Can we build language-independent OCR using LSTM networks?

Language models or recognition dictionaries are usually considered an essential step in OCR. However, using a language model complicates training of OCR systems, and it also narrows the range of texts that an OCR system can be used with. Recent results have shown that Long Short-Term Memory (LSTM) based OCR yields low error rates even without language modeling. In this paper, we explore the question to what extent LSTM models can be used for multilingual OCR without the use of language models. To do this, we measure cross-language performance of LSTM models trained on different languages. LSTM models show good promise to be used for language-independent OCR. The recognition errors are very low (around 1%) without using any language model or dictionary correction.

[1]  Henry S. Baird,et al.  Document image defect models , 1995 .

[2]  Thomas M. Breuel,et al.  The OCRopus open source OCR system , 2008, Electronic Imaging.

[3]  Yoshua Bengio,et al.  Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies , 2001 .

[4]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[5]  Richard M. Schwartz,et al.  Multilingual Machine Printed OCR , 2001, Int. J. Pattern Recognit. Artif. Intell..

[6]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[7]  Jürgen Schmidhuber,et al.  Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks , 2006, ICML.

[8]  W. Marsden.  I and J , 2012 .

[9]  R. Smith,et al.  An Overview of the Tesseract OCR Engine , 2007, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007).

[10]  Andrew W. Senior,et al.  Off-line Cursive Handwriting Recognition using Recurrent Neural Networks , 1994 .

[11]  Jakir Hossain,et al.  Multilingual OCR (MOCR): An Approach to Classify Words to Languages , 2011 .

[12]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[13]  Thomas M. Breuel,et al.  High-Performance OCR for Printed English and Fraktur Using LSTM Networks , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[14]  Herbert Jaeger,et al.  A tutorial on training recurrent neural networks , covering BPPT , RTRL , EKF and the " echo state network " approach - Semantic Scholar , 2005 .

[15]  Raymond Smith,et al.  Adapting the Tesseract open source OCR engine for multilingual OCR , 2009, MOCR '09.