Robust Scene Text Recognition with Automatic Rectification
arXiv:1603.03915
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.
Accepted by CVPR 2016
References in corpus (8)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Neural Machine Translation by Jointly Learning to Align and Translate
- Sequence to Sequence Learning with Neural Networks
- ADADELTA: An Adaptive Learning Rate Method
- On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
- Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
- Deep Structured Output Learning for Unconstrained Text Recognition
- Multi-Oriented Text Detection with Fully Convolutional Networks
Cited by in corpus (6)
- Self-Supervised Learning for Videos: A Survey
- UTRNet: High-Resolution Urdu Text Recognition In Printed Documents
- You Only Recognize Once: Towards Fast Video Text Spotting
- Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting
- Object-QA: Towards High Reliable Object Quality Assessment
- Using Human Psychophysics to Evaluate Generalization in Scene Text Recognition Models