A dye-edge tracking algorithm was used to determine the corresponding points in the two images (anterior-posterior and lateral) of the digital subtraction biplane angiography. This correspondence was used to reconstruct three-dimensional images of cerebral arteries in a dog experiment and a clinical observation. The method was tested by comparing the measured image of oblique view to the computed reconstructed image. For the present study, we have developed three new algorithms. The first algorithm is to determine the corresponding dye-edge points using the fact that the density of contrast media at the moving edge shows the same changing pattern in the two projection views. This moving pattern of dye-edge density is computed using a matching method of cross correlation for the two sequential frames' dye density. The second algorithm is for simplified perspective transformation, and the third is to identify the corresponding points using a complementary method for locating the approximate points on the small vessels. The present method can be applied to compute the velocity of blood flow using the dye-edge displacement and the three-dimensional distance data.