中文摘要：

提出了一种融合分水岭变换和图论的图像分割方法。利用图像的局部灰度信息进行分水岭变换后，将图像分割成多个小区域，再结合各小区域的灰度和空间信息从全局角度用Normalized Cut方法在区域之间进行分割，产生最终的分割结果。实验结果表明，该方法可以消除分水岭变换后所产生的过分割现象，是一种有效的图像自动分割方法。

英文摘要：

An image segmentation approach based on watershed translation and graph theory is proposed. The image is segmented into a large number of small partitions using watershed translation on the basis of local gray value. By integrating gray feature and spatial location of each partition, normalized cutting approach is used to segment the image among partitions from global view, by which the final segmented image can be generated. Experiment results show that the over-segmentation can be eliminated effectively by the proposed approach.