Algorithm and software for monozygotic twins recognizing

The problem of face recognition of monozygotic twins is very important and difficult to solve. Existing face recognition software products for this purpose in most cases fail to cope with this task. In this paper, we propose an algorithm for face recognition of monozygotic twins based on natural and artificially created facial asymmetry using Fourier transform. The program implementing the proposed algorithm creates two images from the left and right halves of the original photo of the face of the first twin and another image as the average of the two created. Based on the obtained four images, a vector of 28 classifier values is created for comparison. Similarly, a second vector is created based on the images of the second twin. When comparing the values of the two vectors, the invisible effect of the asymmetry of the twins' faces is triggered, allowing to distinguish them.