# Efficient, Lexicon-Free OCR using Deep Learning

arXiv: https://arxiv.org/abs/1906.01969 · HTML: https://mlsanity.com/paper/1906.01969/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jun 2019.

## Built on by (most cited first, 5 of 5)

- [IDPL-PFOD2: A New Large-Scale Dataset for Printed Farsi Optical Character Recognition](https://mlsanity.com/paper/2312.01177/) (2023)
- [Noise-Aware Named Entity Recognition for Historical VET Documents](https://mlsanity.com/paper/2601.00488/) (2026)
- [An end-to-end, interactive Deep Learning based Annotation system for cursive and print English handwritten text](https://mlsanity.com/paper/2304.08670/) (2023)
- [Advancing Generative Model Evaluation: A Novel Algorithm for Realistic Image Synthesis and Comparison in OCR System](https://mlsanity.com/paper/2402.17204/) (2024)
- [Two-Step Occupation Coding](https://mlsanity.com/paper/2607.20101/) (2026)

## Abstract (arXiv)

Contrary to popular belief, Optical Character Recognition (OCR) remains a challenging problem when text occurs in unconstrained environments, like natural scenes, due to geometrical distortions, complex backgrounds, and diverse fonts. In this paper, we present a segmentation-free OCR system that combines deep learning methods, synthetic training data generation, and data augmentation techniques. We render synthetic training data using large text corpora and over 2000 fonts. To simulate text occurring in complex natural scenes, we augment extracted samples with geometric distortions and with a proposed data augmentation technique - alpha-compositing with background textures. Our models employ a convolutional neural network encoder to extract features from text images. Inspired by the recent progress in neural machine translation and language modeling, we examine the capabilities of both recurrent and convolutional neural networks in modeling the interactions between input elements.