• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.423-424
• /
• 2006

This paper describes a 3D face recognition using different devices for 3D faces and input faces which include several different pose. Before the recognition stage, through the EC-SVD, all data have to be preprocessed and normalized. At recognition stage, we propose the multi-point signature method for measuring facial surface information. And we use the root mean square error for matching. From the experiment results, we have 92.5% recognition rate.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.615-618
• /
• 2005

This dissertation proposes a technique of user centered document ranking using User Profile to provide more satisfied results whitch feflect preference of speccific user. User Profile is comstructed to represent his reference of the user.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.21 no.8
• /
• pp.1311-1321
• /
• 1997

In multibody dynamics, differential and algebraic equations which can satisfy both equation of motion and kinematic constraint equation should be solved. To solve these equations, coordinate partitioning method and constraint stabilization method are commonly used. In the coordinate partitioning method, the coordinates are divided into independent and dependent and coordinates. The most typical coordinate partitioning method are LU decomposition, QR decomposition, and SVD (singular value decomposition). The objective of this research is to find an efficient coordinate partitioning method in the dynamic analysis of flexible multibody systems. Comparing two coordinate partitioning methods, i.e. LU and QR decomposition in the flexible multibody systems, a new hybrid coordinate partitioning method is suggested for the flexible multibody analysis.

• Journal of Korea Multimedia Society
• /
• v.12 no.6
• /
• pp.785-793
• /
• 2009

This paper proposes a signature using dominant singular values for video sequence matching. By considering the input image as matrix A, a partition procedure is first performed to separate the matrix into non-overlapping sub-images of a fixed size. The SVD(Singular Value Decomposition) process decomposes matrix A into a singular value-singular vector factorization. As a result, singular values are obtained for each sub-image, then k dominant singular values which are sufficient to discriminate between different images and are robust to image size variation, are chosen and normalized as the signature for each block in an image frame for matching between the reference video clip and the query one. Experimental results show that the proposed video signature has a better performance than ordinal signature in ROC curve.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.28-30
• /
• 2011

본 논문에서는 특이값 분해(Singular Value Decomposition)을 이용하여 이미지의 주파수 영역 내에 정보를 은닉하는 방법을 제시한다. 이미지를 주파수 영역으로 변환하기 위하여 블록 단위로 이산 코사인 변환(Discrete Cosine Transform)을 수행한다. 이후 인접한 네 블록의 DC 값들로 구성된 행렬의 특이값을 은닉하고자 하는 정보에 따라 변환한다. 원래의 DC 값은 정보에 따라 변환된 DC 값으로 대체되고 역 이산 코사인 변환(Inverse Discrete Cosine Transform)을 수행하여 정보가 은닉된 이미지를 얻는다. 제안하는 알고리즘의 성능을 분석하기 위해 JPEG(Joint Photographic Coding Experts Group), 선명화(Sharpening), 히스토그램 등화(Histogram Equalization)와 같이 다양한 이미지 변화를 거친 후, 은닉된 정보의 신뢰도를 비교한다.

• Journal of the Korean Magnetic Resonance Society
• /
• v.6 no.1
• /
• pp.12-19
• /
• 2002

A shift-averaged Haar wavelet transform was introduced as a new and excellent tool to distinguish real peaks from the noise contaminated NMR signals. It is based on Haar wavelet transform and translation-invariant denoising process. Donoho＇s universal threshold was newly introduced to the shift-averaged Haar wavelet transform for the purpose of automated noise suppression, and was quantitatively compared with the conventional uniform threshold method in terms or threshold and signal to noise ratio (SNR). New algorithm was combined with a routine to suppress a large solvent peak by singular value decomposition (SVD). Combined algorithm was applied to the real spectrum that containing large solvent peak.

• Journal of Mechanical Science and Technology
• /
• v.17 no.5
• /
• pp.698-707
• /
• 2003

A new quadratic response surface modeling method is presented. In this method, the incomplete small composite design (ISCD) is newly proposed to .educe the number of experimental runs than that of the SCD. Unlike the SCD, the proposed ISCD always gives a unique design assessed on the number of factors, although it may induce the rank-deficiency in the normal equation. Thus, the singular value decomposition (SVD) is employed to solve the normal equation. Then, the duality theory is used to newly develop the conservative least squares fitting (CONFIT) method. This can directly control the ever- or the under-estimation behavior of the approximate functions. Finally, the performance of CONFIT is numerically shown by comparing its'conservativeness with that of conventional fitting method. Also, optimizing one practical design problem numerically shows the effectiveness of the sequential approximate optimization (SAO) combined with the proposed ISCD and CONFIT.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.147-150
• /
• 2001

본 논문은 비최소 위상을 가지는 시스템에 대한 역변환 문제를 실험적으로 고찰, 연구하였다. 일반적으로 선형적이고 인과적인 시스템의 입$cdot$ 출력관계는 행렬형태로 공식화할 수 있다. 최소위상(minimum phase) 시스템의 시스템행렬은 항상 역행렬이 존재하며 안정적이지만 비최소 위상(non-minimum phase)시스템의 시스템행렬은 근사특이(near-singular)행렬 또는 특이(singular) 행렬이므로 불량조건(ill-conditioning)이 발생하고 역변환이 존재할 수 없다. 비최소 위상 시스템의 역변환 문제는 다른 과정을 포함하지 않고서는 인과적이고 안정적인 역변환 필터를 가질 수 없다. 따라서 역변환 필터의 구현을 위해 SVD(singular value decomposition)를 이용하였다. 비최소 위상 시스템인 경우 시스템행렬은 하나이상의 매우 작은 특이 값을 가지며 이것은 시스템의 위상정보를 가진다. 이 성질을 이용하여 시스템의 근사적인 역변환 필터를 구현하고 비최소 위상을 갖는 외팔보에 대해 실험적으로 검증하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.271-273
• /
• 2002

추천 시스템에서 사용되고 있는 중요한 방법인 협력적 여과는 유사한 사용자들에 기초하여 그 사용자들이 선호하는 아이템을 교차 추천을 해주는 방법이다. 사용자들에 대한 정보는 아이템을 평가한 등급에 기초하며, 그 평가 등급 패턴이 유사한 사용자를 찾게 된다. 협력적 여과는 사용자와 정보의 증가에 따라서 성능이 저하되는 문제점을 가지고 있다. 이러한 문제점을 해결하기 위하여 SVD, PCA, LSI와 같은 차원 감소 방법이 제시되어 왔으나, 이러한 방법은 계산 비용이 크다는 단점을 가지고 있다. 따라서, 계산 비용이 적고, 정확성에 있어서도 충분히 정확한 임시 사상이 최근에 주목을 받고 있다. 본 논문에서는 임의 사상을 이용한 차원 감소 방법이 협력적 여과에 미치는 효과를 실험을 통하여 제시한다. 실험적으로, 임의 사상 방법은 협력적 여과에서 충분히 정확한 성능을 보였다.

• Journal of the Chungcheong Mathematical Society
• /
• v.27 no.4
• /
• pp.675-688
• /
• 2014

In this paper, we present an efficient way to determine a suitable value of the regularization parameter using the global generalized cross validation and analyze the experimental results from preconditioned global conjugate gradient linear least squares(Gl-CGLS) method in solving image deblurring problems. Preconditioned Gl-CGLS solves general linear systems with multiple right-hand sides. It has been shown in [10] that this method can be effectively applied to image deblurring problems. The regularization parameter, chosen from the global generalized cross validation, with preconditioned Gl-CGLS method can give better reconstructions of the true image than other parameters considered in this study.