Image Registration Neural System for the Analysis of Fundus Topology
Abstract
The developed system is a tool for high aperture imaging of the fundus. The obtained high resolution images preserve the topology of the blood vessels. The system is based on mosaicking a series of distinct low aperture fragments in order to obtain a high aperture image. Mosaicking is implemented by a neural network with stubborn learning taking into account the importance of the information of particular features. In mosaicking, the aberrations of the third order are partly compensated.
Cite
Text
Salakhutdinov et al. "Image Registration Neural System for the Analysis of Fundus Topology." European Conference on Computer Vision, 2004. doi:10.1007/978-3-540-27816-0_36Markdown
[Salakhutdinov et al. "Image Registration Neural System for the Analysis of Fundus Topology." European Conference on Computer Vision, 2004.](https://mlanthology.org/eccv/2004/salakhutdinov2004eccv-image/) doi:10.1007/978-3-540-27816-0_36BibTeX
@inproceedings{salakhutdinov2004eccv-image,
title = {{Image Registration Neural System for the Analysis of Fundus Topology}},
author = {Salakhutdinov, Viktor K. and Smetanin, Yuri G. and Murashov, Dmitry and Gandurin, V. A.},
booktitle = {European Conference on Computer Vision},
year = {2004},
pages = {417-422},
doi = {10.1007/978-3-540-27816-0_36},
url = {https://mlanthology.org/eccv/2004/salakhutdinov2004eccv-image/}
}