This paper introduces the theory of algorithm results of different image processing techniques in lane marking line recognition, including binarize, edge detection and lane extraction. Analyze and compare the accuracy of the each stages of processing algorithms, reliability and real-time performance. And then compare the various combinations of algorithms to detect lane marking lines in several conditions. Finally, an ideal detection algorithm is proposed, which using progressive threshold method to binarize, the contour extraction method, lane edge tracing and curve fitting method.