Scene Text recognition with Full Normalization

Abstract

Scene text recognition has made significant progress in recent years and has become an important part of the work-flow. The widespread use of mobile devices opens up wide possibilities for using OCR technologies in everyday life. However, lack of training data for new research in this area remains relevant. In this article, we present a new dataset consisting of real shots on smartphones and demonstrate the effectiveness of profile normalization in this task. In addition, the influence of various augmentations during the training of models for analyzing document images on smartphones is studied in detail. Our dataset is publicly available.

arXiv commentarXiv admin note: text overlap with arXiv:1907.09653 by other authors

References in corpus (7)

• Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
• Focusing Attention: Towards Accurate Text Recognition in Natural Images
• TextBoxes: A Fast Text Detector with a Single Deep Neural Network
• Text-Attentional Convolutional Neural Networks for Scene Text Detection
• Single Shot Text Detector with Regional Attention
• Scene Text Synthesis for Efficient and Effective Deep Network Training
• Towards Realistic 3D Embedding via View Alignment