• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.565-567
• /
• 2010

일반적으로 얼굴 인식 방법에는 템플릿 기반 통계적 기법들이 사용되고 있다. 이 방법들은 2차원 영상을 고차원 벡터로 표현하여 특징을 추출한다. 그러나 많은 이미지와 비디오 데이터는 본래 텐서로 표현된다. 따라서, 본 논문에서는 벡터 표현보다는 직접적인 텐서 표현으로 특징들을 추출하기 위해 텐서 얼굴의 다선형 주성분 분석(MPCA: Multilinear Principal Component Analysis) 기법을 이용한 동영상 기반 얼굴인식에 대해 다룬다. 마지막으로, u-로봇 테스트베드 환경에서 구축된 얼굴 인식 데이터 베이스를 이용하여 제안된 방법과 기존 방법들의 인식처리시간과 성능을 비교한다.

• Journal of KIISE:Software and Applications
• /
• v.36 no.8
• /
• pp.664-672
• /
• 2009

Recently, studies on utilizing tensor expression on image data analysis and processing have been attracting much interest. The purpose of this study is to develop an efficient system for classifying image patterns by using second order tensor expression. To achieve the goal, we propose a data generation model expressed by class factors and environment factors with second order tensor representation. Based on the data generation model, we define a function for measuring similarities between two images. The similarity function is obtained by estimating the probability density of environment factors using a matrix normal distribution. Through computational experiments on a number of benchmark data sets, we confirm that we can make improvement in classification rates by using second order tensor, and that the proposed similarity function is more appropriate for image data compared to conventional similarity measures.

• Smart Media Journal
• /
• v.7 no.4
• /
• pp.90-98
• /
• 2018

A Multilinear LDA Method of Tensor Representation for ECG Signal Based Individual Identification Electrocardiogram signals, included in the cardiac electrical activity, are often analyzed and used for various purposes such as heart rate measurement, heartbeat rhythm test, heart abnormality diagnosis, emotion recognition and biometrics. The objective of this paper is to perform individual identification operation based on Multilinear Linear Discriminant Analysis (MLDA) with the tensor feature. The MLDA can solve dimensional aspects of classification problems in high-dimensional tensor, and correlated subspaces can be used to distinguish between different classes. In order to evaluate the performance, we used MPhysionet's MIT-BIH database. The experimental results on this database showed that the individual identification by MLDA outperformed that by PCA and LDA.

• Journal of KIISE
• /
• v.43 no.8
• /
• pp.910-918
• /
• 2016

A tensor is a multi-dimensional array that represents many data such as (user, user, time) in the social network system. A tensor generator is an important tool for multi-dimensional data mining research with various applications including simulation, multi-dimensional data modeling/understanding, and sampling/extrapolation. However, existing tensor generators cannot generate sparse tensors like real-world tensors that obey power law. In addition, they have limitations such as tensor sizes that can be processed and additional time required to upload generated tensor to distributed systems for further analysis. In this study, we propose TeT, a distributed tera-scale tensor generator to solve these problems. TeT generates sparse random tensor as well as sparse R-MAT and Kronecker tensor without any limitation on tensor sizes. In addition, a TeT-generated tensor is immediately ready for further tensor analysis on the same distributed system. The careful design of TeT facilitates nearly linear scalability on the number of machines.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.5
• /
• pp.136-146
• /
• 2015

The active control of a vehicle based on vehicle recognition is one of key technologies for the intelligent vehicle, and the part-based image representation is necessary to recognize vehicles with only partial shapes of vehicles especially in urban scene where occlusions frequently occur. In this paper, we implemented a part-based image representation scheme using non-negative tensor factorization(NTF) and realized a robust vehicle recognition system using the NTF feature. The result shows that the proposed method gives more intuitive part-based representation and more robust recognition in urban scene.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.11a
• /
• pp.7-8
• /
• 2007

생체데이터란 인간개체로부터 얻을 수 있는 고유의 생체신호를 통틀어 일컫는 것이다. 본 연구에서는 생체데이터를 위한 팩터 분석 모델에 텐서 개념을 적용하여, 2차 텐서로 표현된 데이터를 위한 생성모델을 제안한다. 이 모델을 바탕으로 데이터로부터 분류에 핵심이 되는 정보를 안정적으로 추출하여 유사도 함수를 만들고 분류를 수행하는 방법을 제안한다. 실험을 통해 제안하는 방법이 기존의 벡터형태의 데이터에 대한 생성 모델을 사용한 경우보다 우수한 성능을 가짐을 확인할 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.11a
• /
• pp.295-297
• /
• 2011

본 논문에서는 동적얼굴영상으로부터 감정인식을 위해 벡터 표현 보다는 직접적인 텐서 표현으로 특징들을 추출하는 텐서 기반 다선형 주성분분석(MPCA: Multilinear Principal Component Analysis) 기법을 사용한다. 사람 6가지의 얼굴 표정을 사용하는데 한 사람의 각 표정마다 5프레임으로 묶어서 텐서 형태로 취하여 특징을 추출하고 인식한다. 시스템의 성능 평가는 CNU 얼굴 감정인식 데이터베이스를 이용하여 특징점 개수와 성능척도에 따른 실험을 수행하여 제시된 방법의 유용성에 관해 살펴본다.

• The Journal of Society for e-Business Studies
• /
• v.21 no.4
• /
• pp.1-14
• /
• 2016

Semantic search is known as a series of activities and techniques to improve the search accuracy by clearly understanding users' search intent without big cognitive efforts. Usually, semantic search engines requires ontology and semantic metadata to analyze user queries. However, building a particular ontology and semantic metadata intended for large amounts of data is a very time-consuming and costly task. This is why commercialization practices of semantic search are insufficient. In order to resolve this problem, we propose a novel semantic search method which takes advantage of our previous semantic tensor space model. Since each term is represented as the 2nd-order 'document-by-concept' tensor (i.e., matrix), and each concept as the 2nd-order 'document-by-term' tensor in the model, our proposed semantic search method does not require to build ontology. Nevertheless, through extensive experiments using the OHSUMED document collection and SCOPUS journal abstract data, we show that our proposed method outperforms the vector space model-based search method.

• The KIPS Transactions:PartB
• /
• v.15B no.3
• /
• pp.205-210
• /
• 2008

A new approach is proposed for restoration of corrupted regions and segmentation in natural text images. The challenge is to fill in the corrupted regions on the basis of color feature analysis by second order symmetric stick tensor. It is show how feature analysis can benefit from analyzing features using tensor voting with chromatic and achromatic components. The proposed method is applied to text images corrupted by manifold types of various noises. Firstly, we decompose an image into chromatic and achromatic components to analyze images. Secondly, selected feature vectors are analyzed by second-order symmetric stick tensor. And tensors are redefined by voting information with neighbor voters, while restore the corrupted regions. Lastly, mode estimation and segmentation are performed by adaptive mean shift and separated clustering method respectively. This approach is automatically done, thereby allowing to easily fill-in corrupted regions containing completely different structures and surrounding backgrounds. Applications of proposed method include the restoration of damaged text images; removal of superimposed noises or streaks. We so can see that proposed approach is efficient and robust in terms of restoring and segmenting text images corrupted.

• Proceedings of the Korean Society of Soil and Groundwater Environment Conference
• /
• 2003.04a
• /
• pp.221-224
• /
• 2003

이 연구는 국내의 균열암반에 대한 지하수 유동 연구가 대수층이 등방이라는 가정하에 진행피고 있는 방법에서 벗어나 대수층이 이방성을 띤다는 가정하에 대수층의 수리적 이방성을 해석하는데 중점을 두었다. 수리시험은 30.91 $m^3$/day로 BH-1공에서 300분간 양수였으며, 각각의 관측공 BH-2, BH-3, BH-4, 및 BH-5공에서 시간에 따른 수위강하를 관측하였다. 수리시험에 의해 얻어진 시간별 수위강하 자료를 이용하여 Jacob(1950)의 직선법에 의해서 직선의 기울기(m)와 수위강하가 영이 되는 지점에서의 시간( $t_{0}$)을 계산하였다. 대수층의 수리학적 이방성 텐서 (tensor) 즉, 최대투수량계수텐서 ( $T_{ξξ}$)와 최소투수량계수텐서 ( $T_{ηη}$)를 산출하기 위해서 Stewart(1973)에 의해서 정립된 정규최소제곱(Ordinary least-square)방법을 적용하였으며, 이 방법은 관측공이 최소한 4개를 필요로 한다. 그 결과로, $T_{ξξ}$는 12.21 $m^2$/day이고 $T_{ηη}$는 10.47 $m^2$/day로 산출되었다. 최대투수량계수텐서의 방향은 Nl9.13$^{\circ}$E 이고 이방성율은 1.17로 산출되었다. BH-1공에서 수리시험시 대수층의 이방성은 등방성에 가깝게 표현되었다. 이는 연구지역 대수층이 다수의 균열에 의해서 수리적 상호연결성이 고루 분포된 것으로 판단된다.