The digitalization processes of bills produce frequently digital images with a mass of redundant background caused by rotation angles and misoperations in the scanning process. The redundant background occupies much storage space. First, this paper proposes a method that combines Hough transform and mathematical morphology to detect the skew. Secondly, the redundant background of bill images is removed after recognizing the coordinates of the top-left and bottom-right points of the target area. Last, experimental results are given on different types of bill images. The method provided in this paper is automated and simple to implement.