• 대한전자공학회논문지SP
• /
• 제46권3호
• /
• pp.44-51
• /
• 2009

본 논문에서는 상관에 기반 한 비선형 합성필터를 이용한 왜곡과 잡음에 강인한 얼굴인식 방법을 연구한다. 상관도 기반 방법은 얼굴 영역의 검출과 인증을 동시에 수행하여 보다 신속한 처리를 할 수 있다는 장점이 있다. 최적화된 비선형 합성필터는 학습영상의 출력 값을 일정하게 유지하면서 입력 영상과 잡음의 필터 출력에너지를 최소화함으로써 얻어진다. 입력 영상의 출력에너지를 최소화하여 허위표적과의 식별력을 부여하고 잡음의 출력에너지를 최소화하여 가산성 잡음에 대한 강인성을 증대한다. 본 논문에서는 비선형 합성필터를 두 개의 학습 영상으로 구성하여 표적의 왜곡과 저해상도 그리고 잡음 환경 하에서 얼굴 인증을 실험하였다. 실험결과는 비선형 합성필터가 SDF(synthetic discriminant function) 필터와 비교하여 ROC(receiver operating characteristics) 커브에서 우수한 성능을 보인다.

• 한국IT서비스학회지
• /
• 제6권3호
• /
• pp.241-249
• /
• 2007

This paper describes a real-time face tracking system using effective detector and Kalman filter. In the proposed system, an image is separated into a background and an object using a real-time updated face color for effective face detection. The face features are extracted using the five types of simple Haar-like features. The extracted features are reinterpreted using Principal Component Analysis (PCA), and interpreted principal components are used for Support Vector Machine (SVM) that classifies the faces and non-faces. The moving face is traced with Kalman filter, which uses the static information of the detected faces and the dynamic information of changes between previous and current frames. The proposed system sets up an initial skin color and updates a region of a skin color through a moving skin color in a real time. It is possible to remove a background which has a similar color with a skin through updating a skin color in a real time. Also, as reducing a potential-face region using a skin color, the performance is increased up to 50% when comparing to the case of extracting features from a whole region.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 V
• /
• pp.2645-2648
• /
• 2003

In this paper, real-time and reconfiguable hardware filter for face recognition is proposed and implemented on FPGA chip using verilog-HDL. In general, face recognition is considerably difficult because it is influenced by noises or the variation of illumination. Some of the commonly used filters such s histogram equalization filter, contrast stretching filter for image enhancement and illumination compensation filter are proposed for realizing more effective illumination compensation. The filter proposed in this paper was designed and verified by debugging and simulating on hardware. Experimental results show that the proposed filter system can generate selective set of real-time reconfiguable hardware filters suitable for face recognition in various situation.

• Journal of International Society for Simulation Surgery
• /
• 제2권2호
• /
• pp.64-66
• /
• 2015

Purpose : In this paper we proposed cascade feature filter and projection method for rapid human face recognition for the large-scale high-dimensional face database. Materials and Methods : The relevant features are selected from the large feature set using Fast Correlation-Based Filter method. After feature selection, project them into discriminant using Principal Component Analysis or Linear Discriminant Analysis. Their cascade method reduces the time-complexity without significant degradation of the performance. Results : In our experiments, the ORL database and the extended Yale face database b were used for evaluation. On the ORL database, the processing time was approximately 30-times faster than typical approach with recognition rate 94.22% and on the extended Yale face database b, the processing time was approximately 300-times faster than typical approach with recognition rate 98.74 %. Conclusion : The recognition rate and time-complexity of the proposed method is suitable for real-time face recognition system on the large-scale high-dimensional face database.

• 설비공학논문집
• /
• 제6권4호
• /
• pp.417-426
• /
• 1994

Filter media performance was evaluated using monodisperse NaCl particles with Differential Mobility Analyzer and Ultrafine Condensation Particle Counter. Low or medium performance filters show that the most penetrating particles size(MPPS) is around $0.3{\mu}m$ in diameter and is shifted to smaller sizes as the filter face velocity increases. However, HEPA and ULPA filters show MPPS is around $0.15{\mu}m$ in diameter and is also shifted to $0.1{\mu}m$ in diameter as the face velocity increases. In case of electret filter, the MPPS is found around $0.04{\mu}m$ region for Boltzmann charge equilibrium particles. There is a tendency of strong collection efficiency decrease for large particles as the face velocity increases on the contrary to the other filters. One of the medium performance filter efficiency was compared with filtration theory and the good agreetment was found in the experimental range.

• 전기학회논문지P
• /
• 제57권4호
• /
• pp.400-403
• /
• 2008

In this work, an individual trespassing detector using a PIR sensor to detect infrared rays only between the range of $9.4{\sim}10.4{\mu}m$ radiated from the body is proposed. This detector using FIR sensor detects not insect or object but human body, It doesn't restrict the inhabitant's behavior because the filter of pm sensor is designed to have face angle and the detector only detects the window area. The existing wide angle filter, RIR sensor, detects $30^{\circ}$ angle while the face angle filter sensor on this paper detects $11^{\circ}$ angle with 3cm of face angle filter from 2m of detecting distance. In case of interruption of electric power, 250mAh of lithium-ion battery has worked for 10 hours consuming 22mA in normal state. Meanwhile, in case of interruption of electric power, 250mAh of battery has worked for 4 hours consuming 60mA in trespassing detecting state. Projector, receptor, controller and alarm are put on one PCB in order to make it convenient to install without any special installation skill.

• 한국멀티미디어학회논문지
• /
• 제10권1호
• /
• pp.26-35
• /
• 2007

본 논문은 연속적으로 입력되는 비디오 영상에서 효과적인 얼굴 검출기와 칼만 필터를 이용하여 강인하게 얼굴을 추적하는 시스템을 제안한다. 효과적인 얼굴 검출기를 구성하기 위해 간단한 다섯 가지 타입의 Haar-like 특징값들을 이용하여 얼굴 특징을 추출한다. 추출된 특징값들은 PCA(Principal Component Analysis)를 이용하여 재해석되고, 해석된 주성분들을 SVM(Support Vector Machine)의 입력 값으로 사용하여 얼굴과 배경으로 분류한다. 검출된 얼굴의 정적정보와 프레임간 변화량을 이용한 동적정보를 칼만 필터(Kalman Filter)에 적용하여 얼굴을 추적한다. 실시간에 적용 가능한 시스템을 구현하기 위하여 얼굴 검출회수를 조정하여 처리속도를 향상시켰다. 실험결과, 평균 93.3%의 추적 성공률과 초당 15 프레임 처리 성능으로 강인한 실시간 얼굴 추적이 가능함을 보여주었다.

• Journal of Information Display
• /
• 제6권3호
• /
• pp.26-29
• /
• 2005

Nanosize cobalt aluminate($CoAl_2O_4$) power was coated as filter layer for us to improve the color purity and contrast performances on the inner face of CRT panel. We simulated color properties by measuring the transmittance and thickness of the coated filter layer. Contrast performance could be improved and color gamut was also changed by the selective light absorption of filter layer at 580${\sim}$605 nm.

• 한국멀티미디어학회논문지
• /
• 제7권12호
• /
• pp.1692-1699
• /
• 2004

Many researchers have developed various techniques for detection of human faces in ordinary still images. Face detection is the first imperative step of human face recognition systems. The two main problems of human face detection are how to cutoff the running time and how to reduce the number of false positives. In this paper, we present frontal and near-frontal face detection algorithm in still gray images using a thick edge image and neural network. We have devised a new filter that gets the thick edge image. Our overall scheme for face detection consists of two main phases. In the first phase we describe how to create the thick edge image using the filter and search for face candidates using a whole face detector. It is very helpful in removing plenty of windows with non-faces. The second phase verifies for detecting human faces using component-based eye detectors and the whole face detector. The experimental results show that our algorithm can reduce the running time and the number of false positives.

• International Journal of Contents
• /
• 제9권3호
• /
• pp.9-14
• /
• 2013

In this paper, we will examine single face tracking algorithms with scaling function in a mobile device. Face detection and tracking either in PC or mobile device with scaling function is an unsolved problem. Standard single face tracking method with particle filter has a problem in tracking the objects where the object can move closer or farther from the camera. Therefore, we create an algorithm which can work in a mobile device and perform a scaling function. The key idea of our proposed method is to extract the average of skin color in face detection, then we compare the skin color distribution between the detected face and the tracking face. This method works well if the face position is located in front of the camera. However, this method will not work if the camera moves closer from the initial point of detection. Apart from our weakness of algorithm, we can improve the accuracy of tracking.