• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.11a
• /
• pp.290-292
• /
• 2011

본 논문에서는 얼굴 요소의 자연적 특징과 PCA(Principal Component Analysis)를 융합한 얼굴인식 알고리즘을 소개한다. 지금까지 PCA 를 비롯한 다양한 얼굴인식 알고리즘이 소개되었지만, 얼굴영상을 하나의 '신호'혹은 '벡터'로 간주하여 이를 수학적 접근법으로 풀이하는 방법이 대부분이었다. 이에 본 논문에서는 템플릿 정합 기법을 이용하여 눈썹, 눈, 턱 등을 형태에 따라 분류하는 특징 분류기를 통하여 그룹을 나누고, 각 그룹별로 PCA 분류를 진행하는 2 단계 알고리즘을 구현하였다. 이를 CMU-PIE 데이터베이스를 이용해 검증하고, 실험 결과를 논의하였다.

• Tribology and Lubricants
• /
• v.14 no.2
• /
• pp.49-56
• /
• 1998

The thermal deformation of the contact seal components has been analyzed using the finite element method. The temperature distributions, the thermal deformations and contact stresses are solved numerically for the contact surface with wear coning effects. The thermal deformation is always shown to distort the sealing surface along the radius of the seal ring. The results show that the deformations of inner radius side are significant compared with those of outer radius. Thus, the thermal deformation due to thermal heatings may promote the coned face wear or wear related thermal cracks at the contacting face of the seal ring component.

• Journal of information and communication convergence engineering
• /
• v.9 no.2
• /
• pp.207-211
• /
• 2011

This paper presents a method for facial feature representation and recognition from the Covariance Matrices of the Gabor-filtered images. Gabor filters are a very powerful tool for processing images that respond to different local orientations and wave numbers around points of interest, especially on the local features on the face. This is a very unique attribute needed to extract special features around the facial components like eyebrows, eyes, mouth and nose. The Covariance matrices computed on Gabor filtered faces are adopted as the feature representation for face recognition. Geodesic distance measure is used as a matching measure and is preferred for its global consistency over other methods. Geodesic measure takes into consideration the position of the data points in addition to the geometric structure of given face images. The proposed method is invariant and robust under rotation, pose, or boundary distortion. Tests run on random images and also on publicly available JAFFE and FRAV3D face recognition databases provide impressively high percentage of recognition.

• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 1998.04a
• /
• pp.149-158
• /
• 1998

The thermal deformation of the contact seal components has been analyzed using the finite element method. The temperature distributions, the thermal deformations and contact stresses are solved numerically for the contact surface with wear coning effects. The thermal deformation is always shown to distort the sealing surface along the radius of the seal ring. The results show that the deformations of inner radius side are significant compared with those of outer radius. Thus, the thermal deformation due to thermal heatings may promote the coned face wear or wear related thermal cracks at the contacting face of the seal ring component.

• International Journal of Contents
• /
• v.1 no.2
• /
• pp.1-4
• /
• 2005

In this paper, we compare 5 weighted distance measures between feature vectors with respect to the recognition performance of the principal component analysis(PCA)-based face recognition method, and propose modified weighted distance. The proposed method was modification of z, the weighted vector. The simulation was performed using the ORL face database, showed the best result for some weighted distances such as weighted manhattan, weighted angle-based, weighted modified manhattan, and weighted modified SSE. We also showed that using some various values of z(weighted values) we can achieve better recognition results that using the existing weighted value.

• Journal of Korea Multimedia Society
• /
• v.15 no.1
• /
• pp.40-50
• /
• 2012

Face recognition is a biometric technology used to identify individuals based on facial feature information. Previous studies of face recognition used features including the eye, mouth and nose; however, there have been few studies on the effects of using other facial components, such as the eyebrows and chin, on recognition performance. We measured the recognition accuracy affected by these facial components, and compared the differences between computer-based and human-based facial recognition methods. This research is novel in the following four ways compared to previous works. First, we measured the effect of components such as the eyebrows and chin. And the accuracy of computer-based face recognition was compared to human-based face recognition according to facial components. Second, for computer-based recognition, facial components were automatically detected using the Adaboost algorithm and active appearance model (AAM), and user authentication was achieved with the face recognition algorithm based on principal component analysis (PCA). Third, we experimentally proved that the number of facial features (when including eyebrows, eye, nose, mouth, and chin) had a greater impact on the accuracy of human-based face recognition, but consistent inclusion of some feature such as chin area had more influence on the accuracy of computer-based face recognition because a computer uses the pixel values of facial images in classifying faces. Fourth, we experimentally proved that the eyebrow feature enhanced the accuracy of computer-based face recognition. However, the problem of occlusion by hair should be solved in order to use the eyebrow feature for face recognition.

• Steel and Composite Structures
• /
• v.34 no.6
• /
• pp.803-818
• /
• 2020

Semi-rigid connections with blind bolts could solve the difficulty that traditional high strength bolts were unavailable to splice a steel/composite beam to a closed section column. However, insufficient investigations have focused on the performance of semi-rigid connection to square concrete filled double-skin steel tubular (CFDST) columns. In this paper, a component model was developed to evaluate the mechanical behavior of semi-rigid composite connections to CFDST columns considering the stiffness and strength of column face in compression and column web in shear which were determined by the load transfer mechanism and superstition method. Then, experimental investigations on blind bolted composite joints to square CFDST columns were conducted to validate the accuracy of the component model. Dominant failure modes of the connections were analyzed and this type of joint behaved semi-rigid manner. More importantly, strain responses of CFDST column web and tubes verified that stiffness and strength of column face in compression and column web in shear significantly affected the connection mechanical behavior owing to the hollow part of the cross-section for CFDST column. The experimental and analytical results showed that the CFDST column to steel-concrete composite beam semi-rigid joints could be employed for the assembled structures in high intensity seismic regions.

• Steel and Composite Structures
• /
• v.33 no.5
• /
• pp.681-697
• /
• 2019

This paper numerically assesses the initial stiffness and moment capacity of stainless steel composite bolted joints with concrete-filled circular tubular (CFCT) columns. By comparing with existing design codes including EN 1993-1-8 and AS/NZS 2327, a modified component method was proposed to better predict the flexural performance of joints involving circular columns and curved endplates. The modification was verified with independent experimental results. A wide range of finite element models were then developed to investigate the elastic deformations of column face in bending which contribute to the corresponding stiffness coefficient. A new design formula defining the stiffness coefficient of circular column face in bending was proposed through regression analysis. Results suggest that a factor for the stiffness coefficient of endplate in bending should be reduced to 0.68, and more contribution of prying forces needs to be considered. The modified component method and proposed formula are able to estimate the structural behaviour with reasonable accuracy. They are expected to be incorporated into the current design provisions as supplementary for beam-to-CFCT column joints.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 2004.07a
• /
• pp.347-347
• /
• 2004

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.597-600
• /
• 2007

Face is considered to be one of the biometrics in person identification. But Face recognition is a high dimensional pattern recognition problem. Even low-resolution face images generate huge dimensional feature space. The aim of this paper is to present a fast feature extraction method for real time human face recognition. first, It compute eigen-vector and eigen-value by Principle component analysis on inputed human face image, and propose method of feature extraction that make feature vector by apply gabor filter to computed eigen-vector. And it compute feature value which multiply by made eigen-value. This study simulations performed using the ORL Database.