A new approach is proposed to segment off-line handwritten Chinese character. Many papers have been published on the off-line recognition of Chinese characters, and almost all of them focus on the recognition of isolated Chinese character. The segmentation is an important preprocess of the off-line Chinese character recognition because correct recognition of characters relies on correct segmentation of characters. In handwritten Chinese characters, characters may be written to touch each other or to overlap with each other, therefore, the segmentation problem is not an easy one. In this paper, we present a novel method which use strokes to build stroke bounding boxes first. Then the knowledge-based merging operations are used to merge those stroke bounding boxes and finally, a dynamic programming method is applied to find the best segmentation boundaries. A series of experiments show that our method is very effective for the off-line handwritten Chinese character segmentation.