De-screening halftones using sigma filters
View Patent ↗A digital imaging system and method uses a two-stage sigma filter to de-screen color images. This filter does not assume any a priori knowledge about the screening process using to produce the halftone image. The two-stage sigma filter may therefore be used to convert color halftone images into continuous-tone images irrespective of the screening process used. The two-stage sigma filter may be constructed, or emulated in software, using an O (N) algorithm which performs smoothing and preserves edge information simultaneously in the Red/Green/Blue color space. This system and method outperforms conventional approaches which, for example, use a Gaussian blur, because it satisfies the dual criteria of completely eliminating halftone screens while preserving edge information. When combined with halftone segmentation techniques, a complete document processing algorithm for gray-scale and color documents is created.
1. A method for converting halftone images into continuous-tone images, comprising:
obtaining a halftone image;
defining a two-stage filter, wherein a first stage is a smoothing filter and a second stage is a sigma filter connected to the smoothing filter;
defining parameters for the smoothing filter and the sigma filter, which includes an intensity difference delta;
inputting the halftone image into a smoothing filter to derive an intermediate image;
sweeping a window across said halftone image and the corresponding intermediate image, and within a window, selecting those pixels that have an intermediate gray value within said intensity difference delta of a center window pixel;
applying a sigma filter to pixels from said halftone image that correspond to pixels selected in said sweeping step; and
outputting from said sigma filter a continuous-tone image which is piecewise-smooth and has preserved edges.
2. The method of claim 1 , wherein said smoothing filter is a low-pass filter.
3. The method of claim 2 , wherein said low-pass filter includes a plurality of Gaussian low-pass filters.
4. The method of claim 1 , further comprising:
printing said continuous-tone image.
5. The method of claim 1 , wherein said halftone image is a color image.
6. The method of claim 1 , wherein said halftone image is a gray-scale image.
7. The method of claim 1 , wherein said smoothing filter is an isotropic low-pass filter.
8. The method of claim 1 , wherein said intensity difference delta is determined by computing a set of edge pixels from said intermediate image and selecting those pixels that fall within a given spatial distance from said set of edge pixels to form a second set, and computing a standard deviation of the gray values of the pixels in the second set, and setting delta to be a multiple of said standard deviation.
9. The method of claim 8 wherein the multiple is 2.