Aesthetic quality classification via subject region extraction = 주요 영역 검출을 이용한 사진의 심미적 평가

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 235
  • Download : 0
Aesthetic quality classification gains growing interest in recent years.In this paper, we propose an aesthetic quality classification method via subject region extraction.We extract subject region by focused pixel detection and saliency detection, which do not need prior knowledge of contents of image.Once the subject regions are extracted, we use regional features to measure contrast between subject region and background region.And global features are also used to describe comprehensive property of the image.Experimental results show that our subject extraction method without prior knowledge is comparable to state-of-the-art subject region extraction methods that use different approaches with prior knowledge.We also show that classification performance is comparable to the performance of state-of-the-art aesthetic quality classification.
Advisors
Kim, Chang-Ickresearcher김창익
Description
한국과학기술원 : 전기및전자공학과,
Publisher
한국과학기술원
Issue Date
2014
Identifier
569309/325007  / 020124387
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 전기및전자공학과, 2014.2, [ v, 32 p. ]

Keywords

Aesthetic Photo; 기계 학습; 주요 영역 검출; 영상 품질 평가; 심미적 영상; Machine Learning; Quality Assessment; Subject Region Extraction

URI
http://hdl.handle.net/10203/196633
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=569309&flag=dissertation
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