└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Curated-scene-text-recognition-analysis 2 | 3 | ## Contributing 4 | Please feel free to [pull requests](https://github.com/seungwooYoo/curated-scene-text-recognition-analysis/pulls), email seungwoo.yoo@gmail.com. 5 | 6 | -------------------- 7 | 8 | ### Datasets 9 | 1. [Oxford Dataset](http://www.robots.ox.ac.uk/~vgg/data/text/) Synthetic word / character datasets. Containing 9M images covering 90k English words. Introduced in the "*M. Jadderberg, and Vedaldi, A. and Zisserman, A.* Deep Features for Text Spotting, ECCV14" 10 | 2. [Street View Text](http://vision.ucsd.edu/~kai/svt/) Street view text image dataset. Gathering from Google Street View. Introduced in the "*Kai Wang and Serge Belong* Word Spotting in the Wild, ECCV 10" 11 | 3. [Chars74K](http://www.ee.surrey.ac.uk/CVSSP/demos/chars74k/) Cropped character images including English, Latin and Hindu-Arabic numerals. Consisting of 64 classes, 7k characters from natural images, 3k handwritten, 60k synthetic images. 12 | 4. [ICDAR03 Robust Reading](http://www.iapr-tc11.org/mediawiki/index.php/ICDAR_2003_Robust_Reading_Competitions) For ICDAR 2003 Robust Reading competitions. 13 | 5. [ICDAR05 Robust Reading](http://www.iapr-tc11.org/mediawiki/index.php/ICDAR_2005_Robust_Reading_Competitions) For ICDAR 2005 Robust Reading competitions. 14 | 5. [MSRA Text Detection](http://www.iapr-tc11.org/mediawiki/index.php/MSRA_Text_Detection_500_Database_(MSRA-TD500)) Containing 500 natural images, with various geometric distortion like perspective distortion. The resolutions of the images vary from 1296x864 to 1920x1280. Introduced in the "*C. Yao, X. Bai, W. Liu, Y. Ma and Z. Tu.* Detecting Texts of Arbitrary Orientations in Natural Images. CVPR 2012" 15 | 6. [SIW-10](http://mc.eistar.net/~xbai/mspnProjectPage/) Script identification datasets - 13,045 multi-scripts text line images in 10 classes, cropped from 7,700 full images taken in-the-wild (Google street view). Introduced in the "*Baoguang Shi, Cong Yao, Chengquan Zhang, Xiaowei Guo, Feiyue Huang, Xiang Bai*, Automatic Script Identification in the Wild. ICDAR 2015" 16 | 7. [Text/Nontext scene dataset](http://mc.eistar.net/~xbai/textDis/textDis.html) Contains 5302 text images and 6000 non-text images, while the testing set contains 2000 text images and 2000 non-text images. Introduced in "*Chengquan Zhang, Cong Yao, Baoguang Shi, Xiang Bai*, Automatic Discrimination of Text and Non-Text Natural Images, ICDAR 2015" 17 | 18 | ------------------- 19 | 20 | 21 | ### Open-source 22 | 23 | 1. [Tesseract] (https://github.com/tesseract-ocr/tesseract) Optical character recognition toolkit. Recognize 39 languages and UTF8 capable. Written in C++. 24 | 2. [clstm](https://github.com/tmbdev/clstm) A small C++ implementation of LSTM networks, focused on OCR. Written in C++ with Python bindings. 25 | 3. [ocrpy](https://github.com/tmbdev/clstm) Python-based OCR package using recurrent neural networks. 26 | 4. [ocrDemo](https://github.com/ptommassen/ocr-demo) OCR-implementation in Android using OpenCV and Tesseract 27 | 5. [LTPTextDetector](https://github.com/mop/LTPTextDetector) Text detector written in C++. Introduced in "*Michael Opitz, Markus Diem, Markus Diem, Florian Kleber, Stefan Fiel and Robert Sablatnig*, End-to-End Text Recognition using Local Ternary Patterns, MSER and Deep Convolutional Neural Networks, DAS 2014. 28 | 5. [Vuforia Text Recognition](https://developer.vuforia.com/library/articles/Training/Text-Recognition-Guide) Qualcomm Vuforia Text recognition SDK. Support custom word lists, various fonts and styles. 29 | 30 | --------------------- 31 | 32 | 33 | ### Miscellaneous 34 | 1. [IAPR TC11 Dataset List](http://www.iapr-tc11.org/mediawiki/index.php/Datasets_List) International Association for Pattern Recognition, Technical Committee 11. Well documented and summarized various datasets and tools for document recognition and analysis 35 | 36 | 37 | --------------------- 38 | ### Paper 39 | --------------------------------------------------------------------------------