A hybrid ASM approach for sparse volumetric data segmentation
| Autor: | Reyer Zwiggelaar, Yanong Zhu, Stuart K. Williams |
|---|---|
| Rok vydání: | 2007 |
| Předmět: |
business.industry
Computer science Volumetric data Pattern recognition Machine learning computer.software_genre Object (computer science) Computer Graphics and Computer-Aided Design Global optimal Data set Dimension (vector space) Pattern recognition (psychology) Segmentation Computer Vision and Pattern Recognition Artificial intelligence business computer |
| Zdroj: | Pattern Recognition and Image Analysis. 17:252-258 |
| ISSN: | 1555-6212 1054-6618 |
| DOI: | 10.1134/s1054661807020125 |
| Popis: | Three-Dimensional (3D) Active Shape Modeling (ASM) is a straightforward extension of 2D ASM. 3D ASM is robust when true volumetric data is considered. However, when the information in one dimension is sparse, pure 3D ASM tends to be less robust. We present a hybrid 2D + 3D methodology which can deal with sparse 3D data. 2D and 3D ASMs are combined to obtain a "global optimal" segmentation of the 3D object embedded in the data set, rather than the "locally optimal" segmentation on separate slices. Experimental results indicate that the developed approach shows equivalent precision on separate slices but higher consis- tency for whole volumes when compared to 2D ASM, while the results for whole volumes are improved when compared to the pure 3D ASM approach. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink