Handwritten digits segmentation based on structural approach

We deal with a new segmentation approach applied to unconstrained handwritten digits. The novelty of the proposed algorithm is based on the combination of two types of structural features in order to provide the best segmentation path between connected entities. This method was developed to be applied in a segmentation-based recognition system. We first present the features used to generate our basic segmentation points, and we define our segmentation paths depending on the encountered configurations with only few heuristic rules. Then, we present a strategy based on graphs in order to manage the segmentation. Finally, we evaluate the output of our segmenter using a integrated classifier with three different combination methods