The presented paper deals with a generic process for road network selection based on data enrichment and structure detection. The first step is to detect significant structures and patterns of the road network like roundabouts or highway interchanges. It allows to enrich the initial dataset with implicit geographic entities and structures. Using this enrichment, the following step is the selection of roads in rural areas thanks to graph theory techniques. After that, urban roads are selected by means of a block aggregation complex algorithm. Continuity between urban and rural areas is guaranteed by a method based on the notion of strokes. Finally, some previously detected structures are typified to maintain their properties in the selected network. This automated process has been fully implemented on ClarityTM and tested on a large dataset.