle.