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) <arXiv:1505.04597> and the U-Net++ architecture by Zhou et al. (2018) <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
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
Old sources: imageseg archive

Linking:

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