Edgeflow-driven Variational Image Segmentation: Theory and Performance Evaluation

Baris Sumengen, B. S. Manjunath
Department of Electrical and Computer Engineering
University of California, Santa Barbara, CA
{sumengen, manj} [at] ece.ucsb.edu

Abstract

We introduce robust variational segmentation techniques that are driven by an Edgeflow vector field. Variational image segmentation has been widely used during the past ten years. While there is a rich theory of these techniques in the literature, a detailed performance analysis on real natural images is needed to compare the various methods proposed. In this context, this paper makes the following contributions: (a) designing curve evolution and anisotropic diffusion methods that use Edgeflow vector fields to obtain good quality segmentation results over a large and diverse class of images, and (b) a detailed experimental evaluation of these segmentation methods. Our experiments show that Edgeflowbased anisotropic diffusion outperforms other competing methods by a significant margin.
[PDF] [BibTex]
B. Sumengen and B. S. Manjunath,
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), May. 2005.
Node ID: 206 , DB ID: 212 , Lab: NO_PUB , Target: Journal
Subject: [Detection on Images and Videos] « Look up more