• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.3
• /
• pp.135-138
• /
• 2014

This paper devices a facial expression recognition method robust to overfitting using 2D-DCT and EHMM algorithm. In particular, this paper achieves enhanced recognition performance by setting up a large window size for 2D-DCT feature extraction and extracting the observation vectors of EHMM. The experimental results on the CK facial expression database and the JAFFE facial expression database showed that the facial expression recognition accuracy was improved according as window size is large. Also, the proposed method revealed the recognition accuracy of 87.79% and showed enhanced recognition performance ranging from 46.01% to 50.05% in comparison to previous approaches based on histogram feature, when CK database is employed for training and JAFFE database is used to test the recognition accuracy.

• The Journal of Advanced Prosthodontics
• /
• v.2 no.3
• /
• pp.65-70
• /
• 2010

Large oro-facial defects result from cancer treatment consequences in serious functional as well as cosmetic deformities. Acceptable cosmetic results usually can be obtained with a facial prosthesis. However, retention of a large facial prosthesis can be challenging because of its size and weight. This article describes prosthetic rehabilitation of a 57-year-old man having a right lateral mid-facial defect with intraoral-extraoral combination prosthesis. A modified technique to fabricate a hollow substructure in heat-polymerizing polymethyl-methacrylate to support silicone facial prosthesis was illustrated. The resultant facial prosthesis was structurally durable and light in weight facilitating the retention with magnets satisfactorily. This technique is advantageous as there is no need to fabricate the whole prosthesis again in case of damage of the silicone layer because the outer silicone layer can be removed and re-packed on the substructure if the gypsum-mold is preserved.

• Archives of Reconstructive Microsurgery
• /
• v.20 no.1
• /
• pp.60-63
• /
• 2011

Capillary malformation is common vascular malformation. In case of facial capillary malformation, patients' cosmetic and functional deficits are quite significant. The standard treatment which has been applied so far for capillary malformation is pulsed dye laser with 585nm. But in case of advanced capillary malformation, surgical interventions are inevitable. The problem of large size facial capillary malformation is how to cover the remnant defect, which occurs after resection. In this case, authors have experienced surgical treatment of large size facial capillary malformation and covered the large facial defect with free thoracodorsal artery perforator flap. The flap was thick, so facial asymmetry remained after the first surgery. But with the secondary procedure, authors have made more symmetric figures. The patient was satisfied with the result. Using free flap to replace the defect after resection due to capillary malformation is useful for these kinds of cases.

• Korean Journal of Head & Neck Oncology
• /
• v.15 no.2
• /
• pp.200-204
• /
• 1999

Objectives: Injuries of neurologic structures during parotid surgery are sometimes unavoidable even in benign tumors. Since the major postoperative neurologic complications such as facial nerve palsy and Frey's syndrome give a serious and heavy burden to both patients and surgeons, it is very important to know detailed information concerning risk factors, the incidence of complication, possibility of recovery, and the term before complete recovery. Materials and Methods: This report was based on 95 patients with parotid gland tumor who had been treated and followed up over 1 year at department of surgery and otolaryngology, chonnam university hospital. Results: 1) Among total 95 cases, the facial nerve palsy developed in 18 cases(l8.9%) and Frey's syndrome in 6 cases(6,3%). 2) The incidence of facial nerve palsy increased in cases with large tumor size, and in those operated with bipolar method. However, we didn't find out relationships between the incidence of facial palsy, localization, and histologic type. 3) The incidence of Frey's syndrome showed an increasing tendency in the cases with large tumor size, benign nature, and in those underwent superficial lobectomy with posterior approach, without a statistical significance. Conclusions: Risk of facial nerve palsy, especially a transient form, seems to be related to tumor size and bipolar coagulation method. Although Frey's syndrome tends to develop easily in the cases treated with superficial lobectomy under the diagnosis of benign tumor, a futhermore study is suggested to obtain a statistical significance.

• The Research Journal of the Costume Culture
• /
• v.12 no.5
• /
• pp.743-756
• /
• 2004

The purpose of this study is to set measurement parts which are important to identify the size and shape of the head in order to produce tightly fitted hats, and to identify detailed sizes and the major factors of head shape classifications of Korean women. A total of 285 Korean women's in the age group of 18 to 35 years old. It were measured through the direct measurement method by selecting 67 measurement items. Materials were analyzed by SPSS Ver.10 and technology statistics and factor analysis were performed according to the agenda. An attempt was made to conduct factor analysis of the measured region of the head in women's. Here, this study drew the head and the facial parts horizontal size as Factor 1, the head and facial parts vertical size as Factor 2, the circumference and width item as Factor 3, the factor representing the form of head height as Factor 4, the factor expressing the proportion of the facial form as Factor 5 and the factor about the frontal and back head form on the plan of the middle as Factor 6. Through this study, we will be able to systemize head measurement materials that can differentiate Korean's head from other peoples' and can use the results in developing head shape models according to Korean's head shape by selecting major head parts needed to identify the sizes and shapes.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.44 no.6
• /
• pp.1163-1177
• /
• 2020

The purpose of this study is to figure out the information needed to improve the shape and size suitability of face-applied mask sheets. The study analyzed the shape of the mask sheet from the scanned images of 50 products of 37 domestic brands. In addition, each measurement of 42 mask sheets were compared and analyzed multilaterally with the 3D measurement dimensions of the faces of men and women in their 20s from the 6th SizeKorea data. Analysis on the shapes of mask sheets indicated that domestic commercial mask sheets are mainly made of single or dual sheets, with slits for enhancing fitness to the three-dimensional face. In the dimensional analysis of Korean men, women and mask sheets, most of the lengths of the mask sheets were significantly larger or smaller than the actual faces of men and women. The horizontal length and vertical length of the forehead above the eyes are significantly shorter, thereby requiring adjustments in the dimensions of this area. In order to improve the size suitability of the mask, it is necessary to adjust the dimensions of the problem area according to the research results as well as diversify the dimensions considering the target layer.

• Journal of Korea Multimedia Society
• /
• v.20 no.5
• /
• pp.748-757
• /
• 2017

In order to recognize the facial expressions, good features that can express the facial expressions are essential. It is also essential to find the characteristic areas where facial expressions appear discriminatively. In this study, we propose a directional LBP feature for facial expression recognition and a method of finding directional LBP operation and feature region for facial expression classification. The proposed directional LBP features to characterize facial fine micro-patterns are defined by LBP operation factors (direction and size of operation mask) and feature regions through AdaBoost learning. The facial expression classifier is implemented as a SVM classifier based on learned discriminant region and directional LBP operation factors. In order to verify the validity of the proposed method, facial expression recognition performance was measured in terms of accuracy, sensitivity, and specificity. Experimental results show that the proposed directional LBP and its learning method are useful for facial expression recognition.

• Journal of Korean Dental Science
• /
• v.17 no.1
• /
• pp.1-13
• /
• 2024

With the advances of digital scanning technology in dentistry, the interests in facial scanning in orthodontics have increased. There are many different manufacturers of facial scanners marketing to the dental practice. How do you know which one will work best for you? What questions should you be asking? We suggest a clinical guideline which may help you make an informed decision when choosing facial scanners. The characteristics of 7 facial scanners were discussed in this article. Here are some considerations for choosing a facial scanner. *Accuracy: For facial scanners to be of real value, having an appropriate camera resolution is necessary to achieve more accurate facial image representation. For orthodontic application, the scanner must create an accurate representation of an entire face. *Ease of Use: Scanner-related issues that impact their ease of use include type of light; scan type; scan time; file type generated by the scanner; unit size and foot print; and acceptance of scans by third-party providers. *Cost: Most of the expenses associated with facial scanning involve the fixed cost of purchase and maintenance. Other expenses include technical support, warranty costs, transmission fees, and supply costs. This article suggests a clinical guideline to make the right choice for facial scanner in orthodontics.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.5
• /
• pp.251-260
• /
• 2016

Face recognition is a technology to extract feature from a facial image, learn the features through various algorithms, and recognize a person by comparing the learned data with feature of a new facial image. Especially, in order to improve the rate of face recognition, face recognition requires various processing methods. In the training stage of face recognition, feature should be extracted from a facial image. As for the existing method of extracting facial feature, linear discriminant analysis (LDA) is being mainly used. The LDA method is to express a facial image with dots on the high-dimensional space, and extract facial feature to distinguish a person by analyzing the class information and the distribution of dots. As the position of a dot is determined by pixel values of a facial image on the high-dimensional space, if unnecessary areas or frequently changing areas are included on a facial image, incorrect facial feature could be extracted by LDA. Especially, if a camera image is used for face recognition, the size of a face could vary with the distance between the face and the camera, deteriorating the rate of face recognition. Thus, in order to solve this problem, this paper detected a facial area by using a camera, removed unnecessary areas using the facial feature area calculated via a Gabor filter, and normalized the size of the facial area. Facial feature were extracted through LDA using the normalized facial image and were learned through the artificial neural network for face recognition. As a result, it was possible to improve the rate of face recognition by approx. 13% compared to the existing face recognition method including unnecessary areas.

• The korean journal of orthodontics
• /
• v.10 no.1
• /
• pp.81-93
• /
• 1980

The interrelationships between growth rates (and size) of the selected cranifacial dimensions and body dimensions (height and weight) were investigated in the longitudinal data of primary school children from 6 to 11 years of age. The data were obtained from serial cephalometric radiographs and health record which were taken at one year interval. Regression analyses were used to analyze the data. The main concludions might be summarized as follows; 1. Size relationships between body height (and weigh) and S-Gn, posterior facial height (s-Go), total mandibular length (Ar-Gn) showed high significant correlation, but no association between body height, weight and anterior cranial base length (S-N). 2. Correlation coefficients between facial dimensions and body height (and weight) were getting lower with age increase. 3. At all age groups, significant prediction equation for some facial dimensions with body height and weight were obtained. 4. In this sample, the growth rates of facial dimensions and body height and weight showed almostly constant during this age period and the growth rate of body height and weight of girls was exceeded that of boys. 5. A relatively high degree of variation between individuals existed in the sample. 6. A positive correlation was found for the relationship between the growth rates of facial dimensions and those of body height (and weight) in boys and girls, but was not found in total samples.