Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

Many biomedical applications require detection of curvilinear networks in images, and would benefit from automatic or semiautomatic segmentation to allow high-throughput measurements. Here we discuss a contrast independent approach to identify curvilinear structures based on oriented phase congruency, the Phase Congruency Tensor. We show that the proposed approach is largely insensitive to intensity variations along the curve, and provides successful detection within noisy regions. Moreover, we demonstrate that the proposed approach may be used in a wide range of curvilinear and non-curvilinear feature enhancement and detection methods, particularly where tensor representation of the image is explored. The performance of the Phase Congruency Tensor-based methods is evaluated by comparing it with state-of-the-art intensity-based methods on both synthetic and real images of biomedical networks. © 2012 IEEE.

Original publication

DOI

10.1109/ISBI.2012.6235931

Type

Journal article

Journal

Proceedings - International Symposium on Biomedical Imaging

Publication Date

15/08/2012

Pages

1796 - 1799