• The KIPS Transactions:PartB
• /
• v.12B no.1 s.97
• /
• pp.9-16
• /
• 2005

This paper focuses on the study of the face authentication system and the robustness of fact authentication methods under illumination changes. Four different face authentication methods are tried. These methods are as fellows; PCA(Principal Component Analysis), GMM(Gaussian Mixture Modeis), 1D HMM(1 Dimensional Hidden Markov Models), Pseudo 2D HMM(Pseudo 2 Dimensional Hidden Markov Models). Experiment results involving an artificial illumination change to fate images are compared with each other. Face feature vector extraction based on the 2D DCT(2 Dimensional Discrete Cosine Transform) if used. Experiments to evaluate the above four different fate authentication methods are carried out on the ORL(Olivetti Research Laboratory) face database. Experiment results show the EER(Equal Error Rate) performance degrade in ail occasions for the varying ${\delta}$. For the non illumination changes, Pseudo 2D HMM is $2.54{\%}$,1D HMM is $3.18{\%}$, PCA is $11.7{\%}$, GMM is $13.38{\%}$. The 1D HMM have the bettor performance than PCA where there is no illumination changes. But the 1D HMM have worse performance than PCA where there is large illumination changes(${\delta}{\geq}40$). For the Pseudo 2D HMM, The best EER performance is observed regardless of the illumination changes.

• 한국체육학회지인문사회과학편
• /
• v.57 no.4
• /
• pp.387-394
• /
• 2018

The purpose of this study is to provide information regarding the strategies by identifying the main variables that determines the winning team based on the records of all games of the 2017 IIHF World Championship Top league. 64 matches were analyzed for the study. 6 variables were analyzed which included ratio of saves, shots on goal, penalties in minutes, time for power play, power play goals, and face off wins. Logistic regression analysis (LRA), multiple regression analysis (MRA), and principal component analysis (PCA) were implemented to examine the relationship between win and loss. In case of LRA, shots on goal (p<.001), face-off wins (p<.001) had significantly positive relation to winning of game whereas, penalties in minutes (p<.01) and time on power play (p<.01) had significantly negative. Using MRA, win percentage was calculated which had significant positive correlation to ratio of saves (p<.01) and face-off wins (p<.001) whereas, a significant negative with penalties in minutes (p<.001). For PCA, the winning team consisted of penalty, attack, and defense factors whereas, losing teams consisted only the attack and defense factors.

• Proceedings of the KIEE Conference
• /
• 2008.04a
• /
• pp.101-102
• /
• 2008

얼굴인식 분야에서 PCA(Principal Component Analysis) 기반 알고리즘은 비교적 간단한 구조와 높은 인식률로 인해 많이 사용되고 있지만 조명이나 얼굴 포즈 변화에 민감하다는 단점이 있다[1]. 이런 단점을 해결하기 위한 노력으로 PCA를 다른 얼굴인식 알고리즘과 결합함으로서 조명과 포즈 변화에 강인한 얼굴인식을 위만 연구가 현재 활발히 진행되고 있다. 본 논문은 PCA기반 얼굴인식에서 조명이 다양하게 변할 때 이에 따른 인식률의 변화와, 인식이 실패했을 경우에 인식 대상이 유사도 상위후보군에 들어가는지를 조사함으로서 PCA기반 알고리즘의 신뢰도를 확인하고자 한다. 이를 위해 Yale Face Database H와 Extended Yale Face Database B를 이용하여 실험한 결과 약 93%의 인식 성공률을 확인했으며, 7%의 인식 실패한 영상의 경우 그 인식하고자 했던 얼굴이 유사도를 기준으로 정렬된 학습 영상에서 상위 후보군에 속한다는 실험 결과를 얻음으로서 PCA기반 얼굴 인식 알고리즘의 신뢰성을 확인할 수 있었다.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.172-174
• /
• 2004

This paper proposes an integerized approach to solve PCA(Principal Component Analysis) feature extract procedure mainly used for the face recognition. A simple conversion to integer values has the risk to reduce the precision compared to that of the floating points operations. We integerize the PC variables by normalizing with the maximum of them, and show the efficiency of the proposed scheme by comparing the results to those of the float/double precisions. The integerized scheme is expected to be an efficient way for the real-time implementation of PCA's recognition stage, because integer operator is more desirable than floating point ones. Further research is to find a way to implement face detection and to measure the distances from the stored PCs for the full real-time face recognition.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.869-870
• /
• 2008

Illumination variation is the most significant factor affecting face recognition rate. In this paper, we propose adaptive smoothing based on combined most significant bit (CMSB) - plane and local entropy for robust face recognition in varying illumination. Illumination normalization is achieved based on Retinex method. The proposed method has been evaluated based on the CMU PIE database by using Principle Component Analysis (PCA).

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.3
• /
• pp.971-976
• /
• 2000

In this paper a new method for head gesture recognition is proposed. A the first stage, face image data are transformed into low dimensional vectors by principal component analysis (PCA), which utilizes the high correlation between face pose images. The a self organization map(SM) is trained by the transformed face vectors, in such a that the nodes at similar locations respond to similar poses. A sequence of poses which comprises each model gesture goes through PCA and SOM, and the result is stored in the database. At the recognition stage any sequence of frames goes through the PCA and SOM, and the result is compared with the model gesture stored in the database. To improve robustness of classification, probabilistic relaxation labeling(PRL) is used, which utilizes the contextural information imbedded in the adjacent poses.

• 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.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2011.06a
• /
• pp.29-30
• /
• 2011

본 논문에서는 스마트폰 얼굴인식을 통해 출입을 관리하는 시스템을 설계하고 구현한다. 이를 위해 스마트폰에서 얼굴인식을 위한 사용가능한 다양한 알고리즘을 조사하였다. 얼굴 인식의 첫 단계는 얼굴검출이며 다음 단계는 얼굴인식이다. 얼굴 검출을 위해서는 컬러 세그멘테이션, 템플릿매칭 등의 알고리즘을 적용하였으며, 얼굴 인식을 위해서는 PCA(Principal Component Analysis)에 기반을 둔 Eigenface와 LDA(Linear Discriminant Analysis)에 기반을 둔 Fisherface를 비교하여 구현하고 적용하였다. 스마트 폰의 제한된 하드웨어에서 얼굴인식 시스템을 구현하는 관계로 알고리즘의 정확도와 알고리즘의 계산 복잡도 사이에서 적절한 조절이 필요하였다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.3
• /
• pp.54-60
• /
• 2010

The local appearance-based method is one of the face recognition methods that divides face image into small areas and extracts features from each area of face image using statistical analysis. It collects classification results of each area and decides identity of a face image using a voting scheme by integrating classification results of each area of a face image. The conventional local appearance-based method divides face images into small pieces and uses all the pieces in recognition process. In this paper, we propose a local appearance-based method that makes use of only the relatively important facial components. The proposed method detects the facial components such as eyes, nose and mouth that differs much from person to person. In doing so, the proposed method detects exact locations of facial components using support vector machines (SVM). Based on the detected facial components, a number of small images that contain the facial parts are constructed. Then it extracts features from each facial component image using principal components analysis (PCA). We compared the performance of the proposed method to those of the conventional methods. The results show that the proposed method outperforms the conventional local appearance-based method while preserving the advantages of the conventional local appearance-based method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.165-170
• /
• 2003

This paper presents an integrated approach to unconstrained face recognition in arbitrary scenes. The front end of the system comprises of a scale and pose tolerant face detector. Scale normalization is achieved through novel combination of a skin color segmentation and log-polar mapping procedure. Principal component analysis is used with the multi-view approach proposed in[10] to handle the pose variations. For a given color input image, the detector encloses a face in a complex scene within a circular boundary and indicates the position of the nose. Next, for recognition, a radial grid mapping centered on the nose yields a feature vector within the circular boundary. As the width of the color segmented region provides an estimated size for the face, the extracted feature vector is scale normalized by the estimated size. The feature vector is input to a trained neural network classifier for face identification. The system was evaluated using a database of 20 person's faces with varying scale and pose obtained on different complex backgrounds. The performance of the face recognizer was also quite good except for sensitivity to small scale face images. The integrated system achieved average recognition rates of 87% to 92%.