Patent EP0469794A2 successfully refreshed from Google Patents.
EP0469794A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Apparatus and method for image area identification
Assignee: NCR International Inc
•
Filing: 1991-07-25
•
Granted: —
•
Expires: 2011-07-25
Abstract
Abstract A flexible technique that is robust in the presence of noise and distortion is disclosed for locating and utilizing fiducial markings to locate predetermined areas within an image. Initially, a set of candidate markings is determined, one marking from within each of a plurality of predesignated areas of a scanned image. Thereafter, an estimate of a set of image distortion factors relative to an ideally registered image of the same type as the scanned image is derived. Predicted locations for the fiducial markings are derived using this estimated set of image distortion factors. If the difference in location between the actual location of any candidate marking and its predicted location is greater than a predetermined threshold, at least one such candidate is removed from the set of candidate markings. The estimation and removal processes are repeated, utilizing the new current set of candidate fiducial markings until all remaining candidate markings are within a predetermined distance of their predicted locations. Predetermined areas within the scanned image can thereafter be accurately located by combining the known location of the area within an ideal image with the final estimated set of image distortion factors. The predicted location may be further improved by using a weighted average of the ideal versus the actual fiducial marking differences, to account for local non-linear variations [FIG. 2].
Inventors
- 👤 Timothy J. Thompson
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-09 13:04
CPC Classifications
H; H04; H04N; H04N1/00; H04N1/40; H04N1/387; G; G06; G06V; G06V10/00; G06V10/20; G06V10/24; G06V10/245; H04N1/38
Claims Analysis
Total Claims: 11
Claim 1
Independent Claim
249 words
A method of searching a scanned image of a predetermined type and determining locations therein CHARACTERIZED BY the steps of: a. obtaining a version of said scanned image; b. obtaining a representation of an ideally registered image of said predetermined type; c. searching each area of a set of predetermined areas of said scanned image for at least one candidate fiducial marking, said candidate fiducial markings from each of said areas forming a set of candidate fiducial markings; d. estimating a set of overall image distortion factors for said scanned image, based on a comparison of said candidate fiducial markings with fiducial markings of said representation of said ideally registered image of said predetermined type; e. determining, which, if any, of said candidate fiducial markings are located more than a predetermined distance away from their expected location; f. if any of said candidate fiducial markings are located more than said predetermined distance away from their expected location, removing from said set of candidate fiducial markings at least one candidate marking that is located more than said predetermined distance away from its expected location; g. if any of said candidate fiducial markings were removed from said set of candidate fiducial markings in the immediately preceding step (f) go back to step (d) and repeat steps (d) through (g); and h. supplying as an output a location for each fiducial marking of said set of candidate fiducial markings and values of said set of image distortion factors for said scanned image.
Claim 2
Dependent Claim
36 words
The method as defined in claim 1 further CHARACTERIZED BY the step of computing a predicted location of a selected point in said scanned image for which a position is known in said ideally registered image.
Claim 3
Dependent Claim
103 words
The method as defined in claim 1 further CHARACTERIZED BY prior to said step of supplying, the steps of: w. determining if any markings not currently in said set of candidate fiducial markings should be added to said set of candidate fiducial markings; x. if any fiducial markings are to be added selecting at least one candidate fiducial marking to be added to said set of candidate fiducial markings; y. adding said selected candidate fiducial markings to said set of candidate fiducial markings; and z. if any fiducial markings have been added go back to step (d) and repeat steps (d) through (z).
Claim 4
Dependent Claim
58 words
The method as defined in claim 1 CHARACTERIZED IN THAT said step of determining further includes the step of compensating each location of each of said candidate markings based on said set of overall image distortion factors and comparing each of said compensated locations to a corresponding location of a known fiducial marking in said ideally registered image.
Claim 5
Dependent Claim
56 words
The method as defined in claim 1 CHARACTERIZED IN THAT said step of determining further includes the step of compensating each location of each known fiducial marking in said ideally registered image based on said set of overall image distortion factors and comparing each of said compensated locations to a corresponding location of said candidate markings.
Claim 6
Dependent Claim
27 words
The method as defined in claim 1 CHARACTERIZED IN THAT in said step of removing a single candidate that is furthest outside said predetermined tolerance is removed.
Claim 7
Dependent Claim
34 words
The method as defined in claim 1 CHARACTERIZED IN THAT in said step of searching, each area is searched for an object within said area having a predetermined probability of being a fiducial marking.
Claim 8
Dependent Claim
28 words
The method as defined in claim 2 CHARACTERIZED IN THAT said step of computing takes into account non-linear distortions in said scanned image relative to said ideal image.
Claim 9
Dependent Claim
17 words
The method as defined in claim 7 CHARACTERIZED IN THAT said predetermined probability is a highest probability.
Claim 10
Dependent Claim
52 words
The method as defined in claim 7 CHARACTERIZED IN THAT said predetermined probability is a probability determined by comparison of a set of characteristics of each object found in said search object relative to said set of characteristics of a fudicial marking located in said predetermined area in said ideally registered image.
Claim 11
Dependent Claim
221 words
Apparatus for searching a scanned image of a predetermined type and determining locations therein CHARACTERIZED BY the steps of: means for obtaining a version of said scanned image [105, 108]; means for obtaining a representation of an ideally registered image of said predetermined type [104]; means for searching each area of a set of predetermined areas of said scanned image for a candidate fiducial marking, said candidate fiducial markings from each of said areas forming a set of candidate fiducial markings [102]; means for estimating a set of overall image distortion factors for said scanned image, based on a comparison of said candidate fiducial markings with fiducial markings of said representation of said ideally registered image of said predetermined type [102, 103]; means for determining, which, if any, of said candidate fiducial markings are located more than a predetermined distance away from their expected location [102, 103]; means responsive to said means for estimating and said means for determining for removing from said set of candidate fiducial markings at least one candidate that is located more than said predetermined distance away from its expected location [102, 103]; means for supplying as an output a location for each fiducial marking of said set of candidate fiducial markings and values of said set of image distortion factors for said scanned image [102, 103].
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.