• 전자공학회논문지B
• /
• 제33B권3호
• /
• pp.79-87
• /
• 1996

A new method for recognizing and locating partially occluded or overlapped two-dimensional objects regardless of their size, translation, and rotation, is presented. Dominant points approximating occuluding contoures of objects are generated by finding local maxima of smoothed k-cosine function, and then used to guide the contour segment matching procedure. Primitives between the dominant points are produced by projecting the local contours onto the line between the dominant points. Robust classification of primitives. Which is crucial for reliable partial shape matching, is performed using adaptive resonance theory (ART2). The matched primitives having similar scale factors and rotation angles are detected in the hough space to identify the presence of the given model in the object scene. Finally the translation vector is estimated by minimizing the mean squred error of the matched contur segment pairs. This model-based matching algorithm may be used in diveerse factory automation applications since models can be added or changed simply by training ART2 adaptively without modifying the matching algorithm.

• 한국공작기계학회논문집
• /
• 제18권1호
• /
• pp.42-49
• /
• 2009

This study proposes a web-based remote monitoring system for evaluating degradation of machine tools using ART2(Adaptive Resonance Theory 2) neural network. A number of studies on the monitoring of machine tools using neural networks have been reported. However, when normal condition is changed due to factors such as maintenance, tool change etc., or a new failure signal is generated, such algorithms need to be entirely retrained in order to accommodate the new signals. To cope with such problems, this study develops a remote monitoring system using ART2 in which new signals when required are simply added to the classes previously trained. This system can monitor degradation as well as failure of machine tools. To show the effectiveness of the proposed approach, the system is experimentally applied to monitoring a simulator similar to the main spindle of a machine tool, and the results show that the proposed system can be extended to monitoring of real industrial machine tools and equipment.

• 한국컴퓨터산업학회논문지
• /
• 제2권4호
• /
• pp.471-480
• /
• 2001

본 연구에서는 적응 공명 이론(ART2) 모델을 이용하여 화자인식 실험을 수행하였으며, 모을 검출을 통하여 미리 등록된 단어가 아닌 경우에도 화자를 인식할 수 있도록 특징 파라메터를 개발하였다. 실험을 위해 0에서 9까지의 숫자 음을 남성화자와 여성화자 각각 5명씩 발음하여 사용하였으며, 이들 음성 데이터로부터 모음을 추출한 다음 얻어진 피치 계수, 선형예측 계수, 선형예측 켑스트럼 계수를 신경망의 입력 패턴으로 입력시켜 인식 성능을 측정하였다. 실험 결과 피치를 사용하는 것이 텍스트-의존, 텍스트-독립 화자인식 모두에서 다른 계수들을 사용하는 것보다 우수한 성능을 보이고 있다.