STN-OCR: A single Neural Network for Text Detection and Text Recognition

TL;DR

STN-OCR introduces a unified neural network that jointly detects and recognizes text in natural scene images, enabling end-to-end training and semi-supervised learning for improved scene text understanding.

Contribution

It presents a novel single neural network architecture combining detection and recognition, simplifying previous multi-step systems and enabling end-to-end semi-supervised training.

Findings

Effective detection and recognition of text in diverse images

Handles multiple tasks without changing network structure

Competitive performance on benchmark datasets

Abstract

Detecting and recognizing text in natural scene images is a challenging, yet not completely solved task. In re- cent years several new systems that try to solve at least one of the two sub-tasks (text detection and text recognition) have been proposed. In this paper we present STN-OCR, a step towards semi-supervised neural networks for scene text recognition, that can be optimized end-to-end. In contrast to most existing works that consist of multiple deep neural networks and several pre-processing steps we propose to use a single deep neural network that learns to detect and recognize text from natural images in a semi-supervised way. STN-OCR is a network that integrates and jointly learns a spatial transformer network, that can learn to detect text regions in an image, and a text recognition network that takes the identified text regions and recognizes their textual content. We investigate how our model behaves on a range of different tasks (detection and recognition of characters, and lines of text). Experimental results on public benchmark datasets show the ability of our model to handle a variety of different tasks, without substantial changes in its overall network structure.