Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Contour based split and merge segmentation and pre-classification of zooplankton in very large images

 
: Gutzeit, Enrico; Scheel, Christian; Dolereit, Tim; Rust, Matthias

:
Volltext urn:nbn:de:0011-n-2909945 (1.2 MByte PDF)
MD5 Fingerprint: f0b1d1b451926961517a2c38840d9d11
Erstellt am: 6.11.2014


Battiato, S. (Hrsg.) ; Institute for Systems and Technologies of Information, Control and Communication -INSTICC-, Setubal:
9th International Conference on Computer Vision, Theory and Applications 2014. Proceedings. Vol.1 : Part of the 9th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2014. Lisbon, Portugal, 5 - 8 January, 2014
SciTePress, 2014
ISBN: 978-989-758-003-1
S.417-424
International Conference on Computer Vision Theory and Applications (VISAPP) <9, 2014, Lisbon>
International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) <9, 2014, Lisbon>
Englisch
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IGD ()
automatic segmentation; image segmentation; large scale image handling; classification methods; Business Field: Visual decision support; Research Area: Generalized digital documents

Abstract
Zooplankton is an important component in the water ecosystem and food chain. To understand the influence of zooplankton on the ecosystem a data collection is necessary. In research the automatic image based recognition of zooplankton is of growing interest. Several systems have been developed for zooplankton recognition on low resolution images. For large images approaches are seldom. Images of this size easily exceed the main memory of standard computers. Our novel automatic segmentation approach is able to handle these large images. We developed a contour based Split & Merge approach for segmentation and, to reduce the nonzooplankton segments, combine it with a pre-classification of the segments in reference to their shape. The latter includes a detection of quasi round segments and a novel one for thin segments. Experimental results on several large images show that we are able to handle them satisfactorily.

: http://publica.fraunhofer.de/dokumente/N-290994.html