Skeletonization and Partitioning of Digital Images Using Discrete Morse Theory.
Saved in:
| Title: | Skeletonization and Partitioning of Digital Images Using Discrete Morse Theory. |
|---|---|
| Authors: | Delgado-Friedrichs, Olaf, Robins, Vanessa, Sheppard, Adrian |
| Source: | IEEE Transactions on Pattern Analysis & Machine Intelligence; Mar2015, Vol. 37 Issue 3, p654-666, 13p |
| Subject Terms: | MORSE theory, IMAGE segmentation, IMAGE recognition (Computer vision), PATTERN matching, DIGITAL image processing, HOMOLOGY theory, ARTIFICIAL intelligence |
| Abstract: | We show how discrete Morse theory provides a rigorous and unifying foundation for defining skeletons and partitions of grayscale digital images. We model a grayscale image as a cubical complex with a real-valued function defined on its vertices (the voxel values). This function is extended to a discrete gradient vector field using the algorithm presented in Robins, Wood, Sheppard TPAMI 33:1646 (2011). In the current paper we define basins (the building blocks of a partition) and segments of the skeleton using the stable and unstable sets associated with critical cells. The natural connection between Morse theory and homology allows us to prove the topological validity of these constructions; for example, that the skeleton is homotopic to the initial object. We simplify the basins and skeletons via Morse-theoretic cancellation of critical cells in the discrete gradient vector field using a strategy informed by persistent homology. Simple working Python code for our algorithms for efficient vector field traversal is included. Example data are taken from micro-CT images of porous materials, an application area where accurate topological models of pore connectivity are vital for fluid-flow modelling. [ABSTRACT FROM PUBLISHER] |
| Copyright of IEEE Transactions on Pattern Analysis & Machine Intelligence is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Biomedical Index |
Full Text Finder 
Nájsť tento článok vo Web of Science Be the first to leave a comment!