Patent US5579445A successfully refreshed from Google Patents.
US5579445A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Image resolution conversion method that employs statistically generated multiple morphological filters
Assignee: Xerox Corp
•
Filing: 1993-12-17
•
Granted: 1996-11-26
•
Expires: 2013-12-17
Abstract
Abstract A method and apparatus for automating the design of morphological or template-based filters for print quality enhancement. A plurality of different phase, but same resolution, subsampled images are generated from training documents. Statistical data derived therefrom is then employed in an automated process to generate filters. The filters may be used for resolution enhancement and/or conversion of bitmap images. Furthermore, the statistical data is used to produce filters that are intended to not only optimize image structure, but image density as well.
Inventors
- 👤 Robert P. Loce
- 👤 Michael S. Cianciosi
- 👤 Jeffrey D. Kingsley
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-31 19:51
CPC Classifications
G; G06; G06T; G06T3/00; G06T3/40
Claims Analysis
Total Claims: 23
Claim 1
Independent Claim
221 words
A method for automatically creating a set of filters to be used for filtering an image bitmap, wherein application of the filters will result in an enhancement of the image bitmap, comprising the steps of: (a) generating a first resolution image, represented as a plurality of image signals, from a document and storing the first resolution image in a first bitmap memory; (b) generating a second resolution image, represented as a plurality of image signals, from the document and storing the second resolution image in a second bitmap memory; (c) subsampling the second bitmap memory to produce a subsampled first resolution image; (d) storing, in a subsample memory, the subsampled first resolution image; (e) defining a multiple signal input window that may be passed through the first bitmap memory; (f) defining a single signal output window that may be passed through the subsample memory, so that the position of the output window within the subsample memory is a function of the position of the input window within the first bitmap memory; (g) storing a plurality.of entries in a database memory, each entry including a representation of the bitmap pattern within the multiple signal input window and corresponding state found within the single signal output window; and (h) deriving, from the database-memory, a set of filters for enhancement of the image bitmap.
Claim 2
Independent Claim
221 words
A method for automatically creating a set of filters to be used for filtering an image bitmap, wherein application of the filters will result in an enhancement of the image bitmap, comprising the steps of: (a) generating a first resolution image, represented as a plurality of image signals, from a document and storing the first resolution image in a first bitmap memory; (b) generating a second resolution image, represented as a plurality of image signals, from the document and storing the second resolution image in a second bitmap memory; (c) subsampling the second bitmap memory to produce a subsampled first resolution image; (d) storing, in a subsample memory, the subsampled first resolution image; (e) defining a multiple signal input window that may be passed through the first bitmap memory; (f) defining a single signal output window that may be passed through the subsample memory, so that the position of the output window within the subsample memory is a function of the position of the input window within the first bitmap memory; (g) storing a plurality.of entries in a database memory, each entry including a representation of the bitmap pattern within the multiple signal input window and corresponding state found within the single signal output window; and (h) deriving, from the database-memory, a set of filters for enhancement of the image bitmap.
Claim 3
Dependent Claim
33 words
The method of claim 1, wherein the step of generating a second resolution image further comprises generating a second resolution image wherein the second resolution is an integer multiple of the first resolution.
Claim 4
Dependent Claim
33 words
The method of claim 1, further comprising the step of selecting the document from a plurality of training documents representative of image bitmaps upon which the set of filters is to be used.
Claim 5
Dependent Claim
69 words
The method of claim 1, wherein step (a), the step of generating a first resolution image, comprises: retrieving, from a storage media, a document comprised of descriptive signals intended to represent the document in a page description language; storing the descriptive signals representing the document in temporary memory; decomposing the descriptive signals to produce a first resolution image; and storing the first resolution image in a first bitmap memory.
Claim 6
Dependent Claim
38 words
The method of claim 4, wherein step (b), the step of generating a second resolution image, comprises: decomposing the descriptive signals to produce a second resolution image; and storing the second resolution image in a second bitmap memory.
Claim 7
Dependent Claim
24 words
The method of claim 3, wherein steps (a) through (g) are repeated for the plurality of training documents prior to execution of step (h).
Claim 8
Dependent Claim
98 words
The method of claim 1, wherein the step of storing a plurality of entries in a database memory further comprises the steps of: establishing an entry that may be indexed in accordance with the bitmap pattern of the multiple signal input window, unless such a pattern already exists within the database memory; and incrementing a count stored in memory fields associated with the single signal output window in accordance with the state of the signal in the single signal output window, so that a total number of occurrences of each signal state is recorded for the subsample memory.
Claim 9
Dependent Claim
31 words
The method of claim 1, wherein the step of deriving a set of filters further comprises the step of conducting a statistical analysis of the database memory to isolate structure elements.
Claim 10
Dependent Claim
93 words
The method of claim 8, wherein the step of conducting a statistical analysis of the database memory comprises: selecting an input pattern entry in the subsample database; determining an occurrence threshold for the selected entry as a function of the number of occurrences of the input pattern; applying the occurrence threshold so as to indicate for activation a subsampled position having an occurrence value greater than the occurrence threshold; and producing a template filter which assures activation of the subsampled position whenever the selected input pattern entry is detected in an input image.
Claim 11
Dependent Claim
113 words
The method of claim 1, wherein the step of deriving a set of filters further comprises: accumulating, from the database entries, a set of general pattern statistics; calculating the mean-absolute-error for each multiple signal input window pattern stored in the database when the pattern is used as a morphological erosion filter; selecting, based upon the mean-absolute-error for each pattern, a library of patterns to be considered for filter elements; sequentially evaluating combinations of patterns for goodness; and producing a morphological filter from those combinations of patterns having a mean-absolute-error less than a predetermined threshold, so as to assure activation of the subsampled position whenever a selected pattern is detected in an input image.
Claim 12
Dependent Claim
37 words
The method of claim 10, wherein the step of selecting a library of patterns includes applying a set of first-order statistics so as to select for the library of patterns, those patterns having the lowest individual mean-absolute-error.
Claim 13
Dependent Claim
32 words
The method of claim 10, wherein the step of sequentially evaluating combinations of patterns for goodness includes determining the goodness as a function of the morphological mean-absolute-error of each combination of patterns.
Claim 14
Dependent Claim
33 words
The method of claim 1, further comprising the step of applying the set of enhancement filters to an input image, represented by a plurality of image signals, to produce an enhanced output image.
Claim 15
Dependent Claim
94 words
The method of claim 13, wherein the step of applying the set of enhancement filters to an input image to produce an enhanced output image, comprises the steps of: selecting a target region within the input image; observing the states of a subset of image signals within the target region; generating a plurality of output image signals as a function of the states of the subset of image signals; and recombining the plurality of output image signals so as to produce a sequential stream of output image signals to form the enhanced output image.
Claim 16
Independent Claim
241 words
A method for automatically creating a set of filters to be used for filtering an image bitmap, wherein application of the filters will result in an enhancement of the image bitmap, comprising the steps of: (a) generating a first resolution image, represented as a plurality of image signals, from a document and storing the first resolution image in a first bitmap memory; (b) generating a second resolution image, represented as a plurality of image signals, from the document and storing the second resolution image in a second bitmap memory; (c) subsampling the second bitmap memory to produce a plurality of subsampled first resolution images; (d) storing, in a plurality of subsample memories, each of the plurality of subsampled first resolution images; (e) defining a multiple signal input window that may be passed through the first bitmap memory; (f) defining a plurality of single signal output windows that may be passed through the subsample memories, so that the position of the output windows within each of the plurality of subsample memories is a function of the position of the input window within the first bitmap memory; (g) storing a plurality of entries in a database memory, each entry including a representation of the bitmap pattern within the multiple signal input window and corresponding states found within each of the plurality of single signal output windows; and (h) deriving, from the database memory, a set of filters for enhancement of the image bitmap.
Claim 17
Independent Claim
241 words
A method for automatically creating a set of filters to be used for filtering an image bitmap, wherein application of the filters will result in an enhancement of the image bitmap, comprising the steps of: (a) generating a first resolution image, represented as a plurality of image signals, from a document and storing the first resolution image in a first bitmap memory; (b) generating a second resolution image, represented as a plurality of image signals, from the document and storing the second resolution image in a second bitmap memory; (c) subsampling the second bitmap memory to produce a plurality of subsampled first resolution images; (d) storing, in a plurality of subsample memories, each of the plurality of subsampled first resolution images; (e) defining a multiple signal input window that may be passed through the first bitmap memory; (f) defining a plurality of single signal output windows that may be passed through the subsample memories, so that the position of the output windows within each of the plurality of subsample memories is a function of the position of the input window within the first bitmap memory; (g) storing a plurality of entries in a database memory, each entry including a representation of the bitmap pattern within the multiple signal input window and corresponding states found within each of the plurality of single signal output windows; and (h) deriving, from the database memory, a set of filters for enhancement of the image bitmap.
Claim 18
Dependent Claim
33 words
The method of claim 15, wherein the step of generating a second resolution image further comprises generating a second resolution image wherein the second resolution is an integer multiple of the first resolution.
Claim 19
Dependent Claim
33 words
The method of claim 15, further comprising the step of selecting the document from a plurality of training documents representative of image bitmaps upon which the set of filters is to be used.
Claim 20
Dependent Claim
69 words
The method of claim 15, wherein step (a), the step of generating a first resolution image, comprises: retrieving, from a storage media, a document comprised of descriptive signals intended to represent the document in a page description language; storing the descriptive signals representing the document in temporary memory; decomposing the descriptive signals to produce a first resolution image; and storing the first resolution image in a first bitmap memory.
Claim 21
Dependent Claim
38 words
The method of claim 18, wherein step (b), the step of generating a second resolution image, comprises: decomposing the descriptive signals to produce a second resolution image; and storing the second resolution image in a second bitmap memory.
Claim 22
Dependent Claim
24 words
The method of claim 19, wherein steps (a) through (g) are repeated for the plurality of training documents prior to execution of step (h).
Claim 23
Dependent Claim
100 words
The method of claim 15, wherein the step of storing a plurality of entries in a database memory further comprises the steps of: establishing an entry that may be indexed in accordance with the bitmap pattern of the multiple signal input window, unless such a pattern already exists within the database memory; and incrementing a count stored in memory fields associated with each of the single signal output windows in accordance with the state of the signals in the single signal output windows, so that a total number of occurrences of each signal state is recorded for each subsample memory.
References Cited (Backward Citations)
US4437122A
Cited
US4437122B1
Cited
US4544922A
Cited
US4460909A
Cited
EP0177640A2
Cited
US4544264A
Cited
US4625222A
Cited
US4814890A
Cited
US4841375A
Cited
US5150311A
Cited
US5005139A
Cited
US4847641A
Cited
US5142374A
Cited
US4933689A
Cited
US5161035A
Cited
US5029108A
Cited
US5134495A
Cited
US5193008A
Cited
US5138339A
Cited
US5301037A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1999-11-26 | 2000-05-27 | 2000-11-26 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2003-11-26 | 2004-05-27 | 2004-11-26 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2007-11-26 | 2008-05-27 | 2008-11-26 | $7700.00 | Window Closed / Lapsed |