Characters on license plate, which is obscured by water or mist, is hard to be recognized through classical license plate recognition technology. In order to get higher recognition rate of blurred character in practical license plate recognition system, an approach to separate characters from a blurred image of vehicle license plate is proposed in this paper. At first, the upper, lower, left and right boundaries of blurred character are assumed to be foreground sample; the broken boundary of character is considered as background sample. At the position of background white scribbles are drawn; in contrast, midpoints of the lines along foreground are painted with black scribbles. Then a scribble image is generated automatically. Furthermore, closed form solution to natural image matting is adopted to obtain the background that is uncovered license plate according to the scribble image. The experiments show that the new algorithm is applicable and helpful to get higher recognition rate of blurred license plate.