• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

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

Vol. 10, No. 11, November 29, 2016
10.3837/tiis.2016.11.020, Download Paper (Free):

Abstract

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.


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
S. Li, J. Zhu, C. Gao and C. Li, "A two-stage cascaded foreground seeds generation for parametric min-cuts," KSII Transactions on Internet and Information Systems, vol. 10, no. 11, pp. 5563-5582, 2016. DOI: 10.3837/tiis.2016.11.020.

[ACM Style]
Shao-Mei Li, Jun-Guang Zhu, Chao Gao, and Chun-Wei Li. 2016. A two-stage cascaded foreground seeds generation for parametric min-cuts. KSII Transactions on Internet and Information Systems, 10, 11, (2016), 5563-5582. DOI: 10.3837/tiis.2016.11.020.