A bottom-up method for salient region detection using textural contrast and its applications구조적 대비를 이용한 상향식 관심 영역 검출 방법과 그 응용에 대한 연구

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 1559
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisorKim, Chang-Ick-
dc.contributor.advisor김창익-
dc.contributor.authorKim, Won-Jun-
dc.contributor.author김원준-
dc.date.accessioned2013-09-11T05:12:57Z-
dc.date.available2013-09-11T05:12:57Z-
dc.date.issued2012-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=511914&flag=dissertation-
dc.identifier.urihttp://hdl.handle.net/10203/180113-
dc.description학위논문(박사) - 한국과학기술원 : 전기및전자공학과, 2012.8, [ ix, 93 p. ]-
dc.description.abstractSalient region detection has been extensively studied due to its great possibilities for various computer vision fields. Despite remarkable research advances, a considerable amount of efforts still has been devoted to detect salient regions, which attract the human visual attention indeed, over the last few years. This is because previous methods are easily biased toward edges or corners, which are statistically significant, but not necessarily salient. Moreover, they often fail to find salient regions in complex scenes due to ambiguities between salient regions and highly textured backgrounds. In this thesis, we present a novel framework for salient region detection based on textural contrast, which is defined by combining the difference of luminance and directional coherence between center and surrounding regions. The proposed method is simple, robust, yet biologically plausible and it can thus be easily extended to a wide range of computer vision applications. Based on various data sets, we conduct comparative evaluations both qualitatively and quantitatively using 12 representative saliency detection models presented in literature, and the results show that the proposed scheme outperforms other previously developed methods in detecting salient regions. We further provide the utility of the proposed method by applying it to real-world applications such as content-aware image resizing (i.e., image retargeting), object segmentation, and video surveillance.eng
dc.languageeng-
dc.publisher한국과학기술원-
dc.subjectsalient region detection-
dc.subjectluminance contrast-
dc.subjectdirectional coherence contrast-
dc.subjecttextural contrast-
dc.subject관심 영역 검출-
dc.subject밝기 대비-
dc.subject방향의 일관성 대비-
dc.subject구조적 대비-
dc.subject중심-주변차이-
dc.subjectcenter-surround hypothesis-
dc.titleA bottom-up method for salient region detection using textural contrast and its applications-
dc.title.alternative구조적 대비를 이용한 상향식 관심 영역 검출 방법과 그 응용에 대한 연구-
dc.typeThesis(Ph.D)-
dc.identifier.CNRN511914/325007 -
dc.description.department한국과학기술원 : 전기및전자공학과, -
dc.identifier.uid020085430-
dc.contributor.localauthorKim, Chang-Ick-
dc.contributor.localauthor김창익-
Appears in Collection
EE-Theses_Ph.D.(박사논문)
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