Unsupervised feature learning for optical character recognition

Abstract

Most of the popular optical character recognition (OCR) architectures use a set of handcrafted features and a powerful classifier for isolated character classification. Success of these methods often depend on the suitability of these features for the language of interest. In recent years, whole word recognition based on Recurrent Neural Networks (RNN) has… (More)
DOI: 10.1109/ICDAR.2015.7333920

Topics

5 Figures and Tables

Statistics

0204020162017
Citations per Year

Citation Velocity: 8

Averaging 8 citations per year over the last 2 years.

Learn more about how we calculate this metric in our FAQ.

Cite this paper

@article{Sahu2015UnsupervisedFL, title={Unsupervised feature learning for optical character recognition}, author={Devendra K. Sahu and C. V. Jawahar}, journal={2015 13th International Conference on Document Analysis and Recognition (ICDAR)}, year={2015}, pages={1041-1045} }