개인구독
소속 기관이 없으신 경우, 개인 정기구독을 하시면 저렴하게
논문을 무제한 열람 이용할 수 있어요.
지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학위논문
- 저자정보
- 지도교수
- 김병규
- 발행연도
- 2016
- 저작권
- 선문대학교 논문은 저작권에 의해 보호받습니다.
이용수1
이 논문의 연구 히스토리 (2)
- 이 논문의 후속연구가 궁금하신가요?
- 연관 학술논문 또는 학술발표를 통해 보다 발전된 연구결과를 확인하실 수 있습니다.
- 이 논문의 연구 히스토리 확인하기
초록· 키워드
오류제보하기
Image segmentation method is widely used as a pre-process in the image process, and exerts a significant effect in analyzing the image. Medical, semiconductor research, intelligent transportation systems, robotics, military, and the like used in various fields, and the trend in the field can be developed and applied as the performance of the algorithm in accordance with the recent development of hardware that are still growing. Image segmentation is required to have a high accuracy as used for pre-processing in other applications. When the boundary between the background and a object is unclear, it causes a problem in the post-processing.
In this thesis, we propose a method in order to divide the background and objects using filtered super-pixel and enhanced saliency map. Comparing the size of the area evenly and smoothed to produce a super pixel and super pixel region removes not equal area. By applying a bilateral filter to the saliency map, it is similar to the human vision system to improve the segmentation of the background and the object is to be applied makes it possible to adaptively without utilizing a number of conditions or pre-information or knowledge not the algorithm tailored to a specific environment.
In this thesis, we propose a method in order to divide the background and objects using filtered super-pixel and enhanced saliency map. Comparing the size of the area evenly and smoothed to produce a super pixel and super pixel region removes not equal area. By applying a bilateral filter to the saliency map, it is similar to the human vision system to improve the segmentation of the background and the object is to be applied makes it possible to adaptively without utilizing a number of conditions or pre-information or knowledge not the algorithm tailored to a specific environment.
목차
등록된 정보가 없습니다.
최근 본 자료
댓글(0)
0