• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.10
• /
• pp.2121-2128
• /
• 2012

This paper proposed the real time face area detection using Wavelet transform and the strong detection algorithm that satisfies the efficiency of computation and detection performance at the same time was proposed. The detected face image recognizes the face by configuring the low-dimensional face symbol through the principal component analysis. The proposed method is well suited for real-time system construction because it doesn't require a lot of computation compared to the existing geometric feature-based method or appearance-based method and it can maintain high recognition rate using the minimum amount of information. In addition, in order to reduce the wrong recognition or recognition error occurred during face recognition, the input symbol of Hidden Markov Model is used by configuring the feature values projected to the unique space as a certain symbol through clustering algorithm. By doing so, any input face will be recognized as a face model that has the highest probability. As a result of experiment, when comparing the existing method Euclidean and Mahananobis, the proposed method showed superior recognition performance in incorrect matching or matching error.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.885-888
• /
• 2005

본 논문에서는 카메라가 장착된 2 족 보행 로봇을 이용한 얼굴 검출 및 추적 시스템을 제안한다. 제안된 시스템은 PCA(Principal Component Analysis) 기반의 시스템으로서 얼굴을 검출하기 위해 먼저, 스킨칼라 정보와 모션 정보를 사용하고, 그 이후에 PCA 를 사용하여 스킨칼라 영역에서 실제 얼굴이 있는지를 검증 한다. 새로 검출된 얼굴과 이전에 추적되는 얼굴 사이의 동일성은 Eigenspace 상에서의 Euclidian distance 를 사용하여 검증한다. 2 족 보행 로봇이 얼굴을 추적하기 위해서는, 검출된 얼굴 영역이 카메라 스크린 중심 영역에 계속 유지되도록 로봇의 움직임을 조절해 간다. 제안된 시스템은 움직임이 많고, 조명 변화나 배경의 변화가 심한 환경에서도, 얼굴을 잘 검출하고 추적 하였으며, 다른 2 족 보행 시스템이나 인간과 로봇의 상호작용을 위한 제스처 인식 시스템으로의 확장도 가능하다.

• Journal of Integrative Natural Science
• /
• v.5 no.2
• /
• pp.120-126
• /
• 2012

This paper describes the algorithm that lowers the dimension, maintains the gesture recognition and significantly reduces the eigenspace configuration time by combining the higher correlation feature information and Principle Component Analysis. Since the suggested method doesn't require a lot of computation than the method using existing geometric information or stereo image, the fact that it is very suitable for building the real-time system has been proved through the experiment. In addition, since the existing point to point method which is a simple distance calculation has many errors, in this paper to improve recognition rate the recognition error could be reduced by using several successive input images as a unit of recognition with K-Nearest Neighbor which is the improved Class to Class method.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2003.06a
• /
• pp.50-53
• /
• 2003

본 논문에서는 multi-camera를 이용한 인터넷 기반의 지능적 감시 시스템을 제안한다. 제안된 시스템은 두 종류의 카메라, static camera와 pan-tilt camera, 를 이용하여 출입구를 감시하고, 비인가자를 추적한다. static camera는 출·입을 검출하고 출입자를 인가자와 비인가자로 분류하는데 이용되고, pan-tilt camera는 비인가자로 분류된 출입자를 추적하는데 이용된다. 제안된 시스템은 세 가지 단계: 출입구 감시, 출입자 검출 및 분류(인가자/비인가자), 비인가자 추적으로 구성된다 출입구 감시는 출입문의 밝기값 변화를 이용한다 출입자 검출 및 분류는 skin color 모델과 얼굴 크기, 위치와 관련된 휴리스틱을 이용하여 얼굴을 검출하고, PCA(Principal Component Analysis)를 이용한 eigenspace상에서의 유클리디언 디스턴스로 템플릿 얼굴과 입력 얼굴의 유사도를 계산하여 인가자인지 비인가자인지 분류한다. 비인가자 추적은 pan-tilt 카메라를 이용하여, static camera에서 분류된, 비인가자의 움직임을 검출하고 카메라를 제어함으로써 추적한다 제안된 시스템은 무인 감시 상황에서 비인가자의 출입시 감시자에게 경고 신호를 제공하고, 감시지역에서 사건 발생시, 사건의 개요를 파악하는 중요한 정보를 빠른 시간에 제공할 수 있다는 장점을 가진다.

• International journal of advanced smart convergence
• /
• v.9 no.4
• /
• pp.192-197
• /
• 2020

In this study, we try to find ways to recognize face recognition more stably and to improve the effectiveness and reliability of face recognition. In order to improve the face recognition rate, a lot of data must be used, but that does not necessarily mean that the recognition rate is improved. Another criterion for improving the recognition rate can be seen that the top/bottom of the recognition rate is determined depending on how accurately or precisely the degree of classification of the data to be used is made. There are various methods for classification analysis, but in this study, classification analysis is performed using a support vector machine (SVM). In this study, feature information is extracted using a normalized image with rotation information, and then projected onto the eigenspace to investigate the relationship between the feature values through the classification analysis of SVM. Verification through classification analysis can improve the effectiveness and reliability of various recognition fields such as object recognition as well as face recognition, and will be of great help in improving recognition rates.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.615-618
• /
• 2002

This paper proposes a real-time face detection and tracking a method in complex backgrounds. The proposed method is based on the principal component analysis (PCA) technique. For the detection of a face, first, we use a skin color model and motion information. And then using the PCA technique the detected regions are verified to determine which region is indeed the face. The tracking of a face is based on the Euclidian distance in eigenspace between the previously tracked face and the newly detected faces. Camera control for the face tracking is done in such a way that the detected face region is kept on the center of the screen by controlling the pan/tilt platform. The proposed method is extensible to other systems such as teleconferencing system, intruder inspection system, and so on.

• Journal of Korea Multimedia Society
• /
• v.7 no.8
• /
• pp.1035-1045
• /
• 2004

In this paper, we describe a method that can recognize gestures and evaluate the degree of the gestures from sequential gesture images by using Gesture Feature Space. The previous popular methods based on HMM and neural network have difficulties in recognizing the degree of gesture even though it can classify gesture into some kinds. However, our proposed method can recognize not only posture but also the degree information of the gestures, such as speed and magnitude by calculating distance among the position vectors substituting input and model images in parametric eigenspace. This method which can be applied in various applications such as intelligent interface systems and surveillance systems is a simple and robust recognition algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.7
• /
• pp.1439-1446
• /
• 2011

This paper describes the algorithm that lowers the dimension, maintains the object recognition and significantly reduces the eigenspace configuration time by combining the higher correlation feature information and Principle Component Analysis. Since the suggested method doesn't require a lot of computation than the method using existing geometric information or stereo image, the fact that it is very suitable for building the real-time system has been proved through the experiment. In addition, since the existing point to point method which is a simple distance calculation has many errors, in this paper to improve recognition rate the recognition error could be reduced by using several successive input images as a unit of recognition with K-Nearest Neighbor which is the improved Class to Class method.

• The Journal of Engineering Geology
• /
• v.6 no.2
• /
• pp.83-93
• /
• 1996

A method is proposed to estimate aquifer parameters in a heterogeneous and anisotropic aquifer under steady-state groundwater flow conditions on the basis of maximum likelihood concept. Zonation method is adopted for parameterization, and estimation errors are analyzed by examining the estimation error covariance matrix in the eigenspace. This study demonstrates the ability of the proposed model to estimate parameters and helps to understand the characteristics of the inverse problem. This study also explores various features of the inverse methodology by applying it to a set of field data of the Taegu area. In the field example, transmissivities were estimated under three different zonation patterns. Recharge rates in the Taegu area were also estimated using MODINV which is an inverse model compatible with MODFLOW.The estimation results indicate that anisotropy of aquifer parameters should be considered for the crystalline rock aquifer which is the dominant aquifer system in Korea.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.6
• /
• pp.1029-1040
• /
• 2011

In this paper we propose an intelligent navigation algorithm for real world problem which can build a map without localization. Proposed algorithm operates online and furthermore does not require many memories for applying real world problem. After applying proposed algorithm to toy and huge data set, it does not require to calculate a whole eigenspace and need less memory compared to existing algorithm. Thus we can obtain that proposed algorithm is suitable for real world mobile navigation algorithm.