DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Yoon, Sung-eui | - |
dc.contributor.advisor | 윤성의 | - |
dc.contributor.author | Cho, Jaehyeong | - |
dc.date.accessioned | 2018-06-20T06:24:04Z | - |
dc.date.available | 2018-06-20T06:24:04Z | - |
dc.date.issued | 2017 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=675459&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/243433 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학부, 2017.2,[iii, 23 p. :] | - |
dc.description.abstract | We present a rank-based voting technique utilizing inclusion relationship for high quality image search. Since images can have multiple regions of interest, we extract representative object regions using a state-of-the-art region proposal method tailored for our search problem. We then extract CNN features locally from those representative regions and identify inclusion relationship between those regions. To identify similar images given a query, we propose a novel similarity measure based on representative regions and their inclusion relationship. Our similarity measure gives a high score to a pair of images that contain similar object regions with similar spatial arrangement. To verify benefits of our method, we test our method in three standard benchmarks and compare it against the state-of-the-art image search methods using CNN features. Our experiment results demonstrate effectiveness and robustness of proposed algorithm, and also show the potential to further improve by cooperating with other state-of-the-art methods. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | image search | - |
dc.subject | object detection | - |
dc.subject | CNN | - |
dc.subject | image similarity | - |
dc.subject | spatial relationship | - |
dc.subject | 이미지 검색 | - |
dc.subject | 물체 검출 | - |
dc.subject | 이미지 유사도 | - |
dc.subject | 공간 관계 | - |
dc.title | Accurate image search using rank-based voting with inclusion relationship | - |
dc.title.alternative | 포함 관계와 순위 기반 투표를 활용한 정밀 이미지 검색 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | 조재형 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.