Embedded Large-Scale Handwritten Chinese Character Recognition
This work addresses the problem of large-scale Chinese handwriting recognition for mobile users, but it is incremental as it builds on existing deep learning systems.
The paper tackled the challenge of recognizing up to 30,000 Chinese characters in real-time on mobile devices, achieving acceptable accuracy through careful data collection and training.
As handwriting input becomes more prevalent, the large symbol inventory required to support Chinese handwriting recognition poses unique challenges. This paper describes how the Apple deep learning recognition system can accurately handle up to 30,000 Chinese characters while running in real-time across a range of mobile devices. To achieve acceptable accuracy, we paid particular attention to data collection conditions, representativeness of writing styles, and training regimen. We found that, with proper care, even larger inventories are within reach. Our experiments show that accuracy only degrades slowly as the inventory increases, as long as we use training data of sufficient quality and in sufficient quantity.