• Journal of the Semiconductor & Display Technology
• /
• v.7 no.3
• /
• pp.45-49
• /
• 2008

Face detection and tracking technology on video sequence has developed indebted to commercialization of teleconference, telecommunication, front stage of surveillance system using face recognition, and video-phone applications. Complex background, color distortion by luminance effect and condition of luminance has hindered face recognition system. In this paper, we have proceeded to research of face recognition on video sequence. We extracted facial area using luminance and chrominance component on $YC_bC_r$ color space. After extracting facial area, we have developed the face recognition system applied to our improved algorithm that combined PCA and LDA. Our proposed algorithm has shown 92% recognition rate which is more accurate performance than previous methods that are applied to PCA, or combined PCA and LDA.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.703-708
• /
• 2009

The present paper describes the application of an improved impression transfer vector method (Sakurai et al., 2007) to transform the three basic dimensions (Evaluation, Activity, and Potency) of higher-order impression. First, a set of shapes and surface textures of faces was represented by multi-dimensional vectors. Second, the variation among faces was coded in reduced parameters derived by applying principal component analysis. Third, a facial attribute along a given impression dimension was analyzed to select discriminative parameters from among principal components with higher sensitivity to impressions, and obtain an impression transfer vector. Finally, the parametric coordinates were changed by adding or subtracting the impression transfer vector and the image was manipulated so that its facial appearance clearly exhibits the transformed impression. A psychological rating experiment confirmed that the impression transfer vector modulated three dimensions of higher-order impression. We discussed the versatility of the impression transfer vector method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2002.05a
• /
• pp.448-451
• /
• 2002

This study will offer multi-feature recognition instead of an using mono-feature to improve the accuracy of recognition. Each Feature can be found by following ways. For a face, the feature is calculated by the principal component analysis with wavelet multiresolution. For a lip, a filter is used to find out on equation to calculate the edges of the lips first. Then the other feature is calculated by the distance ratio of facial parameters. We've sorted backpropagation neural network and experimented with the inputs used above and then based on the experimental results we discuss the advantage and efficiency.

• Journal of KIISE:Software and Applications
• /
• v.26 no.11
• /
• pp.1332-1341
• /
• 1999

본 논문에서는 시간에 따라 위치 및 회전각도가 변하는 얼굴 영상을 분석하여 눈과 입을 추출하는 방법을 제안한다. 동영상에서의 얼굴 영역을 효과적으로 추적하기 위해 간편화된 칼만 필터를 제안하며, 예측된 얼굴 영역 내에서 얼굴의 회전 각도를 고려하여 수직 및 수평 프로파일을 적용함으로써 좀 더 정교하게 얼굴 구성요소를 추출한다. 제안한 방법의 효율성은 실험 결과를 통하여 보인다.Abstract We propose the method that extracts eyes and mouth of human by analysing facial image sequences which can change their positions and orientations along the time. We propose the simplified Kalman filter to track the area of human face efficiently in image sequences. We also devise the method of slant-compensation, so that the facial components could be extracted more accurately by using vertical and horizontal profiles of the compensated images. Finally, we show the effectiveness of the suggested method through experimental results.

• Journal of the Korean Institute of Telematics and Electronics T
• /
• v.36T no.3
• /
• pp.26-31
• /
• 1999

In this paper, we propose a facial characteristic detection algorithm based on knowledge and object segmentation method for image communication. In this algorithm, under the condition of the same lumination and distance from the fixed video camera to human face, we capture input images of 256 $\times$ 256 of gray scale 256 level and then remove the noise using the Gaussian filter. Two images are captured with a video camera, One contains the human face; the other contains only background region without including a face. And then we get a differential image between two images. After removing noise of the differential image by eroding End dilating, divide background image into a facial image. We separate eyes, ears, a nose and a mouth after searching the edge component in the facial image. From simulation results, we have verified the efficiency of the Proposed algorithm.

• The korean journal of orthodontics
• /
• v.49 no.3
• /
• pp.170-180
• /
• 2019

Objective: The purpose of this study was to investigate the relationship between the facial skeletal patterns and the shape of the mandibular symphysis in adults with malocclusion by using a structural equation model (SEM). Methods: Ninety adults who had malocclusion and had records of facial skeletal measurements performed using cone-beam computed tomography were selected for this study. The skeletal measurements were classified into three groups (vertical, anteroposterior, and transverse). Cross-sectional images of the mandibular symphysis were analyzed using generalized Procrustes and principal component (PC) analyses. A SEM was constructed after the factors were extracted via factor analysis. Results: Two factors were extracted from the transverse, vertical, and anteroposterior skeletal measurements. Latent variables were extracted for each factor. PC1, PC2, and PC3 were selected to analyze the variations of the mandibular symphyseal shape. The SEM was constructed using the skeletal variables, PCs, and latent variables. The SEM showed that the vertical latent variable exerted the most influence on the mandibular symphyseal shape. Conclusions: The relationship between the skeletal pattern and the mandibular symphysis was analyzed using a SEM, which showed that the vertical facial skeletal pattern had the highest effect on the shape of the mandibular symphysis.

• The korean journal of orthodontics
• /
• v.12 no.2
• /
• pp.79-93
• /
• 1982

The purpose of orthodontic treatment is to achieve normal occlusion and good facial esthetics for individual patients. To produce harmonized facial balance, treatment planning for patient who require orthodontic treatment should include both a hard tissue and soft tissue cephalometric analysis. Author studied to derive the normal standards of soft tissue profile in Koreans by roentgenocephalometric analysis. For this study 12 soft tissue profile landmarks were plotted and 23 linear length, 9 soft tissue thickness, 8 vertical height length, 12 angles of soft tissue profile, and 3 vertical proportion were measured. The subjects consisted of 166 males and 209 females from 7 to 19 years with normal occlusion and acceptable profiles, and were divided into five groups according to age. The obtained results were as follows; 1. From the basis of N-Pog (Nasion-Pogonion) plane, the growth of facial soft tissue in the middle region especially nose area was greater than others facial region. 2. From the basis of G-Pog' (Glabella-soft tissue Pogonion) plane, the values of linear measurement of soft tissue Nasion and Inferior labial sulcus decreased and nose tip grew forward as growing older. 3. The growth of the facial soft tissue thickness was greatest in superior labial sulcus and the thickness of soft tissue nasion gradually became thinner as growing old. 4. The thickness of upper and lower lip was 14.47mm, 14.57mm in adulr male, 12.76mm, 13.78mm in adult female. 5. The soft tissue thickness of the lower lip was thicker than that of upper lip in all age groups and both sexes, 6. The vertical length of the upper and lower lips were 25.04mm, 49.97mm in adult male and 23.50mm, 48.39mm in adult female. 7. By the significant test, there were significant difference between male and female in fifth adult group on all vertical length measurements of lower face. 8. In fifth adult group, the perpendicular distance from LS, LI to Steiner's line and Ricketts' esthetic line were as follow; Steiner line to LS, LI were 7.98mm, 5.84mm in male. Steiner line to LS, LI were 6.71mm, 5.08mm in female. Ricketts' esthetic line to LS, LI were -0.40mm, 1.72mm in male. Ricketts' esthetic line to Ls, LI were -1.38mm 0.65mm in female. 9. In fifth adult group, the facial convexity angle and lower facial component angle were $171.17^{\circ}142.94^{\circ}$ in male and $172.5^{\circ}$, $144.41^{\circ}$ in female.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.831-832
• /
• 2008

This paper proposes the experimental results and analysis of face recognition on an conventional UMPC(Ultra Mobile Personal Computer). With face images acquired by the embedded camera of UMPC, we detected the facial region by using Adaboost face detector. The detected image was normalized into a $32{\times}32$ pixel sized image for face recognition. We performed face recognition based on PCA (Principal Component Analysis). As experimental results, the TER (Total Error Rate) of face recognition was 19.77%.

• Archives of Plastic Surgery
• /
• v.47 no.4
• /
• pp.301-304
• /
• 2020

Dermal injectables are the most popular material for facial enhancement, including volumizing and wrinkle correction. However, although hyaluronic acid is the most common component of dermal injectables, the character of hyaluronic acid products is quite variable. These materials can be described in terms of their viscoelastic properties using four parameters. In this article, the author would like to describe these properties in detail. Although many physicians consider this material to be convoluted, thoroughly understanding the characteristics of various injectables enables us to tailor procedures accordingly and to enhance the final results.

• Journal of Multimedia Information System
• /
• v.2 no.1
• /
• pp.171-178
• /
• 2015

This article describes 3 dimensional (3D) face recognition system using histogram of oriented gradients (HOG) based on face curvature. The surface curvatures in the face contain the most important personal feature information. In this paper, 3D face images are recognized by the face components: cheek, eyes, mouth, and nose. For the proposed approach, the first step uses the face curvatures which present the facial features for 3D face images, after normalization using the singular value decomposition (SVD). Fisherface method is then applied to each component curvature face. The reason for adapting the Fisherface method maintains the surface attribute for the face curvature, even though it can generate reduced image dimension. And histogram of oriented gradients (HOG) descriptor is one of the state-of-art methods which have been shown to significantly outperform the existing feature set for several objects detection and recognition. In the last step, the linear discriminant analysis is explained for each component. The experimental results showed that the proposed approach leads to higher detection accuracy rate than other methods.