Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition

TL;DR

This paper introduces a synthetic data-driven neural network framework for natural scene text recognition that outperforms existing methods without requiring real labeled data.

Contribution

It presents a novel approach using synthetic data to train holistic neural networks for scene text recognition, eliminating the need for human-labeled datasets.

Findings

Achieved state-of-the-art results on standard datasets.

Demonstrated effectiveness of synthetic data for training neural networks.

Compared three different word recognition models with high accuracy.

Abstract

In this work we present a framework for the recognition of natural scene text. Our framework does not require any human-labelled data, and performs word recognition on the whole image holistically, departing from the character based recognition systems of the past. The deep neural network models at the centre of this framework are trained solely on data produced by a synthetic text generation engine -- synthetic data that is highly realistic and sufficient to replace real data, giving us infinite amounts of training data. This excess of data exposes new possibilities for word recognition models, and here we consider three models, each one "reading" words in a different way: via 90k-way dictionary encoding, character sequence encoding, and bag-of-N-grams encoding. In the scenarios of language based and completely unconstrained text recognition we greatly improve upon state-of-the-art performance on standard datasets, using our fast, simple machinery and requiring zero data-acquisition costs.