Home > Archive > 2022 > Volume 12 Number 5 (Sept. 2022) >
IJMLC 2022 Vol.12(5): 154-163 ISSN: 2010-3700
DOI: 10.18178/ijmlc.2022.12.5.1095

Improvement in OCR Technologies in Postal Industry Using CNN-RNN Architecture: Literature Review

P. Verma and G. M. Foomani

Abstract—Convolutional Recurrent Neural Network (CRNN) based architecture is an attractive branch of Optical Character Recognition (OCR) studies. OCR is the process for transforming the image or the text obtained by scanning documents into machine-modifiable or editable format. It belongs to the domain of automatic identification of algorithms, modeled loosely after the animal brains, which are designed for pattern and character recognition. Hence, it falls under the neural networks category. An OCR system relies for the most part on the pre-processing, character/ image segmentation and feature extraction. This technology is an essential segment for automation processed in postal industry to read mail addresses and process mails. The first objective of this paper is to summarize the research that has been conducted in the field and further to present best in practice examples in this regard. Secondly, this research will also discuss about some gaps in the area and try to identify opportunities for future studies.

Index Terms—Automatic mail sorting, convolutional recurrent neural network (CRNN), neural networks, optical character recognition, postal industry.

P. Verma is with the Canada Post Corporation, Ottawa, Ontario, Canada. She is with Global Innovative Campus, Canada (e-mail: palak.verma@canadapost.postescanada.ca, pverma0402@gmail.com)
G. M. Foomani is with Canada Post Corporation, Ottawa, Ontario,Canada. He is now with the Department of Civil Engineering, Concordia University, Montreal, Quebec, Canada (e-mail: matin.giahifoomani@mail.concordia.ca, Matin.Foomani@canadapost.postescanada.ca).

[PDF]

Cite: P. Verma and G. M. Foomani, "Improvement in OCR Technologies in Postal Industry Using CNN-RNN Architecture: Literature Review," International Journal of Machine Learning and Computing vol. 12, no. 5, pp. 154-163, 2022.

Copyright @ 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

General Information

  • E-ISSN: 2972-368X
  • Abbreviated Title: Int. J. Mach. Learn.
  • Frequency: Quaterly
  • DOI: 10.18178/IJML
  • Editor-in-Chief: Dr. Lin Huang
  • Executive Editor:  Ms. Cherry L. Chen
  • Abstracing/Indexing: Inspec (IET), Google Scholar, Crossref, ProQuest, Electronic Journals LibraryCNKI.
  • E-mail: ijml@ejournal.net


Article Metrics in Dimensions