Characters as Graphs: Recognizing Online Handwritten Chinese Characters via Spatial Graph Convolutional Network
This addresses the challenge of recognizing online handwritten Chinese characters, which is important for users of Chinese language input systems, but it is incremental as it builds on existing graph-based and convolutional approaches.
The paper tackles online handwritten Chinese character recognition by representing characters as geometric graphs that retain spatial structures and temporal orders, and proposes a spatial graph convolutional network (SGCN) to classify them, achieving comparable performance to state-of-the-art methods on datasets like IAHCC-UCAS2016, ICDAR-2013, and UNIPEN.
Chinese is one of the most widely used languages in the world, yet online handwritten Chinese character recognition (OLHCCR) remains challenging. To recognize Chinese characters, one popular choice is to adopt the 2D convolutional neural network (2D-CNN) on the extracted feature images, and another one is to employ the recurrent neural network (RNN) or 1D-CNN on the time-series features. Instead of viewing characters as either static images or temporal trajectories, here we propose to represent characters as geometric graphs, retaining both spatial structures and temporal orders. Accordingly, we propose a novel spatial graph convolution network (SGCN) to effectively classify those character graphs for the first time. Specifically, our SGCN incorporates the local neighbourhood information via spatial graph convolutions and further learns the global shape properties with a hierarchical residual structure. Experiments on IAHCC-UCAS2016, ICDAR-2013, and UNIPEN datasets demonstrate that the SGCN can achieve comparable recognition performance with the state-of-the-art methods for character recognition.