Learning an Artificial Neural Network to Discover Combinations of Bit-Quads to Compute the Euler Characteristic of a 2-D Binary Image

Abstract

The Image Analysis community has widely used so-called bit-quads to propose formulations for computing the Euler characteristic of a 2-D binary image. Reported works have manually proposed different combinations of bit-quads to provide one or more formulations to calculate this important topological feature. This paper empirically shows how an Artificial Neural Network can be trained to find an optimal combination of bit-quads to compute the Euler characteristic of any binary image. We present results with binary images of different complexities and sizes and compare them with state-of-the-art machine learning algorithms.