Interface with Google Cloud Document AI API.

daiR: OCR with Google Document AI in R

daiR is an R package for Google Document AI, a powerful server-based OCR service with support for over 60 languages. The package provides an interface for the Document AI API and comes with additional tools for output file parsing and text reconstruction. See the daiRwebsite and this journal article for more details.

Use

Quick OCR short documents:

## NOT RUN
library(daiR)
get_text(dai_sync("file.pdf"))

Turn images of tables into R dataframes:

## NOT RUN:
# Assumes a default processor of type "FORM_PARSER_PROCESSOR"
get_tables(dai_sync("file.pdf"))

Draw bounding boxes on the source image:

## NOT RUN:
draw_blocks(dai_sync("file.pdf"))

Requirements

Google Document AI is a paid service that requires a Google Cloud account and a Google Storage bucket. I recommend using Mark Edmondson's googleCloudStorageRpackage in combination with daiR.

Installation

Install daiR from CRAN:

install.packages("daiR")

Or install the latest development version from Github:

devtools::install_github("hegghammer/daiR")

Citation

To cite daiR in publications, please use

Hegghammer, T., (2021). daiR: an R package for OCR with Google Document AI. Journal of Open Source Software, 6(68), 3538, https://doi.org/10.21105/joss.03538

Bibtex:

@article{Hegghammer2021,
  doi = {10.21105/joss.03538},
  url = {https://doi.org/10.21105/joss.03538},
  year = {2021},
  publisher = {The Open Journal},
  volume = {6},
  number = {68},
  pages = {3538},
  author = {Thomas Hegghammer},
  title = {daiR: an R package for OCR with Google Document AI},
  journal = {Journal of Open Source Software}
}

Acknowledgments

Thanks to Mark Edmondson, Hallvar Gisnås, Will Hanley, Neil Ketchley, Trond Arne Sørby, Chris Barrie, and Geraint Palmer for contributions to the project.

Code of conduct

Please note that the daiR project is released with a Contributor Code of Conduct. By contributing to this project, you agree to abide by its terms.