Fast Multi-language LSTM-based Online Handwriting Recognition
This work addresses handwriting recognition for multiple languages, offering significant performance improvements, though it appears incremental as it builds on existing sequence recognition methods.
The paper tackled online handwriting recognition for 102 languages using a deep neural network, reducing error rates by 20%-40% relative and achieving up to 10x faster recognition times compared to a previous system, with new state-of-the-art results on IAM-OnDB.
We describe an online handwriting system that is able to support 102 languages using a deep neural network architecture. This new system has completely replaced our previous Segment-and-Decode-based system and reduced the error rate by 20%-40% relative for most languages. Further, we report new state-of-the-art results on IAM-OnDB for both the open and closed dataset setting. The system combines methods from sequence recognition with a new input encoding using Bézier curves. This leads to up to 10x faster recognition times compared to our previous system. Through a series of experiments we determine the optimal configuration of our models and report the results of our setup on a number of additional public datasets.