Xerox Patent US 7,139,442

Template matching applied to selector planes for multiple raster content (MRC) representation of documents

Publication number US7139442 B2
Publication type Grant
Application number 10/320,825
Publication date 21 Nov 2006
Filing date 16 Dec 2002
Priority date 16 Dec 2002
Also published as US20040114832
Inventors Donald J. Curry, Fritz F. Ebner
Original Assignee Xerox Corporation

Abstract

A method and a system for separating an image signal into a set of image planes are disclosed. The system comprises a way to perform resolution conversion from low resolution to high resolution binary images either for synthetic or scanned imagery by using template matching with pattern replacement. More specifically, the invention applies resolution conversion to the selector plane of mixed raster content images. For selector planes in which edges are encoded (vs. region classification), template matching/pattern replacement works well, and does not affect halftoned regions, as they are not encoded in this image.

1. Field of the Invention

The present invention relates generally to methods and systems for segmenting digitally scanned documents into two or more planes, and more particularly to methods and systems for applying resolution conversion to the selector plane of Multiple Raster Content (MRC) representation of documents.

While people have suggested that line art should be part of the bitmap plane, the patent observes that:

FIG. 1 shows the general MRC representation. The representation comprises up to four independent planes: Foreground, Background, Selector, and Rendering Hints. In the most general case, there could be multiple Foreground and Selector pairs at higher levels. However, in most applications, the representation is limited to three or four planes. The Background plane is typically used for storing continuous-tone information such as pictures and/or smoothly varying background colors. The Selector plane normally holds the image of text (binary) as well as other edge information (e.g., line art drawings). The Foreground plane usually holds the color of the corresponding text and/or line art. However, the MRC representation only specifies the planes and their associated compression methods. It does not otherwise restrict nor enforce the content of each of the planes. The content of each of the planes may be defined appropriately by an implementation of the MRC representation.

The patent itself cites many Xerox patents as prior art

US5365251 28 Aug 1992 15 Nov 1994 Xerox Corporation Image quality improvement by hierarchical pattern matching with variable size templates
US5778092 * 20 Dec 1996 7 Jul 1998 Xerox Corporation Method and apparatus for compressing color or gray scale documents
US6275620 * 7 Dec 2000 14 Aug 2001 Xerox Corporation Method and apparatus for pre-processing mixed raster content planes to improve the quality of a decompressed image and increase document compression ratios
US6324305 * 22 Dec 1998 27 Nov 2001 Xerox Corporation Method and apparatus for segmenting a composite image into mixed raster content planes
US6332044 21 Jan 1997 18 Dec 2001 Xerox Corporation System and method for enhancement of image contour fidelity
US6334001 * 7 Dec 2000 25 Dec 2001 Xerox Corporation Iterative smoothing technique for pre-processing mixed raster content planes to improve the quality of a decompressed image and increase document compression ratios
US6400844 * 2 Dec 1998 4 Jun 2002 Xerox Corporation Method and apparatus for segmenting data to create mixed raster content planes
US6437881 * 24 Sep 1998 20 Aug 2002 Fuji Xerox Co., Ltd. Image processing apparatus and image processing method
US6608928 * 3 Nov 1999 19 Aug 2003 Xerox Corporation Generic pre-processing of mixed raster content planes
US6832007 * 21 Nov 2000 14 Dec 2004 Xerox Corporation Method and system for compensating for scaling artifacts in mixed raster content (MRC) representations
US6859204 * 1 Jul 2002 22 Feb 2005 Xerox Corporation Dynamic threshold system for multiple raster content (MRC) representation of documents
US6987882 * 1 Jul 2002 17 Jan 2006 Xerox Corporation Separation system for Multiple Raster Content (MRC) representation of documents
US20040052427 * 1 Jul 2003 18 Mar 2004 Xerox Corporation Foreground erosion method and system for Multiple Raster Content (MRC) representation of documents
US20040096122 * 1 Jul 2003 20 May 2004 Xerox Corporation Segmentation method and system for multiple raster content (MRC) representation of documents
US20040227758 * 12 Feb 2004 18 Nov 2004 Xerox Corporation Segmentation method and system for scanned documents