Abstract: An algorithm for feature matching from network data at different map scaled based on similarity measure is presented.The whole strategy of matching is the first pre-matching of nodes and arcs,followed by accurate matching through similarity of node-arc topologies and discrete Fréchet distance.The matching process combines the matches in geometry,semantics,topology,nodes and arcs effectively.Finally,the different matching results are displayed to facilitate the human-computer interaction.The experimental results show that this method can match correspondent roads under complicated conditions effectively,and heighten the correctness and the speed of the feature matching.