Facsimile and static presentation processing – Static presentation processing – Attribute control
Reexamination Certificate
1999-09-09
2003-10-28
Rogers, Scott (Department: 2624)
Facsimile and static presentation processing
Static presentation processing
Attribute control
C358S003260, C382S173000, C382S180000, C382S228000
Reexamination Certificate
active
06639692
ABSTRACT:
BACKGROUND OF THE INVENTION
The present invention relates to a system and method for processing segmentation tags, and more particularly, to a system and method to clean segmentation tags to reduce artifacts resulting from misclassification and abrupt changes in image classification.
In the reproduction or display of images from image data, and more particularly, to the rendering of image data representing original document that has been electronically scanned, one is faced with the limited resolution capabilities of the rendering system. An image processing system may be tailored so as to offset the limitations of the rendering system; however, this tailoring is difficult due to the divergent processing needs required by different image types.
Optimizing the system for one common image type typically comes at the expense of degraded rendering of other image types. For example, optimizing the system for low frequency halftones often comes at the expense of degraded rendering of high frequency halftones or text/line art, and visa versa. In view of this, optimizing the image processing system for one image type in an effort to offset the limitations in the resolution and the depth capability of the rendering apparatus may not be possible, requiring a compromised choice which may not produce acceptable results. Further complicating the reproduction of original documents is the reality that a document may be comprised of multiple image types (image classes), including continuous tones (contones), halftones of various frequencies, text/line art, error diffused images, etc.
To address this situation, digital reproduction devices often use automatic image segmentation techniques. Auto-segmentation is a well known operation that may use any of a number of classification functions (e.g., auto-correlation, frequency analysis, pattern or template matching, peak/valley detection, histograms, etc.) to analyze video image data and classify image pixels as one of several possible image classes. A typical auto-segmentation process generates a pixel classification signal, known as a segmentation tag, that identifies the pixel as a particular image class. Some common image types (image classes) include smooth contone, rough contone, text, text on tint, low frequency halftone, high frequency halftone, various intermediate frequency halftones which may be implemented as fuzzy frequencies, background and edge.
A one-pass digital reprographic system (scanning and printing done in a single pass of the image) gets just one chance to analyze and classify each pixel of an image based on a few scanlines of neighboring data. Due to the limited context for classification often one-pass segmentation results in erroneous switching between categories and since different categories require different type of rendering, any misclassification results in segmentation defects on the final rendered image. Conventional segmentation techniques base classification decisions on information gathered over context of several pixels from a few scanlines of neighboring data, effectively causing the image data to be lowpass filtered. The resulting classification decisions change from one class of imagery to another causing abrupt changes in the wrong places. This abrupt decision making, which produces a forced choice among several discrete alternate choices, is a primary reason for the formation of visible artifacts in the resulting output image.
Moreover, the classification of real images covers a continuum from well below to well above the transition point or thresholds used to delineate classifications. There are areas of an image which are, for example, just above a threshold. However, variations in the gathered image data due to “flaws” in the input video or ripple due to interactions between areas used for classification and periodic structures in the input video result in some areas falling below the threshold. This results in a different classification that introduces artifacts in the rendered image.
Several approaches to improve segmentation processes to reduce the segmentation artifacts resulting from misclassification and/or abrupt changes in image classification have been employed with varying degrees of success. The following references may be found relevant to the present disclosure:
U.S. Pat. No. 5,327,262 to Williams which discloses in conjunction with an image segmentation arrangement in which an image is processed with an image type detection arrangement, a morphological filtering operation which initially provides a noise removal filter operating an the image detection signal to remove noise within an area of the image detection signal and subsequently provides a hole filling filter which bridges small gaps in the image type detection results.
U.S. Pat. No. 5,765,029 to Schweid et al. discloses a method and system that electronically fuzzy classify a pixel belonging to a set of digital image data with respect to a membership of the pixel in a plurality of image classes. This process determines a fuzzy classification of the pixel and generates an effect tag for the pixel based on the fuzzy classification determination. Each class is defined by a set of heuristic rules such that the image classes are non mutually exclusive.
U.S. Pat. No. 5,850,474 to Fan et al. discloses a method and apparatus for segmenting image data into windows and for classifying the windows as typical image types which include making two passes through the image data. The method includes a step of making a first pass through the image data to identify windows and to record the beginning points and image types of each of the windows, and a step of making a second pass through the image data to label each of the pixels as a particular image type.
SUMMARY OF THE INVENTION
In accordance with the present invention, there is provided a method of processing segmentation tags to clean pixel level tags based upon neighboring block level tags. The method comprises identifying a current pixel level tag; identifying a neighborhood window comprising a plurality of segmentation tags; and cleaning the current pixel level tag based upon the segmentation tags within the neighborhood window. In accordance with further aspects of the present invention, cleaning the current pixel is based upon the frequency of selected image types within the neighborhood window.
In accordance with another aspect of the present invention, there is provided a method for processing segmentation tags that receives blocks of segmentation tags each of which has an associated block level tag that is representative of the segmentation tags within the block. The method positions a neighborhood window about a current block and a neighboring block and cleans a target segmentation tag within the current block based upon the block level tags within the neighborhood window using a set of tag cleaning rules.
In accordance with another aspect of the present invention, there is provided a system for processing video image data comprising a print engine connected to receive print ready data for generating an image on a receiving medium in response to the print ready data and a image processor connected to receive video image data and generate print ready data from the video image data. The image processor comprises a segmentation processor coupled to receive the video image data and generate segmentation tags that identify image pixels as a particular image class; a neighborhood window generator connected to receive the segmentation tags and identify a neighborhood window comprising blocks of segmentation tags each of which has an associated block tag; and a tag analysis module connected to receive the blocks of segmentation tags and the associated block tags and replace selected segmentation tags within the blocks with a cleaned tag.
REFERENCES:
patent: 5327262 (1994-07-01), Williams
patent: 5574802 (1996-11-01), Ozaki
patent: 5699453 (1997-12-01), Ozaki
patent: 5765029 (1998-06-01), Schweid et al.
patent: 5767978 (1998-06-01), Revankar et al.
patent: 5778156 (1998-07-01), Schweid et a
Li Xing
Nagarajan Ramesh
Tse Francis K.
Eipert William
Rogers Scott
Xerox Corporation
LandOfFree
Pixel level segmentation tag cleanup does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Pixel level segmentation tag cleanup, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Pixel level segmentation tag cleanup will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3122813