A model of stroke extraction from Chinese character images

摘要

Given the large number and complexity of Chinese characters,pattern matching based on structural decomposition and analysis isbelieved to be necessary and essential to off-line characterrecognition. The paper proposes a model of stroke extraction for Chinesecharacters. One problem for stroke extraction is how to extract primarystrokes. Another major problem is to solve the segmentation ambiguitiesat intersection points. We use the degree information and the strokecontinuation property to tackle these two problems. The proposed modelcan be used to extract strokes from both printed and handwrittencharacter images