# Fast Multi-language LSTM-based Online Handwriting Recognition

## TL;DR

This paper presents a deep neural network-based online handwriting recognition system supporting 102 languages, achieving significant error reduction and faster recognition times, setting new state-of-the-art results on IAM-OnDB.

## Contribution

The paper introduces a novel multi-language LSTM-based system with Bézier curve encoding, replacing previous methods and significantly improving accuracy and speed.

## Key findings

- Reduced error rate by 20%-40% across most languages
- Achieved up to 10x faster recognition times
- Set new state-of-the-art results on IAM-OnDB

## Abstract

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 B\'ezier 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.