Image segmentation combining region growing and edge detection

Yu Xiaohan, Juha Ylä-Jääski, Olli Huttunen, Tuomo Vehkomäki, Outi Sipilä, Toivo Katila

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

45 Citations (Scopus)

Abstract

In this paper a new image segmentation technique is presented combining region growing, edge detection, and a new edge preserving smoothing algorithm. The combined method helps to avoid characteristic segmentation errors which occur when using region growing or edge detection separately. Boundary smoothing is also introduced to ensure more realistic region boundaries. The algorithm can directly be extended for 3-dimensional data. Experimental results are shown to demonstrate the validity of the algorithm.
Original languageEnglish
Title of host publicationProceedings of the 11th IAPR International Conference on Pattern Recognition
Subtitle of host publicationConference C: Image, Speech and Signal Analysis
PublisherIEEE Institute of Electrical and Electronic Engineers
Pages481-484
VolumeIII
ISBN (Print)0-8186-2920-7
DOIs
Publication statusPublished - 1992
MoE publication typeA4 Article in a conference publication
Event11th IAPR International Conference on Pattern Recognition - The Hague, Netherlands
Duration: 30 Aug 19921 Sept 1992

Conference

Conference11th IAPR International Conference on Pattern Recognition
Country/TerritoryNetherlands
CityThe Hague
Period30/08/921/09/92

Fingerprint

Dive into the research topics of 'Image segmentation combining region growing and edge detection'. Together they form a unique fingerprint.

Cite this