Intelligent driving technology is attracting more and more attention, which can improve the efficiency and safety of transportation greatly. One of its important research directions is detecting and recognizing the lane lines on road. This paper uses the machine vision methods to recognize the curvy lane lines on freeway. The circular curve matching algorithm is proposed. The transformation between the road plane and the image plane is presented. And the match algorithm is executed in the image plane to reduce the time complexity and improve recognition accuracy. Experimental results testify the efficiency of the proposed algorithm.