Conference paper · 2018 · Open access

Fully Convolutional Networks for Handwriting Recognition

Felipe Petroski Such, Dheeraj Peri, Frank Brockler, Paul Hutkowski, Raymond Ptucha

International Conference on Frontiers in Handwriting Recognition, 86–91 · Published 1 August 2018 · DOI 10.1109/icfhr-2018.2018.00024

Free PDFView at the publisherCite this paper

In brief

“Fully Convolutional Networks for Handwriting Recognition” is a 2018 conference paper by Felipe Petroski Such and 4 co-authors, published in International Conference on Frontiers in Handwriting Recognition. OpenAlex counts 39 citations as of 15 November 2026. It is open access under a CC BY-SA licence: the full text is free to read at arXiv (Cornell University).

Citations
39
Most cited in
2020 (10)
Field-weighted impact
1.39
References
31
Authors
5

Abstract

Handwritten text recognition is challenging because of the virtually infinite ways a human can write the same message. Our fully convolutional handwriting model takes in a handwriting sample of unknown length and outputs an arbitrary stream of symbols. Our dual stream architecture uses both local and global context and mitigates the need for heavy preprocessing steps such as symbol alignment correction as well as complex post processing steps such as connectionist temporal classification, dictionary matching or language models. Using over 100 unique symbols, our model is agnostic to Latin-based languages, and is shown to be quite competitive with state of the art dictionary based methods on the popular IAM and RIMES datasets. When a dictionary is known, we further allow a probabilistic character error rate to correct errant word blocks. Finally, we introduce an attention based mechanism which can automatically target variants of handwriting, such as slant, stroke width, or noise.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Such, F. P., Peri, D., Brockler, F., Hutkowski, P., & Ptucha, R. (2018). Fully Convolutional Networks for Handwriting Recognition. International Conference on Frontiers in Handwriting Recognition, 86–91. https://doi.org/10.1109/icfhr-2018.2018.00024

MLA 9

Such, Felipe Petroski, et al. “Fully Convolutional Networks for Handwriting Recognition.” International Conference on Frontiers in Handwriting Recognition, 2018, pp. 86–91. https://doi.org/10.1109/icfhr-2018.2018.00024.

Chicago

Such, Felipe Petroski, Dheeraj Peri, Frank Brockler, Paul Hutkowski, and Raymond Ptucha. 2018. “Fully Convolutional Networks for Handwriting Recognition.” International Conference on Frontiers in Handwriting Recognition: 86–91. https://doi.org/10.1109/icfhr-2018.2018.00024.

Harvard

Such, F. P. et al. (2018) ‘Fully Convolutional Networks for Handwriting Recognition’, International Conference on Frontiers in Handwriting Recognition, pp. 86–91. doi:10.1109/icfhr-2018.2018.00024.

IEEE

F. P. Such, D. Peri, F. Brockler, P. Hutkowski, and R. Ptucha, “Fully Convolutional Networks for Handwriting Recognition,” International Conference on Frontiers in Handwriting Recognition, pp. 86–91, 2018, doi: 10.1109/icfhr-2018.2018.00024.

BibTeX

@inproceedings{such2018fully,
  title     = {{Fully Convolutional Networks for Handwriting Recognition}},
  author    = {Such, Felipe Petroski and Peri, Dheeraj and Brockler, Frank and Hutkowski, Paul and Ptucha, Raymond},
  booktitle = {International Conference on Frontiers in Handwriting Recognition},
  year      = {2018},
  pages     = {86--91},
  doi       = {10.1109/icfhr-2018.2018.00024},
  url       = {https://doi.org/10.1109/icfhr-2018.2018.00024}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
201811
201911
20201010
202177
202266
202355
202422
202544
202633

Its field-weighted citation impact is 1.39: it has been cited 1.39 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Handwritten Text Recognition Techniques

  • handwriting recognition
  • fully convolutional network
  • dual-stream architecture
  • local and global context
  • connectionist temporal classification
  • attention mechanism
  • IAM dataset

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Such, F. P., Peri, D., Brockler, F., Hutkowski, P., & Ptucha, R. (2018). Fully Convolutional Networks for Handwriting Recognition. International Conference on Frontiers in Handwriting Recognition, 86–91. https://doi.org/10.1109/icfhr-2018.2018.00024

How many times has this paper been cited?

39 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at arXiv (Cornell University).

Who wrote this paper?

Felipe Petroski Such, Dheeraj Peri, Frank Brockler, Paul Hutkowski, Raymond Ptucha.

What is the DOI of this paper?

10.1109/icfhr-2018.2018.00024. The permanent link is https://doi.org/10.1109/icfhr-2018.2018.00024.

Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.