Texture Analysis of 3D Fluorescence Microscopy Images Using RSurf 3D Features
| Authors | |
|---|---|
| Year of publication | 2016 |
| Type | Article in Proceedings |
| Conference | International Symposium on Biomedical Imaging (ISBI'16) |
| MU Faculty or unit | |
| Citation | |
| Doi | https://doi.org/10.1109/ISBI.2016.7493484 |
| Field | Use of computers, robotics and its application |
| Keywords | RSurf features;HeLa cell images;object recognition;classification;fluorescence microscopy |
| Description | Classification tasks of biomedical images are still interesting topic of research with many possibilities of improvement. A very important part in this task is feature extraction process, where different image descriptors are used. Recently, a new approach of RSurf features was introduced with application in recognition of the 2D HEp-2 cell images. In this work, we present the extension of these features for the 3D volumetric images and demonstrate its superiority in recognition of sub-cellular protein distribution. The performance is tested on public HeLa dataset containing 9 different classes. The presented k-NN classifier based purely on the RSurf 3D features achieves more than 99% accuracy in recognition of the 3D HeLa images. |
| Related projects: |