読者です 読者をやめる 読者になる 読者になる

OCR・文字認識の論文とかのまとめ

必要な気がしてまとめました。現在は文字領域を物体認識と同じ要領で切り取ってから文字を認識、といった形が最も強いのかな。 ただ手書き文字認識とか色々ごっちゃになってまとまりがない...。

論文

End-to-End Text Recognition with Convolutional Neural Networks

pdf: ここ

Wang, Tao, et al. "End-to-end text recognition with convolutional neural networks." Pattern Recognition (ICPR), 2012 21st International Conference on. IEEE, 2012.

Word Spotting and Recognition with Embedded Attributes

Almazán, Jon, et al. "Word spotting and recognition with embedded attributes." IEEE transactions on pattern analysis and machine intelligence 36.12 (2014): 2552-2566.

Deep structured output learning for unconstrained text recognition

Jaderberg, Max, et al. "Deep structured output learning for unconstrained text recognition." arXiv preprint arXiv:1412.5903 (2014).

Deep Features for Text Spotting

Jaderberg, Max, Andrea Vedaldi, and Andrew Zisserman. "Deep features for text spotting." European conference on computer vision. Springer International Publishing, 2014.

http://gitxiv.com/posts/uB4y7QdD5XquEJ69c/deep-features-for-text-spotting

Reading Text in the Wild with Convolutional Neural Networks

pdf: [1412.1842] Reading Text in the Wild with Convolutional Neural Networks

Jaderberg, Max, et al. "Reading text in the wild with convolutional neural networks." International Journal of Computer Vision 116.1 (2016): 1-20.

コード: Visual Geometry Group Home Page

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

pdf: [1507.05717] An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

Shi, Baoguang, Xiang Bai, and Cong Yao. "An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition." arXiv preprint arXiv:1507.05717 (2015).

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

pdf: [1601.07140] COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images

Veit, Andreas, et al. "COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images." arXiv preprint arXiv:1601.07140 (2016).

Strokelets: A Learned Multi-Scale Mid-Level Representation for Scene Text Recognition

pdf: ここ

f:id:misos:20161106004158p:plain

Bai, Xiang, Cong Yao, and Wenyu Liu. "Strokelets: A Learned Multi-Scale Mid-Level Representation for Scene Text Recognition." IEEE Transactions on Image Processing 25.6 (2016): 2789-2802.

Object Proposals for Text Extraction in the Wild

Gomez, Lluis, and Dimosthenis Karatzas. "Object proposals for text extraction in the wild." Document Analysis and Recognition (ICDAR), 2015 13th International Conference on. IEEE, 2015.

pdf: [1509.02317] Object Proposals for Text Extraction in the Wild

解説・チュートリアルブログ

LeNet – Convolutional Neural Network in Python

Handwritten Digit Recognition using Convolutional Neural Networks in Python with Keras

machinelearningmastery.com

Using TensorFlow to create your own handwriting recognition engine

Applying OCR Technology for Receipt Recognition