awesome-ocr

A few things I find useful. Please check back later.

Popular Projects

1. Tesseract
   • Python wrapper: https://github.com/sirfz/tesserocr
   • Python wrapper: https://github.com/openpaperwork/pyocr
2. Tesseract JS
3. React Native wrapper for tesseract: https://github.com/jonathanpalma/react-native-tesseract-ocr

Applications (Open Source)

1. paperwork - Personal document manager (Linux/Windows) - https://openpaper.work/
2. paperless - Scan, index, and archive all of your paper documents
3. card.io to Scan credit cards in your mobile app
4. open-paperless - Scan, index, and archive all of your paper documents (acquired by Mayan EDMS) https://openpaperless.com
5. https://github.com/mre/receipt-parser
6. https://github.com/isee15/Card-Ocr
7. Python and OpenCV scripts to detect digits on a Gas Pump
8. Deep Learning OCR using TensorFlow and Python
9. Extracting Text from Binary Document Formats using AWS Lambda
10. Receipt scanner extracts information from your PDF or image receipts - built in NodeJS
11. OCR engine for all the languages http://kraken.re
12. Python wrapper to grab text from all the images in a directory and save a subdirectory as text files using Tesseract Engine

APIs and Products (mostly paid)

1. https://cloud.google.com/vision/
2. https://azure.microsoft.com/en-in/services/cognitive-services/computer-vision/
3. https://cloud.google.com/functions/docs/tutorials/ocr
4. https://www.silversparro.com/single-post/2018/02/20/Automated-Document-Classification-using-Deep-Learning-APIs
5. https://blog.signzy.com/how-we-replaced-humans-in-identity-card-classification-with-our-deep-learning-ai-ae8c6564e338
6. https://www.idfy.com/products
7. http://hyperverge.co/bfsi.html (Demo on YouTube)

Lit Review

1. Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks
2. https://www.researchgate.net/publication/321813745_Text_recognition_on_PAN_card_using_template_matching_method

Other awesome-repos

1. A collection of resources (including the papers and datasets) of OCR
2. Extract text information from Aadhaar Card using tesseract-ocr
3. PAN Card OCR

Document Management and Search Systems

1. https://github.com/sismics/docs
2. https://github.com/RD17/ambar

Extracting (tables?) from PDFs

1. https://github.com/WZBSocialScienceCenter/pdftabextract
2. https://github.com/jbarlow83/OCRmyPDF

Synthetic Data Generator

1. https://github.com/Belval/TextRecognitionDataGenerator
2. https://github.com/Sanster/text_renderer

Deep Learning in Action

1. https://github.com/weinman/cnn_lstm_ctc_ocr
2. https://github.com/eragonruan/text-detection-ctpn
3. https://github.com/bgshih/crnn
4. https://github.com/tianzhi0549/CTPN
5. https://github.com/pannous/tensorflow-ocr 6, https://github.com/MhLiao/TextBoxes_plusplus
6. https://github.com/emedvedev/attention-ocr
7. https://github.com/dengdan/seglink
8. https://github.com/wushilian/CRNN_Attention_OCR_Chinese
9. https://github.com/DetectionTeamUCAS/R2CNN_Faster-RCNN_Tensorflow
10. https://github.com/watsonyanghx/CNN_LSTM_CTC_Tensorflow

Blogposts and QnA (to be sorted through)

0. Official Tess Wiki - Improving the quality of the output
1. Mastercard or Visa ? Image classification with Transfer Learning and Fastai
2. Detecting the National ID card and getting the details
3. Algorithm to detect credit card sized card
4. Deep Learning based Text Recognition (OCR) using Tesseract and OpenCV
5. Credit card OCR with OpenCV and Python
6. we are doing pan OCR, using tesseract but is not able to detect the details like name and pan number
7. image processing to improve tesseract OCR accuracy
8. Using tesseract to recognize license plates
9. Improve Accuracy of OCR using Image Preprocessing
10. Detect text region in image using Opencv
11. we are doing pan OCR, using tesseract but is not able to detect the details like name and pan number