US6639692B1
Expired / Lapsed
US
⏱️ 0.0 years remaining
Pixel level segmentation tag cleanup
Assignee: Xerox Corp
•
Filing: 1999-09-09
•
Granted: 2003-10-28
•
Expires: 2019-09-09
Abstract
Abstract A system and method of processing segmentation tags is disclosed. In accordance with the present invention, 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.
Inventors
- 👤 Xing Li
- 👤 Ramesh Nagarajan
- 👤 Francis K. Tse
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 18:00
CPC Classifications
H; H04; H04N; H04N1/00; H04N1/40; H04N1/40062; G; G06; G06T; G06T7/00; G06T7/10; G06T7/11; G06T7/187
Claims Analysis
Total Claims: 17
Claim 1
Independent Claim
39 words
A method of processing segmentation tags, comprising: 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.
Claim 2
Independent Claim
39 words
A method of processing segmentation tags, comprising: 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.
Claim 3
Dependent Claim
58 words
The method of claim 1 , wherein said cleaning step comprises: determining a frequency of occurrence within the neighborhood window for a selected image type; and generating a cleaned pixel level tag for said current pixel level tag based upon the frequency of the selected image type and the image type represented by the current pixel level tag.
Claim 4
Dependent Claim
74 words
The method of claim 1 , wherein the cleaning step comprises: comparing the current pixel level tag to the segmentation tags within the neighborhood window; and generating a cleaned pixel tag equal to the current pixel level tag if the current pixel level tag is the same as one of the segmentation tags within the neighborhood window; otherwise generating a cleaned pixel tag as a function of the segmentation tags within the neighborhood window.
Claim 5
Dependent Claim
62 words
The method of claim 3 , wherein said step of generating a cleaned pixel tag as a function of the segmentation tags within the neighborhood window includes: setting the cleaned pixel tag to represent a selected image type based on the image type represented by the current pixel level tag and the frequency of occurrence of image types within the neighborhood window.
Claim 6
Dependent Claim
64 words
The method of claim 4 , wherein the current pixel level tag resides within a current block and the neighborhood window comprises a current block tag and an adjacent block tag, the current block tag being a representative tag for the current block and the adjacent block tag being a representative tag for a block of pixel level tags adjacent to said current block.
Claim 7
Independent Claim
63 words
A method for processing segmentation tags, comprising: receiving blocks of segmentation tags, each of the received blocks having an associated block level tag representative of the segmentation tags within the block; positioning a neighborhood window about a current block and a neighboring block; and cleaning a target segmentation tag within the current block based upon the block level tags within the neighborhood window.
Claim 8
Independent Claim
63 words
A method for processing segmentation tags, comprising: receiving blocks of segmentation tags, each of the received blocks having an associated block level tag representative of the segmentation tags within the block; positioning a neighborhood window about a current block and a neighboring block; and cleaning a target segmentation tag within the current block based upon the block level tags within the neighborhood window.
Claim 9
Dependent Claim
28 words
The method of claim 6 , wherein the cleaning step generates a cleaned segmentation tag for the target segmentation tag based upon a set of tag cleaning rules.
Claim 10
Dependent Claim
46 words
The method of claim 7 , wherein the set of tag cleaning rules includes: setting the cleaned segmentation tag equal to the target segmentation tag if the target segmentation tag is the same as a threshold number of the block level tags within the neighborhood window.
Claim 11
Dependent Claim
48 words
The method of claim 8 wherein the set of tag cleaning rules further comprises: setting the cleaned segmentation tag to equal a segmentation tag generated as function of the block level tags if a frequency of the target segmentation tag within the neighborhood is less than a threshold.
Claim 12
Dependent Claim
61 words
The method of claim 7 , wherein the set of tag cleaning rules comprises: setting the cleaned segmentation tag to indicate an image type selected from one of low frequency halftone and high frequency halftone if the target segmentation tag represents an image type selected from a fuzzy low frequency halftone, a fuzzy high frequency halftone and a intermediate frequency halftone.
Claim 13
Independent Claim
149 words
A system for processing video image data, comprising: a print engine connected to receive print ready data, the marking engine generating an image on a receiving medium in response to the print ready data; and a image processor connected to receive video image data, the image processor generating the print ready data from the video image data, the image processor comprising a segmentation processor coupled to receive the video image data, the segmentation processor generating segmentation tags that identify image pixels as a particular image class; a neighborhood window generator connected to receive said segmentation tags, the neighborhood window generator identifying a neighborhood window comprising blocks of segmentation tags, each block having an associated block tag; and a tag analysis module connected to receive the blocks of segmentation tags and the associated block tags, the tag analysis module replacing selected segmentation tags within the blocks with a cleaned tag.
Claim 14
Independent Claim
149 words
A system for processing video image data, comprising: a print engine connected to receive print ready data, the marking engine generating an image on a receiving medium in response to the print ready data; and a image processor connected to receive video image data, the image processor generating the print ready data from the video image data, the image processor comprising a segmentation processor coupled to receive the video image data, the segmentation processor generating segmentation tags that identify image pixels as a particular image class; a neighborhood window generator connected to receive said segmentation tags, the neighborhood window generator identifying a neighborhood window comprising blocks of segmentation tags, each block having an associated block tag; and a tag analysis module connected to receive the blocks of segmentation tags and the associated block tags, the tag analysis module replacing selected segmentation tags within the blocks with a cleaned tag.
Claim 15
Dependent Claim
58 words
The system of claim 11 , wherein the tag analysis module replaces a segmentation tag that is not the same as one of the associated block tags with a cleaned tag generated as a function of the image type represented by the segmentation tag and the frequency of occurrence of the associated block tags within the neighborhood window.
Claim 16
Dependent Claim
73 words
The system of claim 11 , wherein the tag analysis module replaces selected segmentation tags with a cleaned segmentation tag based upon a set of tag cleaning rules, the set of tag cleaning rules including: replacing a target segmentation tag with a cleaned segmentation tag equal to the target segmentation tag if the frequency of occurrence within the neighborhood window of the target segmentation tag is greater than or equal to a threshold.
Claim 17
Dependent Claim
54 words
The system of claim 13 wherein the set of tag cleaning rules further comprises: replacing a target segmentation tag with a cleaned segmentation tag equal to a segmentation tag generated as function of the block level tags if a frequency of the target segmentation tag within the neighborhood window is less than a threshold.
References Cited (Backward Citations)
US5327262A
Cited
US5574802A
Cited
US5699453A
Cited
US5765029A
Cited
US5778156A
Cited
US5850474A
Cited
US5767978A
Cited
US6137907A
Cited
US6480626B1
Cited
US6429950B1
Cited
US6493463B1
Cited
US6516091B1
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2006-10-27 | 2007-04-28 | 2007-10-28 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2010-10-27 | 2011-04-28 | 2011-10-28 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2014-10-27 | 2015-04-28 | 2015-10-28 | $7700.00 | Window Closed / Lapsed |