• 한국산학기술학회논문지
• /
• 제20권9호
• /
• pp.1-6
• /
• 2019

영상 인식을 위한 한 방법으로 템플릿 매칭이 있다. 기존의 템플릿 매칭에서는 주어진 매칭 영상 내에서 템플릿의 2차원 이동 변위를 바꿔가면서 블록 매칭 알고리즘(BMA)을 수행한다. 이 블록 매칭 알고리즘 수행 중에 템플릿의 크기와 모양은 바뀌지 않는다. 그리고 각각의 2차원 이동변위에 해당하는 블록에서 유사성 척도(similarity measure)로 계산된 매칭 에러 값을 비교하여 대상 체의 위치를 결정한다. 2차원 이동변위만 고려하기 때문에 템플릿과 매칭 영상에서 대상 체의 크기와 방향이 일치하지 않으면 성공률이 떨어진다. 반면 본 논문의 경우는 템플릿의 2차원 방향과 크기를 조정하는 변수를 새로이 추가하고 각각의 2차원 이동 변위에 해당하는 블록에서 이 변수의 최적 값이 자동으로 계산된다. 이렇게 계산된 최적 값을 사용하여, 각 블록에 최적인 템플릿으로 자동 변형된다. 그리고 자동 변형된 템플릿을 기준으로 각 블록의 매칭 에러 값이 계산된다. 이렇게 방향과 크기 차이가 보정된 각 블록의 매칭 에러 값들을 비교하여 대상 체의 위치를 결정한다. 따라서 방향과 크기 차이에 대해 좀 더 안정적인 결과 값을 얻을 수 있다. 사용의 편의를 위해서, 알고리즘을 템플릿 영상 외에 추가의 정보, 예를 들면, 거리정보를 필요로 하지 않는 닫힌 형태로 설계하는 데 주력한다.

• 산업공학
• /
• 제10권3호
• /
• pp.133-143
• /
• 1997

In this paper, an improved method is developed for automatic inspection system using simbology patterns. The developed method uses the two previously developed matching methods the template maching method and the feature matching method. The template matching method is very sensitive to variations of target images such as translation and rotation of objects. On the other hand, the feature matching method doesn't extract proper features in some types of symbology patterns. The proposed method shows the improvement of precision in recognition of defects and flexibility of different types of symbology patterns.

• 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.

• 한국소음진동공학회논문집
• /
• 제26권2호
• /
• pp.172-178
• /
• 2016

The location template matching (LTM) method is a technique of identifying an impact location on a structure, and is often applied to structural health monitoring and large scale human-computer interface (HCI) systems. The LTM method utilizes a certain measure of similarity between two time signals. The correlation coefficient is most widely used for this purpose, and the group delay based method is recently proposed to improve the accuracy of finding the best matching pair of signals. In practice, one of key essential consideration for implementing the LTM method is to guarantee that a sufficient number of vibration modes must be contained in the measured signal, and yet the lower sampling rate is needed for a real-time implementation. In this paper, the properties of correlation coefficient and group delay with respect to the number of vibration modes are investigated. A few important results are obtained through extensive computer simulations and experiments. If the number of vibration modes contained in the measured signal is more than four it is sufficient for the correlation based LTM method, while the group delay based LTM method requires smaller number of vibration modes.

• 로봇학회논문지
• /
• 제6권3호
• /
• pp.247-254
• /
• 2011

This paper presents a method of sonar grid map matching for topological place recognition. The proposed method provides an effective rotation invariant grid map matching method. A template grid map is firstly extracted for reliable grid map matching by filtering noisy data in local grid map. Using the template grid map, the rotation invariant grid map matching is performed by Ring Projection Transformation. The rotation invariant grid map matching selects candidate locations which are regarded as representative point for each node. Then, the topological place recognition is achieved by calculating matching probability based on the candidate location. The matching probability is acquired by using both rotation invariant grid map matching and the matching of distance and angle vectors. The proposed method can provide a successful matching even under rotation changes between grid maps. Moreover, the matching probability gives a reliable result for topological place recognition. The performance of the proposed method is verified by experimental results in a real home environment.

• 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.

• 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.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1315-1318
• /
• 2004

Based on fuzzy 2-mean classification and template matching method, we propose a new algorithm to detect the edges of an image. In the algorithm, fuzzy 2-mean classification can classify all pixels in the mask into two clusters whatever the mask in the dark or light region; and template matching not only determines the edge's direction, but also thins the detected edge by a set of inference rules and, by the way, reduces the impulse noises.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 G
• /
• pp.2821-2823
• /
• 1999

In this paper we proposed an algorithm for rotation-invariant pattern recognition and rotated angle estimation between two patterns by employing selective template matching. Generally template matching has been used in determining the location of pattern but template matching requires a number of calculating correlation. To reduce the number of correlation we used steady-state genetic algorithm which is effective in optimization problem. We apply this method to distinguish specific pattern from similar coin patterns and estimate rotated angle between patterns. Our result leads us to the conclusion that proposed method performed faster than classical template matching

• 제어로봇시스템학회논문지
• /
• 제16권3호
• /
• pp.264-268
• /
• 2010

The purpose of this paper is to propose new techniques to match measured optical images by using the edge abstraction method and differentiation method based on image processing technology. To do this, we detect the matching template and non-matching template from each optical image. And then, we detect the edge parts of the overlaped image from comer edge abstraction method and remove noise image. At last, these data are related to applied first-order derivative operator. Finally, we show the effectiveness and feasibility of the proposed method through some experiments.