• 제목/요약/키워드: two-stage cascaded ranking

검색결과 1건 처리시간 0.013초

A two-stage cascaded foreground seeds generation for parametric min-cuts

  • Li, Shao-Mei;Zhu, Jun-Guang;Gao, Chao;Li, Chun-Wei
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제10권11호
    • /
    • pp.5563-5582
    • /
    • 2016
  • Parametric min-cuts is an object proposal algorithm, which can be used for accurate image segmentation. In parametric min-cuts, foreground seeds generation plays an important role since the number and quality of foreground seeds have great effect on its efficiency and accuracy. To improve the performance of parametric min-cuts, this paper proposes a new framework for foreground seeds generation. First, to increase the odds of finding objects, saliency detection at multiple scales is used to generate a large set of diverse candidate seeds. Second, to further select good-quality seeds, a two-stage cascaded ranking classifier is used to filter and rank the candidates based on their appearance features. Experimental results show that parametric min-cuts using our seeding strategy can obtain a relative small pool of proposals with high accuracy.