Loading...
Please wait, while we are loading the content...
Similar Documents
Towards Segmentation of Irregular Tubular Structures in 3 D Confocal Microscope Images
| Content Provider | Semantic Scholar |
|---|---|
| Author | Santamaría-Pang, Alberto Bı̂ldea, Teodor Ş. Colbert, C. M. Saggau, Peter Kakadiaris, Ioannis A. |
| Copyright Year | 2006 |
| Abstract | In this paper, we propose a general framework for learning and predicting tubular models in 3D images. By using Support Vector Machines we take advantage of the data transformation into a high dimensional space to estimate the posterior probability of an element belonging to a tube-like 3D object. This learning eliminates the need for performing multiscale analysis on the data. We compare the performance of our method with standard approaches for tubularity enhancement in both synthetic data and confocal 3D images. Our method achieves substantial improvements over classical methods. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.miaab.org/miaab-2006-papers/miaab-2006-18-santamaria.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
