Road vectorization aims to delineate road centerlines from aerial and satellite images. In this paper, binary road image space clustering techniques, which are used to determine key points on the road, are expanded to a more accurate and reliable algorithm, the Increasing Ellipse Clustering technique. Accurate noise cluster recognition and omission are two strengths of the proposed algorithm. In order to establish the true connections between predetermined key points on the road, a very fast, novel, and reliable fuzzy ellipse-shaped clustering methodology is introduced. Different accuracy assessment parameters are established and evaluated based on results obtained for simulated and real road binary images. The sub-pixel geometric accuracy of the extracted road network, with a completeness of more than 80 percent, demonstrates the promising results of the vectorization algorithm that is presented in this paper.