└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Deep Learning for OCR 2 | This is a reading list for deep learning for OCR. I became interested in this topic when I was developing a mobile app for receipt and shopping management. See [my homepage](https://hengshuaiyao.github.io/) for more this app. I am going to release the dataset we collected for this project. 3 | 4 | ## Papers 5 | - Reading text in the wild with convolutional neural networks (2016), M. Jaderberg et al. *(DeepMind)* [[pdf]](http://arxiv.org/pdf/1412.1842) 6 | - Recursive Recurrent Nets with Attention Modeling for OCR in the Wild, Chen-Yu Lee, Simon Osindero, 2016, [pdf](https://arxiv.org/pdf/1603.03101v1) 7 | - The Unreasonable Effectiveness of Recurrent Neural Networks, Andrej Karpathy, 2015, [blog](http://karpathy.github.io/2015/05/21/rnn-effectiveness/) 8 | - A Comparison of Sequence-Trained Deep Neural Networks and Recurrent Neural Networks Optical Modeling for Handwriting Recognition, Theodore Bluche, Hermann Ney, and Christopher Kermorvant, slsp, 2014. [pdf](http://www.a2ialab.com/lib/exe/fetch.php?media=publications:slsp2014.pdf) 9 | - Optical Character Recognition (OCR), Marina Samuel, [blog](http://aosabook.org/en/500L/optical-character-recognition-ocr.html) 10 | - Text Recognition in Videos using a Recurrent Connectionist Approach, Khaoula Elagouni, Christophe Garcia, Franck Mamalet1 11 | , and Pascale Sebillot, 2012. [pdf](http://liris.cnrs.fr/Documents/Liris-5660.pdf) 12 | - A Novel Word Spotting Method Based on Recurrent Neural Networks, Volkmar Frinken, Andreas Fischer, R. Manmatha, and Horst Bunke, [pdf](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.367.75&rep=rep1&type=pdf) 13 | - SEQUENCE TO SEQUENCE LEARNING FOR OPTICAL CHARACTER RECOGNITION, Devendra Kumar Sahu & Mohak Sukhwani, 2015, [pdf](http://arxiv.org/pdf/1511.04176.pdf) 14 | - Scan, Attend and Read: End-to-End Handwritten Paragraph Recognition with MDLSTM Attention, Theodore Bluche Jerome Louradour, Ronaldo Messina, 2016. [pdf](https://arxiv.org/pdf/1604.03286.pdf) 15 | - Recursive Recurrent Nets with Attention Modeling for OCR in the Wild, Chen-Yu Lee, Simon Osindero, CVPR, 2016, [pdf](http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Lee_Recursive_Recurrent_Nets_CVPR_2016_paper.pdf) 16 | - Reading Scene Text in Deep Convolutional Sequences, Pan He, Weilin Huang, Yu Qiao, Chen Change Loy, and Xiaoou Tang, 2016, [pdf](http://www.whuang.org/papers/phe2016_aaai.pdf) 17 | - Multi-digit Number Recognition from Street View, Imagery using Deep Convolutional Neural Networks, Ian J. Goodfellow, Yaroslav Bulatov, Julian Ibarz, Sacha Arnoud, Vinay Shet. 2014. [pdf](https://arxiv.org/pdf/1312.6082.pdf) 18 | - ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks, Francesco Visin, Kyle Kastner,Kyunghyun Cho, Matteo Matteucci,Aaron Courville, Yoshua Bengio. [pdf](https://arxiv.org/pdf/1505.00393.pdf) 19 | - End-to-End Text Recognition with Convolutional Neural Networks, Tao Wang, David J. Wu, Adam Coates, Andrew Y. Ng, ICPR, 2012. [pdf](https://crypto.stanford.edu/~dwu4/papers/ICPR2012.pdf) 20 | - Towards End-to-End Speech Recognition with Recurrent Neural Networks. Alex Graves, Navdeep Jaitly. ICML, 2014. [pdf](http://www.jmlr.org/proceedings/papers/v32/graves14.pdf) 21 | - PhotoOCR: Reading Text in Uncontrolled Conditions, Alessandro Bissacco, Mark Cummins, Yuval Netzer, Hartmut Neven. [pdf](https://ai2-s2-pdfs.s3.amazonaws.com/31a8/803d7e2618bfa44c472d003055bb5961b9de.pdf) 22 | - High Performance OCR for Printed English and Fraktur using LSTM Networks. ICDAR, 2013. [pdf](https://www.researchgate.net/profile/Adnan_Ul-Hasan/publication/260341302_High_Performance_OCR_for_Printed_English_and_Fraktur_using_LSTM_Networks/links/0deec530da5e58f067000000.pdf?origin=publication_detail) 23 | - Image binarization for end-to-end text understanding in natural images, Sergey Milyaev, Olga Barinova, Tatiana Novikova, Pushmeet Kohli, Victor Lempitsky. ICDAR, 2013, [pdf](http://research.microsoft.com/en-us/um/people/pkohli/papers/mbnlk_icdar2013.pdf) 24 | - Deep Features for Text Spotting, European Conference on Computer Vision, M. Jaderberg, A. Vedaldi, A. Zisserman, 2014. [pdf](http://www.robots.ox.ac.uk/~vgg/publications/2014/Jaderberg14/jaderberg14.pdf.pdf), [code](https://bitbucket.org/socialauth/migrate/?next=/jaderberg/eccv2014_textspotting) 25 | 26 | 27 | --------------------------------------------------------------------------------