• 한국소음진동공학회논문집
• /
• 제24권4호
• /
• pp.310-316
• /
• 2014

The location template matching(LTM) method is a technique of identifying an impact location on a structure, and requires a certain measure of similarity between two time signals. In general, the correlation coefficient is widely used as the measure of similarity, while the group delay based method is recently proposed to improve the accuracy of the impact localization. Another possible measure is the frequency response assurance criterion(FRAC), though this has not been applied yet. In this paper, these three different measures of similarity are examined comparatively by using experimental data in order to understand the properties of these measures of similarity. The comparative study shows that the correlation coefficient and the FRAC give almost the same information while the group delay based method gives the shape oriented information that is best suitable for the location template matching method.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2014년도 춘계학술대회 논문집
• /
• pp.506-511
• /
• 2014

The location template matching (LTM) method is a technique of identifying an impact location on a structure, and requires a certain measure of similarity between two time signals. In general, the correlation coefficient is widely used as the measure of similarity, while the group delay based method is recently proposed to improve the accuracy of the impact localization. Another possible measure is the frequency response assurance criterion (FRAC), though this has not been applied yet. In this paper, these three different measures of similarity are examined comparatively by using experimental data in order to understand the properties of these measures of similarity. The comparative study shows that the correlation coefficient and the FRAC give almost the same information while the group delay based method gives the shape oriented information that is best suitable for the location template matching method.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.174-177
• /
• 2009

In object tracking, the template matching methods have been developed and frequently used. It is fast enough, but not robust to an object with the variation of size and shape. In order to overcome the limitation of the template matching method, this paper proposes a template update technique. After finding an object position using the correlation-based adaptive predictive search, the proposed method selects blocks which contain object's boundary. It estimates the motion of boundary using block matching, and then updates template. We applied it to IR image sequences including an approaching object. From the experimental results, the proposed method showed successful performance to track object.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2008년도 학술대회 1부
• /
• pp.847-850
• /
• 2008

오늘날 인간은 기계와의 상호의사소통을 이용하여 기계를 더욱 발전시켜가고 있다. 시각기반인지시스템을 비롯한 여러 HCI(Human Computer Interaction)시스템 중 손가락 제스처를 인식, 추적하는 기술은 HCI 시스템에서 매우 중요한 부분을 차지하고 있다. 이 논문에서는 손가락을 구분하기 위해서 제한된 배경과 복잡한 배경에서의 손가락을 구분할 뿐만 아니라 배경과 전경을 분리하는 차영상을 이용하여 더욱더 효과적으로 손가락을 구분해내는 방법을 이용한다. 손가락을 구분하기 위해서는 미리 정의해놓은 손가락 끝 이미지들과 Template-Matching 을 통하여 손가락을 인식한다. 그리고 인식된 손가락을 추적한 후 미리 정의해놓은 제스처들과 비교함으로써 제스처를 인식한다. 이 논문에서는 차영상과 Template Matching 반을 이용하지 않고 미리 관심영역을 획득한 후 그 영역 안에서 Template Matching 을 수행한다. 그래서, 실행속도 및 반응속도를 줄이는 데 중점을 두고 있으며 더욱 효과적으로 제스처를 인식하는 방법에 대해 제안한다.

• 한국군사과학기술학회지
• /
• 제17권3호
• /
• pp.364-377
• /
• 2014

In this paper, we have developed a target recognition algorithm based on a template matching technique using Synthetic Aperture Radar (SAR) images. For efficient computations, Radon transform-based azimuth estimation algorithm was used with the template matching. MSTAR data set was divided into two groups according to the depression angles, which were a train set and a test set. Template data were generated by rotating and cropping chips which were from MSTAR train set using the azimuth estimation algorithm. Then the template matching process between test data and template data was performed under various conditions. Performance variation according to contrast enhancement preprocessing which is scarce in open literature was also presented. The analysis results show that the target recognition algorithm could be useful for the automatic target recognition using SAR images.

• 지능정보연구
• /
• 제13권4호
• /
• pp.65-78
• /
• 2007

추천시스템은 개인화 서비스를 구현하는 방법 중의 하나이다. 추천시스템은 다양한 기법을 통해 구축될 수 있는데, 최근 전자상거래 분야에서 사용되는 기법들 중에서 대표적인 것이 협업필터링이다. 협업필터링은 영화나 음악 같이 명시적인 속성만으로 그 특성을 기술하는데 한계가 있는 아이템의 추천문제에 효과적으로 적용되어 왔다. 하지만, 이 기법은 희박성, 확장성 및 투명성 등의 문제점을 가지고 있는데, 본 연구에서는 희박성과 확장성 문제를 극복하는 방안으로 장르별 협업필터링 방법을 제안한다. 장르별 협업필터링 방법은 아이템을 최종적으로 추천하기 전에 아이템의 상위 카테고리, 즉 장르에 대한 정보를 활용하는 방법이다. 본 연구에서 제안하는 방법의 실용성을 보이기 위하여, 영화 추천시스템인 GenreWise_CF를 개발하여, 공개 데이터인 MovieLens Data에 적용하여 평가하였다. 실험 결과, 본 연구에서 제안한 GenreWise_CF가 전통적인 협업 필터링을 적용하여 개발한 추천시스템인 Basic_CF보다 향상된 성능을 보였다.

• 한국지능시스템학회논문지
• /
• 제19권5호
• /
• pp.683-688
• /
• 2009

본 논문에서는 비젼을 이용한 영상처리 기술을 기반으로 비접촉식 미세 측정 광학기에 의해 측정된 이미지를 템플릿 매칭과 B-Spline 보간법에 의해 보다 빠르고, 정밀한 복원 기법을 제안한다. 이를 위해 먼저 각각의 이미지로부터 매칭 템플릿과 피 매칭 템플릿을 검출한다. 그런 다음 기준면으로부터 두 이미지의 중첩되는 부분의 롤, 피치, 요 오차를 보정하여 정합시킨다. 그리고 B-Spline 보간법에 의해 정합된 부분을 연속화한다. 마지막으로, 제안된 방법은 실험을 통해 그 응용 가능성을 증명한다.

• 제어로봇시스템학회논문지
• /
• 제15권2호
• /
• pp.225-230
• /
• 2009

We propose a template matching method for component inspection of SMD assembly system. To discriminate wrong assembled components, the input image of component is matched with its standard image by template matching algorithm. For a fast inspection system, the calculation time of matching algorithm should be reduced. Since the standard images of all components located in a PCB are stored in computer, it is desirable to reduce the memory size of standard image. We apply the discrete wavelet transformation to reduce the image size as well as the calculation time. Only 7% memory of the BMP image is used to discriminate goodness or badness of components assembly. Comparative results are presented to verify the usefulness of the proposed method.

• 전기학회논문지
• /
• 제57권4호
• /
• pp.700-705
• /
• 2008

In this paper, we propose object classification algorithm for real-time surveillance system. We have approached this problem using silhouette-based template matching. The silhouette of the object is extracted, and then it is compared with representative template models. Template models are previously stored in the database. Our algorithm is similar to previous pixel-based template matching scheme like Hausdorff Distance, but we use 1D image array rather than 2D regions inspired by Hilbert Path. Transformation of images could reduce computational burden to compute similarity between the detected image and the template images. Experimental results show robustness and real-time performance in object classification, even in low resolution images.

• 전기학회논문지
• /
• 제59권8호
• /
• pp.1471-1476
• /
• 2010

This paper proposes the robust matching algorithm of the optical images. To do this, we propose two algorithms, that is, matching algorithms when the silhouette of images is detected and when it is not detected. Also, we propose the method for detecting the matching template and non-matching template from each optical image. And then, optical images are matched according to the coefficient of correlation represented by the similar degree between optical images. Finally, we show the effectiveness and feasibility of the proposed method through some experiments.