RISS 학술연구정보서비스

검색
다국어 입력

http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.

변환된 중국어를 복사하여 사용하시면 됩니다.

예시)
  • 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
  • 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
닫기
    인기검색어 순위 펼치기

    RISS 인기검색어

      검색결과 좁혀 보기

      선택해제

      오늘 본 자료

      • 오늘 본 자료가 없습니다.
      더보기
      • 무료
      • 기관 내 무료
      • 유료
      • 프레임간의 운동방향을 고려한 tracking을 통해 동영상의 feature 추출

        심승보(Seungbo Sim),최성후(Sunghoo Choi) 대한전기학회 2009 정보 및 제어 심포지엄 논문집 Vol.2009 No.10

        These days, object recognition has been developed and used in many industrial area. To automate assembly line or identification of the slab numbers which are serial number written on iron, object recognition is very useful and efficient. However, object recognition is very sensitive to noise, illumination, scale and so on. Therefore, success of the object recognition depends on consideration of such external factors. It means that there is no absolute solution which makes an object recognition success in all cases. In industrial area. especially. it is very difficult to recognize something using image processing and video because environment of the industrial area is very poor. The most important thing that is needed to recognize an object using a camera is invariance of the environment and image quality. Most industrial area. nevertheless, few facilities are provided to enhance in variance of the illumination and image quality where the camera is installed. That is the reason why a new algorithm is needed to cope with the poor environment. Consequently this, paper presents a new algorithm which is little sensitive to environment using hams corner, codebook and histogram algorithm.

      연관 검색어 추천

      이 검색어로 많이 본 자료

      활용도 높은 자료

      해외이동버튼