Salient region detection using a discriminative color transform dictionary = 차별적 색상 변환 사전을 이용한 관심 영역 검출

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 237
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisorKim, Junmo-
dc.contributor.advisor김준모-
dc.contributor.authorKim, Jiwhan-
dc.contributor.author김지환-
dc.date.accessioned2017-03-29T02:37:17Z-
dc.date.available2017-03-29T02:37:17Z-
dc.date.issued2013-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=657348&flag=dissertationen_US
dc.identifier.urihttp://hdl.handle.net/10203/221695-
dc.description학위논문(석사) - 한국과학기술원 : 전기및전자공학과, 2013.8 ,[v, 33 p. :]-
dc.description.abstractSalient region detection is a process of extracting a visually attractive region from a single image. In this paper, we present a novel method for automatically detecting salient region with discriminative color transform dictionary. The key assumption of the proposed framework is that the saliency map can be represented as a linear combination of color components of an image. To find a set of optimal coefficients for this linear combination, we incorporate least squares with constructing color transform dictionary, which includes multiple powers of color components in RGB and CIELab color space. In addition, we refine the saliency map by solving sparse representation problem with local dictionary, which is intended to enhance the compactness of the salient region in the saliency map. Experimental results show that the proposed method provides the saliency maps of two benchmark datasets with better quality and improved performance, compared to the previous state-of-the-art techniques.-
dc.languageeng-
dc.publisher한국과학기술원-
dc.subjectsaliency detection-
dc.subjectcompactness-
dc.subjectleast-squares-
dc.subjectdictionary learning-
dc.subjectcolor space-
dc.subject관심 영역 검출-
dc.subject조밀도-
dc.subject최소자승법-
dc.subject사전 학습-
dc.subject색상 공간-
dc.titleSalient region detection using a discriminative color transform dictionary = 차별적 색상 변환 사전을 이용한 관심 영역 검출-
dc.typeThesis(Master)-
dc.identifier.CNRN325007-
dc.description.department한국과학기술원 :전기및전자공학과,-
Appears in Collection
EE-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0