Patent US6122401A successfully refreshed from Google Patents.
US6122401A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Image processing method and apparatus
Assignee: Eastman Kodak Co
•
Filing: 1992-01-30
•
Granted: 2000-09-19
•
Expires: 2012-01-30
Abstract
Abstract An image processing method and apparatus in the form of a sampling mask that enables slight image variations to be absorbed and improves the accuracy of image matching based on a comparison of characteristic quantities such as by the template matching method. A multi-dimensional image is divided into regions that overlap each other. The pixels in each of the regions are weighted in accordance with a predetermined function whereby the weighting is largest at the center of a region and decreases as the distance from the center increases. The characteristic sums of the weighted pixel values are extracted as the mask output for absorbing local image variation.
Inventors
- 👤 Kagenori Nagao
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-30 10:28
CPC Classifications
G; G06; G06V; G06V10/00; G06V10/70; G06V10/74; G06V10/75; G06V10/751
Claims Analysis
Total Claims: 30
Claim 1
Independent Claim
97 words
A digital image processing method, comprising the steps of: (a) partitioning a multi-dimensional image comprising a plurality of image elements into overlapping multi-dimensional regions; (b) applying a predetermined weighting function to the image elements within each region for distinguishing image elements at the periphery of each region from image elements at the center of each region, to provide a weighted image element value for each image element; and (c) determining a characteristic output of each region from the weighted image element values, the characteristic output comprising one or more characteristics of the input image within that region.
Claim 2
Dependent Claim
97 words
A digital image processing method, comprising the steps of: (a) partitioning a multi-dimensional image comprising a plurality of image elements into overlapping multi-dimensional regions; (b) applying a predetermined weighting function to the image elements within each region for distinguishing image elements at the periphery of each region from image elements at the center of each region, to provide a weighted image element value for each image element; and (c) determining a characteristic output of each region from the weighted image element values, the characteristic output comprising one or more characteristics of the input image within that region.
Claim 3
Dependent Claim
38 words
A method according to claim 1, further comprising the step of: (d) comparing the characteristic outputs of the regions to a plurality of predetermined reference images such that the input image may be recognized notwithstanding local image variation.
Claim 4
Dependent Claim
26 words
A method according to claim 1 wherein the predetermined weighting function increases towards the center of each region and decreases towards the periphery of each region.
Claim 5
Dependent Claim
30 words
A method according to claim 1 wherein the predetermined weighting function is largest at the center of each region and is at a minimum at the periphery of each region.
Claim 6
Dependent Claim
11 words
A method according to claim 1 wherein the regions are hexagonal.
Claim 7
Dependent Claim
24 words
A method according to claim 1 wherein the characteristics of the input image within the region are chosen from intensity, curvature, and tangent angle.
Claim 8
Dependent Claim
23 words
A method according to claim 1 wherein the centers of the regions are uniformly spaced along each axis of the multi-dimensional input image.
Claim 9
Dependent Claim
21 words
A method according to claim 1 wherein the periphery of each region is tangent to the centers of each adjacent region.
Claim 10
Dependent Claim
20 words
A method according to claim 1 wherein said step of determining the characteristic output is simultaneously performed for all regions.
Claim 11
Independent Claim
124 words
A method of image recognition, comprising the steps of: (a) partitioning a multi-dimensional image, comprising a plurality of image elements, into overlapping multi-dimensional regions; (b) applying a predetermined weighting function to the image elements within each region, the predetermined weighting function increasing towards the center of each region and decreasing towards the periphery of each region, to provide a weighted image element value for each image element; (c) determining a characteristic output of each region from the weighted image element values, the characteristic output comprising one or more characteristics of the input image within that region; and (d) comparing the characteristic outputs of the regions to a plurality of predetermined reference images such that the input image may be recognized notwithstanding local image variation.
Claim 12
Independent Claim
124 words
A method of image recognition, comprising the steps of: (a) partitioning a multi-dimensional image, comprising a plurality of image elements, into overlapping multi-dimensional regions; (b) applying a predetermined weighting function to the image elements within each region, the predetermined weighting function increasing towards the center of each region and decreasing towards the periphery of each region, to provide a weighted image element value for each image element; (c) determining a characteristic output of each region from the weighted image element values, the characteristic output comprising one or more characteristics of the input image within that region; and (d) comparing the characteristic outputs of the regions to a plurality of predetermined reference images such that the input image may be recognized notwithstanding local image variation.
Claim 13
Dependent Claim
24 words
A method according to claim 10 wherein the characteristics of the input image within the region are chosen from intensity, curvature, and tangent angle.
Claim 14
Dependent Claim
23 words
A method according to claim 10 wherein the centers of the regions are uniformly spaced along each axis of the multi-dimensional input image.
Claim 15
Dependent Claim
21 words
A method according to claim 10 wherein the periphery of each region is tangent to the centers of each adjacent region.
Claim 16
Dependent Claim
20 words
A method according to claim 10 wherein said step of determining the characteristic output is simultaneously performed for all regions.
Claim 17
Independent Claim
114 words
An apparatus for processing an image having a plurality of image elements, comprising: (a) masking means for partitioning a multi-dimensional image into overlapping multi-dimensional regions; (b) adjusting means, responsive to said masking means, for applying a predetermined weighting function to the image elements within each region, the predetermined weighting function increasing towards the center of each region and decreasing towards the periphery of each region, to provide a weighted image element value for each image element; and (c) computing means, responsive to said adjusting means, for determining a characteristic output of each region from the weighted image element values, the characteristic output comprising one or more characteristics of the input image within that region.
Claim 18
Independent Claim
114 words
An apparatus for processing an image having a plurality of image elements, comprising: (a) masking means for partitioning a multi-dimensional image into overlapping multi-dimensional regions; (b) adjusting means, responsive to said masking means, for applying a predetermined weighting function to the image elements within each region, the predetermined weighting function increasing towards the center of each region and decreasing towards the periphery of each region, to provide a weighted image element value for each image element; and (c) computing means, responsive to said adjusting means, for determining a characteristic output of each region from the weighted image element values, the characteristic output comprising one or more characteristics of the input image within that region.
Claim 19
Dependent Claim
17 words
An apparatus according to claim 15 wherein said masking means partitions the multi-dimensional image into hexagonal regions.
Claim 20
Dependent Claim
30 words
An apparatus according to claim 15 wherein said computing means comprises means for summing the weighted image element values within each region to provide a characteristic output for each region.
Claim 21
Dependent Claim
24 words
An apparatus according to claim 15 wherein the characteristics of the input image within the region are chosen from intensity, curvature, and tangent angle.
Claim 22
Dependent Claim
23 words
An apparatus according to claim 15 wherein the centers of the regions are uniformly spaced along each axis of the multi-dimensional input image.
Claim 23
Dependent Claim
21 words
An apparatus according to claim 15 wherein the periphery of each region is tangent to the centers of each adjacent region.
Claim 24
Dependent Claim
24 words
An apparatus according to claim 15 wherein said computing means is a parallel processor for simultaneously determining the characteristic output of all the regions.
Claim 25
Independent Claim
149 words
An apparatus for recognizing an image having a plurality of image elements, comprising: (a) masking means for partitioning a multi-dimensional image into overlapping multi-dimensional regions; (b) adjusting means, responsive to said masking means, for applying a predetermined weighting function to the image elements within each region, the predetermined weighting function increasing towards the center of each region and decreasing towards the periphery of each region, to provide a weighted image element value for each image element; (c) computing means, responsive to said adjusting means, for determining a characteristic output of each region from the weighted image element values, the characteristic output comprising one or more characteristics of the input image within that region; and (d) identification means, responsive to said computing means, for comparing the characteristic outputs of the regions to a plurality of predetermined reference images such that the input image may be recognized notwithstanding local image variation.
Claim 26
Independent Claim
149 words
An apparatus for recognizing an image having a plurality of image elements, comprising: (a) masking means for partitioning a multi-dimensional image into overlapping multi-dimensional regions; (b) adjusting means, responsive to said masking means, for applying a predetermined weighting function to the image elements within each region, the predetermined weighting function increasing towards the center of each region and decreasing towards the periphery of each region, to provide a weighted image element value for each image element; (c) computing means, responsive to said adjusting means, for determining a characteristic output of each region from the weighted image element values, the characteristic output comprising one or more characteristics of the input image within that region; and (d) identification means, responsive to said computing means, for comparing the characteristic outputs of the regions to a plurality of predetermined reference images such that the input image may be recognized notwithstanding local image variation.
Claim 27
Dependent Claim
30 words
An apparatus according to claim 22 wherein said computing means comprises means for summing the weighted image element values within each region to provide a characteristic output for each region.
Claim 28
Dependent Claim
23 words
An apparatus according to claim 22 wherein the centers of the regions are uniformly spaced along each axis of the multi-dimensional input image.
Claim 29
Dependent Claim
24 words
An apparatus according to claim 22 wherein said computing means is a parallel processor for simultaneously determining the characteristic output of all the regions.
Claim 30
Dependent Claim
29 words
An apparatus according to claim 22 wherein said identification means is a neutral network for comparing the characteristic outputs of the regions to a plurality of predetermined reference images.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2003-09-19 | 2004-03-20 | 2004-09-19 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2007-09-19 | 2008-03-20 | 2008-09-19 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2011-09-19 | 2012-03-20 | 2012-09-19 | $7700.00 | Window Closed / Lapsed |