Abstract | ||
---|---|---|
We present a novel end-to-end trainable OCR system combining a CNN for feature extraction with 1-D LSTMs for sequence modeling. We present results on English and Arabic handwriting data, and on English machine print data, showing state-of-the-art performance. We believe that our method is simpler than existing 2D LSTM models, and will make it easier to use techniques borrowed from CNN research in computer vision to improve OCR performance. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/ICDAR.2017.34 | 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) |
Keywords | Field | DocType |
OCR performance,convolutional neural networks,LSTMs,segmentation-free OCR,end-to-end trainable OCR system,feature extraction,sequence modeling,English machine print data,English handwriting data,Arabic handwriting data,computer vision | Arabic handwriting,Pattern recognition,Convolutional neural network,Segmentation,Computer science,Handwriting recognition,Feature extraction,Artificial intelligence,Sequence modeling,Decoding methods,Hidden Markov model | Conference |
Volume | ISSN | ISBN |
01 | 1520-5363 | 978-1-5386-3587-2 |
Citations | PageRank | References |
1 | 0.36 | 16 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
stephen rawls | 1 | 59 | 4.08 |
Huaigu Cao | 2 | 347 | 29.09 |
Kumar, S. | 3 | 4 | 1.81 |
Premkumar Natarajan | 4 | 874 | 79.46 |