Conference paper Open Access

Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition

Michael, Johannes; Labahn, Roger; Gruning, Tobias; Zollner, Jochen

Encoder-decoder models have become an effective approach for sequence learning tasks like machine translation, image captioning and speech recognition, but have yet to show competitive results for handwritten text recognition. To this end, we propose an attention-based sequence-to-sequence model. It combines a convolutional neural network as a generic feature extractor with a recurrent neural network to encode both the visual information, as well as the temporal context between characters in the input image, and uses a separate recurrent neural network to decode the actual character sequence. We make experimental comparisons between various attention mechanisms and positional encodings, in order to find an appropriate alignment between the input and output sequence. The model can be trained end-to-end and the optional integration of a hybrid loss allows the encoder to retain an interpretable and usable output, if desired. We achieve competitive results on the IAM and ICFHR2016 READ data sets compared to the state-of-theart without the use of a language model, and we significantly improve over any recent sequence-to-sequence approaches.

Files (347.6 kB)
Name Size
Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition.pdf
347.6 kB Download
All versions This version
Views 208208
Downloads 101101
Data volume 35.1 MB35.1 MB
Unique views 179179
Unique downloads 9090


Cite as