STN-OCR: A single Neural Network for Text Detection and Text Recognition
This addresses the challenge of scene text recognition for computer vision applications, but it is incremental as it builds on existing neural network approaches.
The paper tackles the problem of detecting and recognizing text in natural scene images by proposing STN-OCR, a single neural network that integrates spatial transformer and text recognition components for end-to-end optimization, achieving competitive performance on public benchmarks without major structural changes.
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.