• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.749-754
• /
• 2011

In this study, we propose the design of optimized pRBFNNs-based face recognition system using two-dimensional Image and ASM algorithm. usually the existing 2 dimensional face recognition methods have the effects of the scale change of the image, position variation or the backgrounds of an image. In this paper, the face region information obtained from the detected face region is used for the compensation of these defects. In this paper, we use a CCD camera to obtain a picture frame directly. By using histogram equalization method, we can partially enhance the distorted image influenced by natural as well as artificial illumination. AdaBoost algorithm is used for the detection of face image between face and non-face image area. We can butt up personal profile by extracting the both face contour and shape using ASM(Active Shape Model) and then reduce dimension of image data using PCA. The proposed pRBFNNs consists of three functional modules such as the condition part, the conclusion part, and the inference part. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of RBFNNs is represented as three kinds of polynomials such as constant, linear, and quadratic. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of Differential Evolution. The proposed pRBFNNs are applied to real-time face image database and then demonstrated from viewpoint of the output performance and recognition rate.

• Journal of Convergence for Information Technology
• /
• v.9 no.12
• /
• pp.17-23
• /
• 2019

In this paper, I propose a system development methodology that accepts images taken by camera attached to drone in real time while controlling mini drone and recognize and confirm the face of certain person. For the development of this system, OpenCV, Python related libraries and the drone SDK are used. To increase face recognition ratio of certain person from real-time drone images, it uses Deep Learning-based facial recognition algorithm and uses the principle of Triples in particular. To check the performance of the system, the results of 30 experiments for face recognition based on the author's face showed a recognition rate of about 95% or higher. It is believed that research results of this paper can be used to quickly find specific person through drone at tourist sites and festival venues.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.5
• /
• pp.423-430
• /
• 2013

In typical face recognition systems, the frontal view of face is preferred to reduce the complexity of the recognition. Thus individuals may be required to stare into the camera, or the camera should be located so that the frontal images are acquired easily. However these constraints severely restrict the adoption of face recognition to wide applications. To alleviate this problem, in this paper, we address the problem of tracking and recognizing faces in video captured with no environmental control. The face tracker extracts a sequence of the angle/size normalized face images using IVT (Incremental Visual Tracking) algorithm that is known to be robust to changes in appearance. Since no constraints have been imposed between the face direction and the video camera, there will be various poses in face images. Thus the pose is identified using a PCA (Principal Component Analysis)-based pose classifier, and only the pose-matched face images are used to identify person against the pre-built face DB with 5-poses. For face recognition, PCA, (2D)PCA, and $(2D)^2PCA$ algorithms have been tested to compute the recognition rate and the execution time.

• Annual Conference of KIPS
• /
• 2004.05a
• /
• pp.873-876
• /
• 2004

사람의 동작을 인식하는 것에 대한 연구는 게임, 유비쿼터스 컴퓨팅 등의 발전에 따라 그 중요성이 증가하고 있다. 그러나, 대부분의 기존 연구에서는 극히 소수의 동작만을 정의하거나 특정 부위의 동작만을 다루므로 실제 응용에 적용하기에는 적합하지 않다. 본 논문에서는 특정 도메인의 사용 없이, 카메라 영상 입력으로 취득된 동작 패턴 정보만을 이용하여 40종 전신 연속 동작을 구분하는 동작인식 방법을 연구하였다. 인식에 사용된 입력 데이터는 동작자 관절들의 위치 및 회전 값들이며, 다수의 동작들을 인식하기 위해서는 기존의 인식 알고리즘들인 특징기반 인식, HMM, 신경망(Neural Network)등을 사용하여 복합적인 인식 엔진을 구성하여야 했다. 입력 데이터별로 적합한 인식 모듈을 거치게 하기 위해서는, 동작에 의한 입력 데이터에서 동작자 움직임의 주요 신체 부위를 추출함으로써 입력 데이터가 해당 그룹의 인식 모듈로 자동적으로 분류되게 하는 방법을 사용한다. 이는 다층의 인식 레이어 중 복잡도가 증가하는 하위 레이어일수록 자동 분류에 의해 걸러진 데이터만을 취급하게 되므로 효과적이다. 전체 실험 결과 단계별로 약 79~97%의 인식률을 보였다. 이는 향후 특정 컨텍스트 정보와 결합할 때 매우 높은 인식률을 기대할 수 있게 하는 수치이다.

• Journal of Korea Multimedia Society
• /
• v.13 no.3
• /
• pp.400-409
• /
• 2010

This paper presents a position error recognition system when the wafer is mounted in cleaning equipment among the wafer manufacturing processes. The proposed system is to enhance the performance in cost and reliability by preventing the wafer cleaning system from damaging by alerting it when it is put in correct position. The key algorithms are the calibration method between image acquired from camera and physical wafer, a infrared lighting and the design of the filter, and the extraction of wafer boundary and the position error recognition resulting from generation of circle based on least square method. The system is to install in-line process using high reliable and high accurate position recognition. The experimental results show that the performance is good in detecting errors within tolerance.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.468-471
• /
• 2008

이 논문은 응급상황을 인식하기 위하여 어안렌즈를 통해 획득된 영상을 이용하여 기절 동작을 인식하는 방법을 제안한다. 거실의 천장 중앙에 위치한 어안렌즈(fish-eye lens)를 장착한 카메라로부터 화각이 170인 RGB 컬러 모델의 어안 영상을 입력 받은 뒤, 가우시안 혼합 모델 기반의 적응적 배경 모델링 방법을 이용하여 동적으로 배경 영상을 갱신한다. 입력 영상의 평균 밝기를 구하고 평균 밝기가 급격하게 변화하지 않도록 영상 픽셀을 보정한 뒤, 입력 영상과 배경 영상과 차이가 큰 픽셀을 찾음으로써 움직이는 객체를 추출하였다. 그리고 연결되어 있는 전경 픽셀 영역들의 외곽점들을 추적하여 타원으로 매핑하고 움직이는 객체 영역의 형태를 단순화하였다. 이 타원을 추적하면서 어안 렌즈 영상을 투시 영상으로 변환한 다음 타원의 크기 변화, 위치 변화, 이동 속도 정보를 추출하여 이동과 정지 및 움직임이 기절동작과 유사한지를 판단하도록 하였다. 본 논문에서는 실험자로 하여금 기절동작, 걷기 동작, 앉기 동작 등 여러 동작을 취하게 하고 기절 동작 인식을 실험하였다. 실험 결과 어안 렌즈 영상을 그대로 사용하는 것보다 투시 영상으로 변환하여 타원의 크기변화, 위치변화, 이동속도 정보를 이용하는 것이 높은 인식률을 보였다.

• Journal of Korea Multimedia Society
• /
• v.8 no.9
• /
• pp.1177-1186
• /
• 2005

In vision-based interfaces for video games, gestures are used as commands of the games instead of pressing down a keyboard or a mouse. In these Interfaces, unintentional movements and continuous gestures have to be permitted to give a user more natural interface. For this problem, this paper proposes a novel gesture spotting method that combines spotting with recognition. It recognizes the meaningful movements concurrently while separating unintentional movements from a given image sequence. We applied our method to the recognition of the upper-body gestures for interfacing between a video game (Quake II) and its user. Experimental results show that the proposed method is on average $93.36\%$ in spotting gestures from continuous gestures, confirming its potential for a gesture-based interface for computer games.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.3
• /
• pp.103-114
• /
• 2004

This paper deals with a system that is capable of recognizing hand-signals in 3-dimensional space. The system uses 2 color cameras as input devices. Vision-based gesture recognition system is known to be user-friendly because of its contact-free characteristic. But as with other applications using a camera as an input device, there are difficulties under complex background and varying illumination. In order to detect hand region robustly from a input image under various conditions without any special gloves or markers, the paper uses previous position information and adaptive hand color model. The paper defines a hand-signal as a combination of two basic elements such as 'hand pose' and 'hand trajectory'. As an extensive classification method for hand pose, the paper proposes 2-stage classification method by using 'small group concept'. Also, the paper suggests a complementary feature selection method from images from two color cameras. We verified our method with a hand-signal application to our driving simulator.

• 전자공학회논문지 IE
• /
• v.43 no.4
• /
• pp.128-135
• /
• 2006

This paper proposes the control method of fuzzy based sensor fusion by using the self localization of environment, position data by dead reckoning of the encoder and world map from sonic sensors. The proposed fuzzy based sensor fusion system recognizes the object and extracts features such as edge, distance and patterns for generating the world map and self localization. Therefore, this paper has developed fuzzy based control of mobile robot with experimentations in a corridor environment.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.06a
• /
• pp.73-76
• /
• 2013

본 논문은 방송 콘텐츠에서 사용할 수 있는 터치리스 형태의 모션기반 인터랙티브 증강현실 어플리케이션을 제안한다. SD 급 해상도를 가진 범용 모션 카메라를 사용하여 HD 해상도의 방송에서 증강현실 어플리케이션을 구현하기 위해서 깊이 영상의 임의 범위를 지정하여, HD 해상도에 매칭시켜 2D 터치리스 영역에서 손의 멀티터치를 인식하게 하였다. 이렇게 인식된 모션을 자주 사용하는 '왼손 클릭', '오른손 클릭', '양손클릭', '스크러빙-상/하/좌/우' 제스쳐를 인식하게 하였으며, '카루젤 메뉴', '막대그래프 메뉴', '슬라이드 메뉴', '큐브 메뉴'를 구현하여 터치리스 형태의 모션기반 인터랙티브 증강현실 어플리케이션을 제안한다. 방송에서 자주 사용하는 그래픽 정보를 연기자나 사회자가 본 논문에서 제안하는 인터랙션 어플리케이션을 통하여 오퍼레이터 없이 스스로 더 능동적으로 정보를 표출할 수 있는 방법을 설명한다.