The Radon transform is able to transform two dimensional images with lines into a space of line parameters, where each line in the image will give a peak positioned at the corresponding line parameters. This has led to many line detection applications in image processing , computer vision and array processing. But when the lines are embedded in very strong noise background, using the Radon transform directly is not so effective. In this paper we present a SR-based Radon transform, in which a bistable stochastic resonance structure is introduced into the Radon transform. Using this kind of transform, we can easily extract weak lines from noise images. We also give applications in the bearing-time record and the LOFAR display.