Edgeflow-driven variational image segmentation: Theory and performance evaluation.

@inproceedings{citeulike:2970663, 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 Edgeflow-based anisotropic diffusion outperforms other competing methods by a significant margin.}, author = {Sumengen, B. and Manjunath, B. S. }, booktitle = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, citeulike-article-id = {2970663}, keywords = {segmentation, texture\_analysis, vision}, month = {May}, posted-at = {2008-07-07 18:44:41}, priority = {2}, title = {Edgeflow-driven variational image segmentation: Theory and performance evaluation.}, url = {http://vision.ece.ucsb.edu/publications/view\_abstract.cgi?212}, year = {2005} }

TY - CONF ID - citeulike:2970663 L3 - citeulike-article-id:2970663 TI - Edgeflow-driven variational image segmentation: Theory and performance evaluation. T2 - IEEE Transactions on Pattern Analysis and Machine Intelligence N2 - 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 Edgeflow-based anisotropic diffusion outperforms other competing methods by a significant margin. KW - segmentation KW - texture_analysis KW - vision AU - Sumengen, B AU - Manjunath, BS PY - 2005/05// UR - http://vision.ece.ucsb.edu/publications/view_abstract.cgi?212 ER -