A Model for Recovering Writing Order from Offline Handwritten Chinese Character
一种脱机手写汉字书写顺序恢复模型

The objective of recovering writing order is to extract dynamic handwriting information from static text images, which can be seen as to convert a 2-dimensional image into sequences of 1-dimensional vectors of pentip positions along the time axis. This paper proposes a model for recovering writing order from offline handwritten Chinese character. In this model, a 4-layer hierarchy is presented to model each Chinese character, where character, component, subcomponent and stroke are located at each layer, respectively. Characters are decomposed into components and each component is decomposed to subcomponents in turn by four decomposing operators. The totally-ordered relations between subcomponents are retrieved by defining the corresponding rules between decomposed relations and a poset of subcomponents. Subcomponents are the basic recovering primitives in this model, whose writing orders are recovered by classifying strokes and pairs of crossing strokes. Experimental results show that the proposed method is effective and accurate.