Hierarchical Layered Mean Shift Methods

被引：0

作者：

Surkala, Milan ^{[1
]}

Mozdren, Karel ^{[1
]}

Fusek, Radovan ^{[1
]}

Sojka, Eduard ^{[1
]}

机构：

[1] Fac Elect Engn & Informat, Ostrava 70833, Czech Republic

来源：

ADVANCED CONCEPTS FOR INTELLIGENT VISION SYSTEMS, ACIVS 2013 | 2013年 / 8192卷

关键词：

layer; segmentation; image; mean shift; hierarchical;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Many image processing tasks exist and segmentation is one of them. We are focused on the mean-shift segmentation method. Our goal is to improve its speed and reduce the over-segmentation problem that occurs with small spatial bandwidths. We propose new mean-shift method called Hierarchical Layered Mean Shift. It uses hierarchical preprocessing stage and stacking hierarchical segmentation outputs together to minimise the over-segmentation problem.

引用

页码：538 / 545

页数：8

共 12 条

[1]

[Anonymous], 2006, P 23 INT C MACH LEAR

[2] MEAN SHIFT, MODE SEEKING, AND CLUSTERING [J].

CHENG, YZ .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1995, 17 (08) :790-799

[3] Mean shift: A robust approach toward feature space analysis [J].

Comaniciu, D ;

Meer, P .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (05) :603-619

[4]

Comaniciu D., 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision, P1197, DOI 10.1109/ICCV.1999.790416

[5]

Comaniciu D, 2001, EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL I, PROCEEDINGS, P438, DOI 10.1109/ICCV.2001.937550

[6]

DeMenthon D., 2002, LAMPTR090 U MAR

[7]

FUKUNAGA K, 1975, IEEE T INFORM THEORY, V21, P32, DOI 10.1109/TIT.1975.1055330

[8]

Martin D, 2001, EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL II, PROCEEDINGS, P416, DOI 10.1109/ICCV.2001.937655

[9]

Surkala M., 2013, LNCS, V7893, P465

[10]

Surkala M, 2011, LECT NOTES COMPUT SC, V6915, P228, DOI 10.1007/978-3-642-23687-7_21

← 1 2 →