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
      • Voxel-Encoded Descriptor for 3D Model Retrieval by Exploring Model`s Spatial Information

        Qian Zhang,Jin-Yuan Jia,Matthew Ming-Fai Yuen,Long Zeng (사)한국CDE학회 2013 한국CAD/CAM학회 국제학술발표 논문집 Vol.2010 No.8

        To develop a model retrieval engine tolerant to defects (e.g. holes and cracks) of digitized models, a new descriptor is proposed by encoding the model’s spatial information, i.e. not only boundary data but also internal data of a complex model. First, a polygonal model is converted into a voxel model and its posture is normalized by a voxel-based principal component analysis technique. Then, six color images are generated by projecting the voxel model along its three local axes. The color value of each pixel is computed from the status of all the voxels which intersect with the ray starting from the pixel and parallel to the axis. The status of the voxels along a ray embodies the spatial distribution of the model along this ray. Finally, a voxel-encoded descriptor is computed by applying Fourier and wavelet transformation to the six color images. To further improve the retrieval efficiency, the database structure is optimized by an improved geometric manifold entropy scheme. The two techniques are integrated into a model retrieval system and the experiments demonstrated that the VED descriptor outperforms current popular shape descriptors.

      연관 검색어 추천

      이 검색어로 많이 본 자료

      활용도 높은 자료

      해외이동버튼