Reading Text in the Wild with Convolutional Neural Networks

TL;DR

This paper introduces an end-to-end deep learning system for detecting and recognizing text in natural images, achieving state-of-the-art results and enabling real-world applications like searchable news footage.

Contribution

It presents a novel combination of proposal generation and large CNNs trained on synthetic data for end-to-end text spotting and retrieval.

Findings

State-of-the-art performance on standard benchmarks

Large CNNs trained on synthetic data outperform character classifiers

Effective real-world application for searchable news footage

Abstract

In this work we present an end-to-end system for text spotting -- localising and recognising text in natural scene images -- and text based image retrieval. This system is based on a region proposal mechanism for detection and deep convolutional neural networks for recognition. Our pipeline uses a novel combination of complementary proposal generation techniques to ensure high recall, and a fast subsequent filtering stage for improving precision. For the recognition and ranking of proposals, we train very large convolutional neural networks to perform word recognition on the whole proposal region at the same time, departing from the character classifier based systems of the past. These networks are trained solely on data produced by a synthetic text generation engine, requiring no human labelled data. Analysing the stages of our pipeline, we show state-of-the-art performance throughout. We perform rigorous experiments across a number of standard end-to-end text spotting benchmarks and text-based image retrieval datasets, showing a large improvement over all previous methods. Finally, we demonstrate a real-world application of our text spotting system to allow thousands of hours of news footage to be instantly searchable via a text query.