# Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks

## TL;DR

This paper introduces a simple, fully convolutional neural network architecture for unconstrained text recognition that is data-efficient, highly accurate, and versatile across various tasks, achieving state-of-the-art results.

## Contribution

The paper presents a novel, fully convolutional, end-to-end neural network model trained with CTC loss for generic text recognition, eliminating the need for recurrent connections.

## Key findings

- Achieved state-of-the-art results on seven benchmark datasets.
- Won the ICFHR2018 Competition on Automated Text Recognition.
- Demonstrated versatility across multiple text recognition tasks.

## Abstract

Unconstrained text recognition is an important computer vision task, featuring a wide variety of different sub-tasks, each with its own set of challenges. One of the biggest promises of deep neural networks has been the convergence and automation of feature extractors from input raw signals, allowing for the highest possible performance with minimum required domain knowledge. To this end, we propose a data-efficient, end-to-end neural network model for generic, unconstrained text recognition. In our proposed architecture we strive for simplicity and efficiency without sacrificing recognition accuracy. Our proposed architecture is a fully convolutional network without any recurrent connections trained with the CTC loss function. Thus it operates on arbitrary input sizes and produces strings of arbitrary length in a very efficient and parallelizable manner. We show the generality and superiority of our proposed text recognition architecture by achieving state of the art results on seven public benchmark datasets, covering a wide spectrum of text recognition tasks, namely: Handwriting Recognition, CAPTCHA recognition, OCR, License Plate Recognition, and Scene Text Recognition. Our proposed architecture has won the ICFHR2018 Competition on Automated Text Recognition on a READ Dataset.