The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.

imageseg: Deep Learning Models for Image Segmentation

A general-purpose workflow for image segmentation using TensorFlow models based on the U-Net architecture by Ronneberger et al. (2015) <doi:10.48550/arXiv.1505.04597> and the U-Net++ architecture by Zhou et al. (2018) <doi:10.48550/arXiv.1807.10165>. We provide pre-trained models for assessing canopy density and understory vegetation density from vegetation photos. In addition, the package provides a workflow for easily creating model input and model architectures for general-purpose image segmentation based on grayscale or color images, both for binary and multi-class image segmentation.

Version: 0.5.0
Imports: grDevices, keras, magick, magrittr, methods, purrr, stats, tibble, foreach, parallel, doParallel, dplyr
Suggests: R.rsp, testthat
Published: 2022-05-29
DOI: 10.32614/CRAN.package.imageseg
Author: Juergen Niedballa ORCID iD [aut, cre], Jan Axtner ORCID iD [aut], Leibniz Institute for Zoo and Wildlife Research [cph]
Maintainer: Juergen Niedballa <niedballa at izw-berlin.de>
BugReports: https://github.com/EcoDynIZW/imageseg/issues
License: MIT + file LICENSE
NeedsCompilation: no
Materials: README NEWS
CRAN checks: imageseg results

Documentation:

Reference manual: imageseg.pdf
Vignettes: A sample session in imageseg

Downloads:

Package source: imageseg_0.5.0.tar.gz
Windows binaries: r-devel: imageseg_0.5.0.zip, r-release: imageseg_0.5.0.zip, r-oldrel: imageseg_0.5.0.zip
macOS binaries: r-release (arm64): imageseg_0.5.0.tgz, r-oldrel (arm64): imageseg_0.5.0.tgz, r-release (x86_64): imageseg_0.5.0.tgz, r-oldrel (x86_64): imageseg_0.5.0.tgz
Old sources: imageseg archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=imageseg to link to this page.

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.