Image analysis – Image segmentation – Distinguishing text from other regions
Reexamination Certificate
1998-12-21
2002-04-16
Au, Amelia M. (Department: 2623)
Image analysis
Image segmentation
Distinguishing text from other regions
C382S232000, C358S464000
Reexamination Certificate
active
06373981
ABSTRACT:
FIELD OF THE INVENTION
This invention relates generally to image processing and, more particularly, to techniques for compressing the digital representation of a document.
BACKGROUND OF THE INVENTION
Documents scanned at high resolutions require very large amounts of storage space. Instead of being stored as is, the data is typically subjected to some form of data compression in order to reduce its volume, and thereby avoid the high costs associated with storing it. “Lossless” compression methods such as Lempel-Ziv Welch (LZW) do not perform particularly well on scanned pixel maps. While “lossy” methods such as JPEG work fairly well on continuous-tone pixel maps, they do not work particularly well on the parts of the page that contain text. To optimize image data compression, techniques, which can recognize the type of data being compressed, are needed.
One approach to satisfy the compression needs of differing types of data has been to use a document image representation which employs a Mixed Raster Content (MRC) format to describe the image. The image—a composite image having text intermingled with color or gray scale information—is segmented into two or more planes, generally referred to as the upper and lower plane, and a selector plane is generated to indicate, for each pixel, which of the image planes contains the actual image data that should be used to reconstruct the final output image. Segmenting the planes in this manner can improve the compression of the image because the data can be arranged such that the planes are smoother and more compressible than the original image. Segmentation also allows different compression methods to be applied to the different planes, thereby allowing a compression technique that is most appropriate for the data residing thereon can be applied to each plane.
An approach such as this is discussed in U.S. Pat. No. 5,778,092 to MacLeod et al. issued Jul. 7, 1998, the contents of which are hereby incorporated by reference. MacLeod et al. discloses a technique for compressing a color or gray scale pixel map that represents a document. The pixel map is decomposed into a three-plane representation—a reduced-resolution foreground plane, a reduced-resolution background plane, and a high-resolution binary selector plane. The foreground plane contains the color or gray scale information of foreground items such as text. The background plane contains the color or gray scale information for the “background” of the page and the continuous tone pictures that are contained on the page. The selector plane stores information for selecting from either the foreground plane or background plane during decompression.
The present invention is directed to segmenting color image data using the MRC format. Edges are generally defined as sharp discontinuities between regions of two constant colors or large sections of light intensity values. Here, edges of the image are separated into two portions. The foreground layer generally contains information about the darker sides, while the background layer contains the information about the smooth regions of the image and the brighter sides of the edges. Segmentation is performed by sectioning the image into stripes and (where the height of each stripe is equal to the size of the block) and processing each stripe block by block from the top of the image to the bottom.
The following disclosures may be relevant to aspects of the present invention:
U.S. Pat. No. 5,251,271 to Fling issued Oct. 5, 1993 discloses a method for registering digitized multi-plane color images. The method designates one plane as the reference plane and registers each of the other warped planes with the reference plane. Each plane comprises pixels representing luminosity values having scalar x and y coordinates representing positions in the horizontal and vertical directions, respectively, of the plane. The planes are divided into regions. Correlation values are calculated for regions within the divisional region of the reference plane with a plurality of regions offset from the corresponding warped divisional region. A warp error value is calculated for each pixel of each divisional region as a function of the scalar offset. The warp error values are interpolated and added to the current position of each pixel of the warped plane.
Separate processing of various types of data contained in a document is disclosed in U.S. Pat. No. 5,060,980 to Johnson et al. issued Oct. 29, 1991 which describes a “form” that includes user modifiable fields and an encoded description of the location, size, type, etc. of the fields to allow for direct programming of a form interpreter. Other information including the processing of the form, encoded data, etc. may be included in the encoded information. A system for creating forms carrying an encoded description of selected attributes of the fields includes means for selecting or creating fields and locating the fields on a form while generating, substantially simultaneously, the encoded description of the selected attributes. A form composer then allows merging of the form and its encoded description for printing or electronic transmission. A system for reading such forms includes a scanner, decoding device, and processor. By reading such forms, data may be entered into or recalled from a data processing system, or a form interpreter may be programmed, locally or remotely, for subsequent handling of forms.
U.S. Pat. No. 5,784,175 to Lee, issued Jul. 21, 1998 discloses a video compression encoder process for compressing digitized video signals representing display motion in video sequences of multiple image frames. The encoder process utilizes object-based video compression to improve the accuracy and versatility of encoding interframe motion and intraframe image features. Video information is compressed relative to objects of arbitrary configurations, rather than fixed, regular arrays of pixels as in conventional video compression methods. This reduces the error components and thereby improves the compression efficiency and accuracy. As another benefit, object-based video compression of this invention provides interactive video editing capabilities for processing compressed video information.
U.S. Pat. No. 5,303,313 to Mark et al. issued Apr. 12, 1994 describes image compression based on symbol matching. An image is “pre-compressed” prior to symbol matching using run-length encoding. Symbols are then extracted from the run-length representation. A voting scheme is used in conjunction with a plurality of similarity tests to improve symbol-matching accuracy. A template composition scheme wherein the template may be modified based on symbol matches is also disclosed.
U.S. Pat. No. 5,432,870 to Schwartz issued Jul. 11, 1995 discloses a method and apparatus for compressing and decompressing images of documents. More specifically, a method and apparatus for compressing images having a binary extractor, a binary compressor and a JPEG compressor is disclosed. The binary extractor produces a binary image representing an estimate of the binary information in the original image. The binary compressor compresses the binary image. The binary image is also subtracted from the original image to produce a difference image representing the continuous-tone information in the original image. The difference image is then compressed using the JPEG compressor. In this manner, the present invention compresses a document image without having to perform segmentation on the image.
Pending U.S. Patent Application by Fan et al. identified as Ser. No. 09/203,870 entitled Method and Apparatus for Segmenting Data to Create Mixed Raster content Planes and assigned to the assignee of the present invention discloses a technique for compressing a color or gray scale pixel map representing a document using an MRC format includes a method of segmenting an original pixel map into two planes, and then compressing the data or each plane in an efficient manner. The image is segmented by separating the image into two portions at the edges. One plane contains
de Queiroz Ricardo L.
Fan Zhigang
Tran Trac D.
Au Amelia M.
Dudley Mark Z.
Nixon & Peabody LLP
Wu Jingge
Xerox Corporation
LandOfFree
Method and apparatus for segmenting data to create mixed... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and apparatus for segmenting data to create mixed..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for segmenting data to create mixed... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2867114