under construction ...
•Challenges
•Methodologies
•Fundamental Sub-problems
•Datasets
•Remaining problems
•TextBoxes: A Fast Text Detector with a Single Deep Neural Network
•Detecting Oriented Text in Natural Images by Linking Segments
•Text Flow: A Unified Text Detection System in Natural Scene Images
•DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images
•Deep TextSpotter: An End-to-End Trainable Scene Text Localization and Recognition Framework
•Reading Scene Text in Deep Conv. Sequences
•An E2E Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
•Robust Scene Text Recognition with Automatic Rectification
•Drawing and Recognizing Chinese Characters with Recurrent Neural Network
•SEE: Towards Semi-Supervised E2E Scene Text Recognition
•Visual attention models for scene text recognition
•Focusing Attention: Towards Accurate Text Recognition in Natural Images
•Recursive Recurrent Nets with Attention Modeling for OCR in the Wild
•Rosetta: Large Scale System for Text Detection and Recognition in Images
•Fooling OCR Systems with Adversarial Text Images
•Appendix: Open OCR Engines
•Tesseract
•Umaru (CLSTM+RNNLib)
•Ocropy (Ocropy2)
•Attention-OCR
•SynthText (+Chinese version)
•Calamari (OCRopy + Kraken)