TextSR: Content-Aware Text Super-Resolution Guided by Recognition

TL;DR

This paper introduces TextSR, a content-aware super-resolution network guided by recognition loss, which enhances low-resolution scene text images to improve recognition accuracy, outperforming traditional methods that focus on natural image textures.

Contribution

It proposes the first text-specific super-resolution method that jointly optimizes for recognition performance using a novel Text Perceptual Loss.

Findings

Significant improvement in text recognition accuracy on challenging benchmarks.

Effective restoration of sharp high-resolution text images from blurred inputs.

End-to-end training of super-resolution and recognition networks enhances performance.

Abstract

Scene text recognition has witnessed rapid development with the advance of convolutional neural networks. Nonetheless, most of the previous methods may not work well in recognizing text with low resolution which is often seen in natural scene images. An intuitive solution is to introduce super-resolution techniques as pre-processing. However, conventional super-resolution methods in the literature mainly focus on reconstructing the detailed texture of natural images, which typically do not work well for text due to the unique characteristics of text. To tackle these problems, in this work, we propose a content-aware text super-resolution network to generate the information desired for text recognition. In particular, we design an end-to-end network that can perform super-resolution and text recognition simultaneously. Different from previous super-resolution methods, we use the loss of text recognition as the Text Perceptual Loss to guide the training of the super-resolution network, and thus it pays more attention to the text content, rather than the irrelevant background area. Extensive experiments on several challenging benchmarks demonstrate the effectiveness of our proposed method in restoring a sharp high-resolution image from a small blurred one, and show that the recognition performance clearly boosts up the performance of text recognizer. To our knowledge, this is the first work focusing on text super-resolution. Code will be released in https://github.com/xieenze/TextSR.