• 제어로봇시스템학회논문지
• /
• 제14권4호
• /
• pp.369-375
• /
• 2008

The kinematics and control problem of a visual alignment system is investigated, which plays a crucial role in the fabrication process of flat panel displays. The first solution is the inverse kinematics of a 4PPR parallel alignment mechanism. It determines the driving distance of each joint to compensate the misalignment between mask and panel. Second, an efficient vision algorithm for fast alignment mark recognition is suggested, where by extracting essential feature points to represent the geometry of a mark, the geometric template matching enables much faster object recognition comparing with the general template matching. Finally, the overall visual alignment process including the kinematic solution, vision algorithm, and joint control is implemented and experimental results are given.

• International journal of advanced smart convergence
• /
• 제1권2호
• /
• pp.39-42
• /
• 2012

This paper proposed a method that detects emergency situations in a video stream using MHI (Motion History Image) and template matching for a video-based intelligent security system. The proposed method creates a MHI of each human object through image processing technique such as background removing based on GMM (Gaussian Mixture Model), labeling and accumulating the foreground images, then the obtained MHI is compared with the existing MHI templates for detecting an emergency situation. To evaluate the proposed emergency detection method, a set of experiments on the dataset of video clips captured from a security camera has been conducted. And we successfully detected emergency situations using the proposed method. In addition, the implemented system also provides MMS (Multimedia Message Service) so that a security manager can deal with the emergency situation appropriately.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2001년도 추계학술발표논문집 (상)
• /
• pp.801-804
• /
• 2001

This article is concerned with automatic segmentation of two adjacent vowels for speech signals. All kinds of transition case of adjacent vowels can be characterized by spectrogram. Firstly the voiced-speech is extracted by the histogram analysis of vowel indicator which consists of wavelet low pass components. Secondly given phonetic transcription and transition pattern spectrogram, the voiced-speech portion which has consecutive vowels automatically segmented by the template matching. The cross-correlation function is adapted as a template matching method and the modified correlation coefficient is calculated for all frames. The largest value on the modified correlation coefficient series indicates the boundary of two consecutive vowel sounds. The experiment is performed for 154 vowel transition sets. The 154 spectrogram templates are gathered from 154 words(PRW Speech DB) and the 161 test words(PBW Speech DB) which are uttered by 5 speakers were tested. The experimental result shows the validity of the method.

• 한국소음진동공학회논문집
• /
• 제20권3호
• /
• pp.308-315
• /
• 2010

This study introduces a new technique to estimate modal parameters of a vibrating string using motion pictures. The approach requires two motion pictures for a vibrating string captured simultaneously by typical potable digital cameras or camcorders. Applying the space intersection theory and the space resection theory in photogrammetry, the steroscopic images for the string are constructed from two flat plane pictures. Then the three dimensional displacement components of the string are extracted by a multiple template matching technique. Finally the modal parameters of the string are estimated from the resulting displacement time histories. The accuracy of the approach has been examined through a small-scale mock-up of a string.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 춘계학술대회 학술발표 논문집
• /
• pp.141-144
• /
• 1997

This paper presents a method of navigation sign recognition in indoor environments using a fuzzy inference for an autonomous mobile robot. In order to adapt to image deformation of a navigation sign resulted from variations of view-points and distances, a multi-labeled template matching(MLTM) method and a dynamic area search method(DASM) are proposed. The DASM is proposed to detect correct feature points among incorrect feature points. Finally sugeno-style fuzzy inference are adopted for recognizing the navigation sign.

• 정보처리학회논문지B
• /
• 제13B권4호
• /
• pp.377-382
• /
• 2006

본 논문에서는 자동결함검출 방법으로 도광판의 다양한 패턴에 나타나는 돌출, 함몰, 점 등과 같은 작은 결함들을 검출하기 위해 모폴로지의 닫힘, 열림 방법을 이용하는 템플레이트 검사 방법을 사용하였고, 얼룩, 스크래치와 같은 큰 결함을 검출하기 위해 영상에서 격자와 같은 일정한 블록을 형성하여 각 블록을 비교하여 결함을 찾는 블록매칭 방법을 사용하였다. 또한 일정한 패턴이 없는 도광판의 결함에 대해 결함을 검출할 수 있는 개선된 오쯔 방법을 이용하였다. 이 알고리즘을 적용한 결과 결함 검출에 좋은 성능이 있음을 보여준다. 제안된 알고리즘은 자체 개발한 장비에서 실제 도광판의 영상을 얻어 테스트 하였다.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1996년도 춘계학술대회
• /
• pp.31-35
• /
• 1996

This paper presents a real time algorithm for monitoring of the arrythmia of ECG signal. A real time monitoring, following by detecting a QRS complex, is the most important. Using 2-dimensional time-delay coordinates which are reconstructed by the phase portrait plotting special trajectory, we detect QRS complexes. In this study, arrythmias are detected by matching the past standard template with tile present pattern when changing abruptly In order to matching with each other, we propose modified chain coding algorithm which applies vetor table consisting of eight orthonormal code(=binary code) to the phase portraits. This algorithm using logical function increases the weight if exceeding to the threshold determinded by correlation value and the distance from a straight line(y=x). Evaluating the performance of the proposed algorithm, we use standard MIT/BIH database. The results are fellowing, 1) Improve the speed of matching template than that of cross-correlation ever has been used. 2) Because the proposed algorithm is robust to varing fiducial point, it is possible to monitor the ECG signal with irregular RR interval. 3) In spite of baseline wandering owing to the low frequency noise, monitoring performance is not reduced.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.28-31
• /
• 2003

In the present work, a main purpose is to propose a fuzzy integral-based aggregation framework to complementarily combine partial information due to lack of completeness. Based on Choquet integral (CI) viewed as monotone expectation, we take into account complementary, non-interactive, and substitutive aggregations of different sources of defective information. A CI-based system representing upper, conventional, and lower expectations is designed far handling three aggregation attitudes towards uncertain information. In particular, based on Choquet integrals for belief measure, probability measure, and plausibility measure, CI$\_$bi/-, CI$\_$pr/ and CI$\_$pl/-aggregator are constructed, respectively. To illustrate a validity of proposed aggregation framework, multiple matching systems are developed by combining three simple individual template-matching systems and tested under various image variations. Finally, compared to individual matchers as well as other traditional multiple matchers in terms of an accuracy rate, it is shown that a proposed CI-aggregator system, {CI$\_$bl/-aggregator, CI$\_$pl/-aggregator, Cl$\_$pl/-aggregator}, is likely to offer a potential framework for either enhancing completeness or for resolving conflict or for reducing uncertainty of partial information.

• 한국인터넷방송통신학회논문지
• /
• 제14권4호
• /
• pp.173-179
• /
• 2014

오늘날 한국 사회에서 백내장 수술은 가장 빈번하게 이루어지는 수술중 하나이다. 백내장을 치료하기 위한 방법은 다양하게 발전해왔다. 이 중 오늘날 널리 쓰이는 방식은 인공 수정체를 이용하여 기존의 수정체와 교환하는 방법이다. 인공 수정체 삽입 시 미리 계산된 지점 및 각도로 정확하게 삽입하는 것이 중요할 수 있는 지점 표시가 필요 하다. 그러나 수술 중에 눈에서 분비되는 이물질 같은 요인에 의해 표시가 지워질 수 있다. 그러므로 이런 표시방법을 실시간으로 카메라 영상을 받음으로써 영상처리로 추적하는 방법이 필요하다. 본 논문에서는 템플릿 매칭과 버퍼를 이용한 특징점 추적 방법을 제안한다. 제안한 방법을 적용함으로 해당 수정체 삽입 위치를 정확히 추적하는 것을 확인하였다.

• 대한교통학회지
• /
• 제17권4호
• /
• pp.111-124
• /
• 1999

본 논문의 목적은 최근에 개발 중에 있는 단일 자석검지기를 이용한 차종인식 알고리즘을 개발하고, 현장실험을 통한 현장 적용성을 검토하는 것이다. 고속도로에 설치되어 이는 자석검지기를 이용하여 자료를 수집하며 분석에 이용되는 자료는 개별차량에 대하여 자속밀도의 변화에 따른 전압 값을 Digital Data값으로 변환한 수치를 사용하였다. 그 수치를 토대로 각 차량의 점유시간을 파악하여 각 차량의 점유시간동안 파형의 특징을 추출하여 각 특징들을 기초로 하여 각 차량이 나타내는 고유의 파형을 식별하는 Template Matching 방법과 신경망기법, 그리고 이들을 상호 보완한 복합기법을 사용하였다. 검지차량에 따른 다양한 점유시간을 일정크기로 수평성분 정규화하고 이에 따른 자속속밀도의 변화에 의한 전압 값을 차종별로 샘플을 취하여 이동평균방법으로 처리를 한 후 위의 세 가지 기법을 사용하여 검지차량의 파형과 기준 파형을 비교하여 차종을 인식하는 방법으로 알고리즘을 개발하였다. 차종의 분류는 3가지 단계로 하였는데 2종분류, 3종분류, 5종분류로 접근하였다. 그리고 각각의 분류에 따라 정규화 크기 및 이동평균간격을 달리하여 적용하여 보았고 2종분류에서 인식율이 82%수준이다.