Handwritten digit recognition using neural networks and dynamic zoning with stroke-based descriptors

This article presents an Off-line handwritten digit recognition approach based on neural networks. We define a numeric character as a composition of vertical and horizontal strokes. After the preprocessing, we use dynamic zoning to retrieve the positions where vertical strokes – the main strokes — are joined to horizontal strokes. These features are recorded into a representative string and verified using a custom matching pattern. Finally, a multilayer perceptron neural network is fed with the previous data to raise the learning process. The results gathered from the experiments performed on the well-known MNIST handwritten database are compared against other proposals providing promising results.