Template-Instance Loss for Offline Handwritten Chinese Character Recognition
This addresses the problem of accurate recognition for offline handwritten Chinese characters, which is incremental as it builds on existing methods with new loss functions.
The paper tackled the challenges of offline handwritten Chinese character recognition, which include character diversity and cursive handwriting, by proposing template and instance loss functions; the result was state-of-the-art performance using a deep network architecture.
The long-standing challenges for offline handwritten Chinese character recognition (HCCR) are twofold: Chinese characters can be very diverse and complicated while similarly looking, and cursive handwriting (due to increased writing speed and infrequent pen lifting) makes strokes and even characters connected together in a flowing manner. In this paper, we propose the template and instance loss functions for the relevant machine learning tasks in offline handwritten Chinese character recognition. First, the character template is designed to deal with the intrinsic similarities among Chinese characters. Second, the instance loss can reduce category variance according to classification difficulty, giving a large penalty to the outlier instance of handwritten Chinese character. Trained with the new loss functions using our deep network architecture HCCR14Layer model consisting of simple layers, our extensive experiments show that it yields state-of-the-art performance and beyond for offline HCCR.