In this paper, we present a new stroke extraction algorithm that integrates all levels of contour information including boundary points, dominant points, corner points, segments, cross section sequence graph, character structure to extract strokes of Chinese characters. In the algorithm, first, the boundary points are extracted, then the dominant and corner points are detected. Third, the character structure including singular and regular regions are extracted by the contour information and a modified cross section sequence graph (CSSG). Finally, a Bezier curve taking dominant points and corner points as inputs is used to check the continuity of strokes. Experimental results show that the proposed algorithm can correctly extract the strokes up to 95% from a printed and handwritten test samples based on the human perception. This research provides a solid basis for the structural matching of Chinese characters.