OCR

Papers

End-to-End Text Recognition with Convolutional Neural Networks

• paper: http://www.cs.stanford.edu/~acoates/papers/wangwucoatesng_icpr2012.pdf
• PhD thesis: http://cs.stanford.edu/people/dwu4/HonorThesis.pdf

Word Spotting and Recognition with Embedded Attributes

• paper: http://ieeexplore.ieee.org.sci-hub.org/xpl/articleDetails.jsp?arnumber=6857995&filter%3DAND%28p_IS_Number%3A6940341%29

Reading Text in the Wild with Convolutional Neural Networks

• paper: http://arxiv.org/abs/1412.1842
• homepage: http://www.robots.ox.ac.uk/~vgg/publications/2016/Jaderberg16/
• demo: http://zeus.robots.ox.ac.uk/textsearch/#/search/
• code: http://www.robots.ox.ac.uk/~vgg/research/text/

Deep structured output learning for unconstrained text recognition

• intro: “propose an architecture consisting of a character sequence CNN and an N-gram encoding CNN which act on an input image in parallel and whose outputs are utilized along with a CRF model to recognize the text content present within the image.”
• arxiv: http://arxiv.org/abs/1412.5903

Deep Features for Text Spotting

• paper: http://www.robots.ox.ac.uk/~vgg/publications/2014/Jaderberg14/jaderberg14.pdf
• code: https://bitbucket.org/jaderberg/eccv2014_textspotting
• GitXiv: http://gitxiv.com/posts/uB4y7QdD5XquEJ69c/deep-features-for-text-spotting

High Performance Offline Handwritten Chinese Character Recognition Using GoogLeNet and Directional Feature Maps

• arXiv: http://arxiv.org/abs/1505.04925
• github: https://github.com/zhongzhuoyao/HCCR-GoogLeNet

Reading Scene Text in Deep Convolutional Sequences

• arxiv: http://arxiv.org/abs/1506.04395

DeepFont: Identify Your Font from An Image

• arxiv: http://arxiv.org/abs/1507.03196

An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

• arXiv: http://arxiv.org/abs/1507.05717

Character-level Convolutional Networks for Text Classification(NIPS 2015. “Text Understanding from Scratch)

• paper: http://arxiv.org/abs/1509.01626
• code: https://github.com/zhangxiangxiao/Crepe
• datasets: http://goo.gl/JyCnZq

Object Proposals for Text Extraction in the Wild((ICDAR 2015)

• arXiv: http://arxiv.org/abs/1509.02317
• github: https://github.com/lluisgomez/TextProposals

Text-Attentional Convolutional Neural Networks for Scene Text Detection

• arXiv: http://arxiv.org/abs/1510.03283

Reading Car License Plates Using Deep Convolutional Neural Networks and LSTMs

• arxiv: http://arxiv.org/abs/1601.05610

COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images

• homepage: http://vision.cornell.edu/se3/coco-text/
• arxiv: http://arxiv.org/abs/1601.07140

Recursive Recurrent Nets with Attention Modeling for OCR in the Wild

• arxiv: http://arxiv.org/abs/1603.03101

Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network

• arxiv: http://arxiv.org/abs/1603.09423

Blogs

Recognize your handwritten numbers

https://medium.com/@o.kroeger/recognize-your-handwritten-numbers-3f007cbe46ff#.jllz62xgu

Training a Computer to Recognize Your Handwriting

https://medium.com/@annalyzin/training-a-computer-to-recognize-your-handwriting-24b808fb584#.gd4pb9jk2

Projects

Reading irctc captchas with 95% accuracy using deep learning

• github: https://github.com/arunpatala/captcha.irctc

ocropy: Python-based tools for document analysis and OCR

• github: https://github.com/tmbdev/ocropy

Extracting text from an image using Ocropus

• blog: http://www.danvk.org/2015/01/09/extracting-text-from-an-image-using-ocropus.html

CLSTM : A small C++ implementation of LSTM networks, focused on OCR

• github: https://github.com/tmbdev/clstm