Training a Multilayered Perceptron to Compute the Euler Number of a 2-D Binary Image

In this short communication, we explain how a Multilayered Perceptron (MLP) can be used to compute the Euler number or Genus of a 2-D binary image. We take as basis the results provided by a mathematical formulation that is known providing exact results in the computation of this important topological image feature to derive two MLP-based architectures, one useful for the 4-connected case and one useful for 8-connected case. We present results with a set of realistic images and compare our proposals in terms of processing with other approaches reported in literature.