在利用X射线对铸造缺陷识别的过程中，由于X光图像中铸件形成的背景复杂，传统的区域分割技术难以分割出缺陷集中的兴趣区域。利用缺陷边缘的分形特性从铸件边缘线图中确定缺陷的边缘线，以聚类方法将缺陷边缘线聚集的区域，即缺陷集中的兴趣区域分割出来。针对汽车铝合金轮毂铸件X光图像，用铸造缺陷区域的分割实验结果证明了该方法的有效性。

In casting defect recognition of an X Ray image，due to the complex image background，it is difficult to do segmentation with traditional segmentation technology for interested regions，in which the defects are intense. In this paper，fractal feature of the edges is introduced to distinguish which edge belongs to the casting defects in an edge image and the regions containing mass defect edges，e.g. interest regions are segmented by clustering. Directed to the aluminum alloy casting of vehicle wheel X Ray images，the fractal based region segmentation method of this paper is used for recognition experiments，and the results show that the approach is effective.