Abstract: Aiming at the complex background of coronary angiograms，weak contrast between the coronary arteries and the background，a new segmentation method based on fusion algorithm is proposed.Firstly，the original coronary angiogram is enhanced res-
pectively by using the top-hat method and the Gaussian filter method，then two enhanced images are obtained.Secondly，two extracted coronary arteries images are obtained by using the local entropy threshold method from two enhanced images.Two images of the extracted coronary arteries are fused at last.The experiments indicate that the proposed method outperforms the other methods mentioned in the paper about the small vessels extraction，connectivity and effectiveness.In addition，the method is indeed valuable for diagnosis.