Mean shift based gradient vector flow for image segmentation

Huiyu Zhou, Xuelong Li, Gerald Schaefer, M. Emre Celebi, Paul Miller

Research output: Contribution to journalArticlepeer-review

96 Citations (Scopus)
385 Downloads (Pure)


In recent years, gradient vector flow (GVF) based algorithms have been successfully used to segment a variety of 2-D and 3-D imagery. However, due to the compromise of internal and external energy forces within the resulting partial differential equations, these methods may lead to biased segmentation results. In this paper, we propose MSGVF, a mean shift based GVF segmentation algorithm that can successfully locate the correct borders. MSGVF is developed so that when the contour reaches equilibrium, the various forces resulting from the different energy terms are balanced. In addition, the smoothness constraint of image pixels is kept so that over- or under-segmentation can be reduced. Experimental results on publicly accessible datasets of dermoscopic and optic disc images demonstrate that the proposed method effectively detects the borders of the objects of interest.
Original languageEnglish
Pages (from-to)1004-1016
Number of pages13
JournalComputer Vision and Image Understanding
Issue number9
Early online date25 Apr 2013
Publication statusPublished - Sep 2013


Dive into the research topics of 'Mean shift based gradient vector flow for image segmentation'. Together they form a unique fingerprint.

Cite this