Robust Scene Text Recognition with Automatic Rectification

TL;DR

This paper introduces RARE, a deep neural network that automatically rectifies irregular scene text images using a Thin-Plate-Spline transformation, significantly improving recognition accuracy of curved and perspective-distorted text in natural images.

Contribution

The paper presents RARE, a novel end-to-end trainable model combining a Spatial Transformer Network and a Sequence Recognition Network for robust scene text recognition.

Findings

Achieves state-of-the-art performance on multiple benchmarks.

Effectively recognizes perspective and curved text.

End-to-end trainable with only images and labels.

Abstract

Recognizing text in natural images is a challenging task with many unsolved problems. Different from those in documents, words in natural images often possess irregular shapes, which are caused by perspective distortion, curved character placement, etc. We propose RARE (Robust text recognizer with Automatic REctification), a recognition model that is robust to irregular text. RARE is a specially-designed deep neural network, which consists of a Spatial Transformer Network (STN) and a Sequence Recognition Network (SRN). In testing, an image is firstly rectified via a predicted Thin-Plate-Spline (TPS) transformation, into a more "readable" image for the following SRN, which recognizes text through a sequence recognition approach. We show that the model is able to recognize several types of irregular text, including perspective text and curved text. RARE is end-to-end trainable, requiring only images and associated text labels, making it convenient to train and deploy the model in practical systems. State-of-the-art or highly-competitive performance achieved on several benchmarks well demonstrates the effectiveness of the proposed model.