US5611033A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Apparatus and method for automerging images by matching features and aligning images
Assignee: Lite On Technology Corp
•
Filing: 1993-07-15
•
Granted: 1997-03-11
•
Expires: 2013-07-15
Abstract
Abstract An apparatus and method for automatically merging multiple image portions to produce a single image. Image portions are produced, such as by a hand-held scanner, with overlapping areas. The overlapping area of a first image portion is examined to determine a distinguishing feature. The overlapping area of the second image portion is then searched to locate the corresponding feature. The differences in alignment of the two features, such as rotation, expansion or compression, are then determined. One of the image portions is then rotated, compressed or expanded in the amount necessary to align the two images. The two images are then merged by eliminating the overlapping portion of one of the images.
Inventors
- 👤 Dominique Pitteloud
- 👤 Peter Phillips
- 👤 Jean-Paul H. Martin
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-27 04:04
CPC Classifications
H; H04; H04N; H04N1/00; H04N1/387; H04N1/04; H04N1/10; H04N1/107; H04N1/3876; H04N2201/00; H04N2201/04; H04N2201/0402; H04N2201/0414; H04N2201/047; H04N2201/04701; H04N2201/04743; H04N2201/04753; H04N2201/04758; H04N2201/04787
Claims Analysis
Total Claims: 29
Claim 1
Independent Claim
151 words
A method for automatically merging first and second images stored on a computer system, said first and second images each having an overlap portion overlapping the other image, the method comprising: (a) comparing pixel values of a plurality of regions to pixel values of adjacent regions; (b) determining an amount of uncorrelation of each region compared to said adjacent regions; (c) identifying as a first feature at least one of said regions having a higher amount of uncorrelation than at least one other region; (d) matching a corresponding feature in the second image to said first feature in the first image; (e) determining a difference in alignment of the two features; and (f) merging the two images into a single image by aligning the two images in accordance with the difference in alignment of the two features such that a single one of said two features remains in said single image.
Claim 2
Independent Claim
151 words
A method for automatically merging first and second images stored on a computer system, said first and second images each having an overlap portion overlapping the other image, the method comprising: (a) comparing pixel values of a plurality of regions to pixel values of adjacent regions; (b) determining an amount of uncorrelation of each region compared to said adjacent regions; (c) identifying as a first feature at least one of said regions having a higher amount of uncorrelation than at least one other region; (d) matching a corresponding feature in the second image to said first feature in the first image; (e) determining a difference in alignment of the two features; and (f) merging the two images into a single image by aligning the two images in accordance with the difference in alignment of the two features such that a single one of said two features remains in said single image.
Claim 3
Dependent Claim
42 words
The method of claim 1, wherein before step (d) further comprises: determining a geometry of the first image; determining a geometry of the second image; and transforming the geometry of the second image to that of the geometry of the first image.
Claim 4
Dependent Claim
16 words
The method of claim 2, wherein said transforming step includes translation, rotation, compression, and expansion transformations.
Claim 5
Dependent Claim
11 words
The method of claim 1, wherein said images are bitmap images.
Claim 6
Dependent Claim
11 words
The method of claim 1, wherein said images are vector-format images.
Claim 7
Dependent Claim
159 words
In a system for providing images to a digital computer, the improvement comprising: means for acquiring a source image as at least first and second image portions, said first and second image portions each having an overlap portion overlapping the other image portion; means for comparing pixel values of a plurality of regions to pixel values of adjacent regions; means for determining an amount of uncorrelation of each region compared to said adjacent regions; means for identifying as a first feature at least one of said regions having a higher amount of uncorrelation than at least one other region; means for matching said first feature to a corresponding feature in said overlap portion of said second image portion; means for determining a difference in alignment of said two features; and means for merging said at least two image portions into a single image by aligning the image portions in accordance with the difference in alignment of the two features.
Claim 8
Dependent Claim
159 words
In a system for providing images to a digital computer, the improvement comprising: means for acquiring a source image as at least first and second image portions, said first and second image portions each having an overlap portion overlapping the other image portion; means for comparing pixel values of a plurality of regions to pixel values of adjacent regions; means for determining an amount of uncorrelation of each region compared to said adjacent regions; means for identifying as a first feature at least one of said regions having a higher amount of uncorrelation than at least one other region; means for matching said first feature to a corresponding feature in said overlap portion of said second image portion; means for determining a difference in alignment of said two features; and means for merging said at least two image portions into a single image by aligning the image portions in accordance with the difference in alignment of the two features.
Claim 9
Dependent Claim
13 words
The system of claim 6, wherein said acquiring means is a handheld scanner.
Claim 10
Dependent Claim
24 words
The system of claim 6, further comprising: means for transforming a geometry of the second image portion to that of the first image portion.
Claim 11
Independent Claim
160 words
A system for entering images into a computer, the system comprising: a computer having a memory and a processor; scanner means for acquiring a source image as a plurality of image portions, at least two of said image portions partially overlapping each other; means for comparing pixel values of a plurality of regions to pixel values of adjacent regions; means for determining an amount of uncorrelation of each region compared to said adjacent regions; means for identifying as a first feature at least one of said regions having a higher amount of uncorrelation than at least one other region; means for determining a difference in alignment of said first feature and a corresponding feature in said overlap portion of said second image portion; and means for merging said at least two image portions by aligning the images in accordance with the difference in alignment of said features such that a single one of said features remains in said single image.
Claim 12
Independent Claim
160 words
A system for entering images into a computer, the system comprising: a computer having a memory and a processor; scanner means for acquiring a source image as a plurality of image portions, at least two of said image portions partially overlapping each other; means for comparing pixel values of a plurality of regions to pixel values of adjacent regions; means for determining an amount of uncorrelation of each region compared to said adjacent regions; means for identifying as a first feature at least one of said regions having a higher amount of uncorrelation than at least one other region; means for determining a difference in alignment of said first feature and a corresponding feature in said overlap portion of said second image portion; and means for merging said at least two image portions by aligning the images in accordance with the difference in alignment of said features such that a single one of said features remains in said single image.
Claim 13
Independent Claim
171 words
A method for automatically merging first and second image strips from a hand-held scanner, said first and second image strips each having an overlap portion overlapping the other image strip, comprising the steps of: a) determining said overlap portion of said first image strip which overlaps with said second image strip; (b) comparing pixel values of a plurality of regions to pixel values of adjacent regions; (c) determining an amount of uncorrelation of each region compared to said adjacent regions; (d) identifying as a first feature at least one of said regions having a higher amount of uncorrelation than at least one other region; (e) matching said first feature to a corresponding feature in an overlap portion of said second image strip; (f) determining a transformation required for a geometry of said first feature to match a geometry of said corresponding feature; (g) applying said transformation to one of said first and second image strips; (h) eliminating one of said overlap portions; and (f) combining said first and second image strips.
Claim 14
Independent Claim
171 words
A method for automatically merging first and second image strips from a hand-held scanner, said first and second image strips each having an overlap portion overlapping the other image strip, comprising the steps of: a) determining said overlap portion of said first image strip which overlaps with said second image strip; (b) comparing pixel values of a plurality of regions to pixel values of adjacent regions; (c) determining an amount of uncorrelation of each region compared to said adjacent regions; (d) identifying as a first feature at least one of said regions having a higher amount of uncorrelation than at least one other region; (e) matching said first feature to a corresponding feature in an overlap portion of said second image strip; (f) determining a transformation required for a geometry of said first feature to match a geometry of said corresponding feature; (g) applying said transformation to one of said first and second image strips; (h) eliminating one of said overlap portions; and (f) combining said first and second image strips.
Claim 15
Dependent Claim
34 words
The method of claim 10 wherein a second feature is located in said overlap portion of said first image and matched to a second corresponding feature in said overlap portion of said second image.
Claim 16
Dependent Claim
30 words
The method of claim 11 further comprising the step of selecting said first and second features from first and second distinct regions of said overlap portion of said first image.
Claim 17
Dependent Claim
58 words
The method of claim 11 further comprising the steps of: determining a first distance between said first and second features; determining a second distance between said corresponding features; comparing said first and second distances; and applying one of a compression or expansion transformation to one of said first and second images to match said first and second distances.
Claim 18
Dependent Claim
16 words
The method of claim 10 wherein said transformation includes rotation and one of compression and expansion.
Claim 19
Dependent Claim
16 words
The method of claim 10 wherein said first and second images are stored as a bitmap.
Claim 20
Dependent Claim
63 words
The method of claim 10 wherein said step of locating at least a first feature includes the steps of: determining at least one attribute of features to be examined; determining a minimum score for said attribute; determining scores for said attribute of features in said overlap portion of said first image; and updating said minimum score to the score of any feature located.
Claim 21
Dependent Claim
44 words
The method of claim 10 further comprising the steps of: predicting a region in said overlap portion of said second image containing said corresponding feature from a location of said first feature in said first image; and searching said region for said corresponding feature.
Claim 22
Independent Claim
184 words
A method for automatically merging first and second image strips from a hand-held scanner, said first and second image strips each having an overlap portion overlapping the other image strip, comprising the steps of: (a) determining said overlap portion of said first image strip which overlaps with said second image strip; (b) comparing pixel values of a plurality of regions to pixel values of adjacent regions; (c) determining an amount of uncorrelation of each region compared to said adjacent regions; (d) identifying as a first feature at least one of said regions having a higher amount of uncorrelation than at least one other region; (e) matching said first and second features to corresponding features in an overlap portion of said second image strip; (f) determining a transformation required for a geometry of said first and second features to match a geometry of said corresponding features, said transformation including rotation and one of compression and expansion; (g) applying said transformation to one of said first and second image strips; (h) eliminating one of said overlap portions; and (i) combining said first and second image strips.
Claim 23
Independent Claim
184 words
A method for automatically merging first and second image strips from a hand-held scanner, said first and second image strips each having an overlap portion overlapping the other image strip, comprising the steps of: (a) determining said overlap portion of said first image strip which overlaps with said second image strip; (b) comparing pixel values of a plurality of regions to pixel values of adjacent regions; (c) determining an amount of uncorrelation of each region compared to said adjacent regions; (d) identifying as a first feature at least one of said regions having a higher amount of uncorrelation than at least one other region; (e) matching said first and second features to corresponding features in an overlap portion of said second image strip; (f) determining a transformation required for a geometry of said first and second features to match a geometry of said corresponding features, said transformation including rotation and one of compression and expansion; (g) applying said transformation to one of said first and second image strips; (h) eliminating one of said overlap portions; and (i) combining said first and second image strips.
Claim 24
Dependent Claim
58 words
The method of claim 18 further comprising the steps of: determining a first distance between said first and second features; determining a second distance between said corresponding features; comparing said first and second distances; and applying one of a compression or expansion transformation to one of said first and second images to match said first and second distances.
Claim 25
Independent Claim
198 words
A method for automatically merging first and second image strips from a hand-held scanner, said first and second image strips each having an overlap portion overlapping the other image strip, comprising the steps of: a) determining said overlap portion of said first image strip which overlaps with said second image strip; b) locating first and second features having a high amount of uncorrelation in first and second distinct regions of said overlap portion; c) matching said first and second features to corresponding features in an overlap portion of said second image strip; d) determining a first distance between said first and second features; e) determining a second distance between said corresponding features; f) comparing said first and second distances; g) applying one of a compression or expansion transformation to one of said first and second images to match said first and second distances; h) determining a transformation required for a geometry of said first and second features to match a geometry of said corresponding features, said transformation including rotation; i) applying said transformation to one of said first and second image strips; j) eliminating one of said overlap portions; and k) combining said first and second image strips.
Claim 26
Independent Claim
198 words
A method for automatically merging first and second image strips from a hand-held scanner, said first and second image strips each having an overlap portion overlapping the other image strip, comprising the steps of: a) determining said overlap portion of said first image strip which overlaps with said second image strip; b) locating first and second features having a high amount of uncorrelation in first and second distinct regions of said overlap portion; c) matching said first and second features to corresponding features in an overlap portion of said second image strip; d) determining a first distance between said first and second features; e) determining a second distance between said corresponding features; f) comparing said first and second distances; g) applying one of a compression or expansion transformation to one of said first and second images to match said first and second distances; h) determining a transformation required for a geometry of said first and second features to match a geometry of said corresponding features, said transformation including rotation; i) applying said transformation to one of said first and second image strips; j) eliminating one of said overlap portions; and k) combining said first and second image strips.
Claim 27
Independent Claim
177 words
A method for automatically merging first and second images stored on a computer system, said first and second image strips each having an overlap portion overlapping the other image strip, the method comprising: (a) comparing pixel values of a plurality of regions to pixel values of adjacent regions; (b) determining an amount of uncorrelation of each region compared to said adjacent regions; (c) identifying as a first feature at least one of said regions having a higher amount of uncorrelation than at least one other region; (d) matching a corresponding second feature in the second image to said first feature in the first image; (e) determining a geometry of the first feature; (f) determining a geometry of the second feature; (g) transforming the geometry of the second image to that of the geometry of the first feature; (h) determining a difference in alignment of the two features; and (i) merging the first and second images into a single image by aligning the first and second images in accordance with the difference in alignment of the two features.
Claim 28
Independent Claim
177 words
A method for automatically merging first and second images stored on a computer system, said first and second image strips each having an overlap portion overlapping the other image strip, the method comprising: (a) comparing pixel values of a plurality of regions to pixel values of adjacent regions; (b) determining an amount of uncorrelation of each region compared to said adjacent regions; (c) identifying as a first feature at least one of said regions having a higher amount of uncorrelation than at least one other region; (d) matching a corresponding second feature in the second image to said first feature in the first image; (e) determining a geometry of the first feature; (f) determining a geometry of the second feature; (g) transforming the geometry of the second image to that of the geometry of the first feature; (h) determining a difference in alignment of the two features; and (i) merging the first and second images into a single image by aligning the first and second images in accordance with the difference in alignment of the two features.
Claim 29
Dependent Claim
16 words
The method of claim 21, wherein said transforming step includes translation, rotation, compression, and expansion transformations.
References Cited (Backward Citations)
US3852573A
Cited
US4272756A
Cited
US4819083A
Cited
EP0267456A2
Cited
US5054097A
Cited
US5220619A
Cited
US5113267A
Cited
US5164997A
Cited
US5355146A
Cited
US5170441A
Cited
US5103490A
Cited
US5142357A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2000-03-10 | 2000-09-09 | 2001-03-11 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2004-03-10 | 2004-09-09 | 2005-03-11 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2008-03-10 | 2008-09-09 | 2009-03-11 | $7700.00 | Window Closed / Lapsed |