US6347152B1
Expired / Lapsed
US
⏱️ 0.0 years remaining
Multiresolutional critical point filter and image matching using the invention
Assignee: JBF PARTNERS Inc
•
Filing: 2000-10-23
•
Granted: 2002-02-12
•
Expires: 2020-10-23
Abstract
Abstract A multiresolutional filter called a critical point filter is introduced. This filter extracts a maximum, a minimum, and two types of saddle points of pixel intensity for every 2x2 (horizontalxvertical) pixels so that an image of a lower level of resolution is newly generated for every type of a critical point. Using this multiresolutional filter, a source image and a destination image are hierarchized, and source hierarchical images and destination hierarchical images are matched using image characteristics recognized through a filtering operation.
Inventors
- 👤 Yoshihisa Shinagawa
- 👤 Tosiyasu Laurence Kunii
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 12:00
CPC Classifications
G; G06; G06V; G06V10/00; G06V10/40; G06V10/44; G06V10/443; G06V10/46; G06V10/462; G06V10/70; G06V10/74; G06V10/75; G06V10/754; G06V30/00; G06V30/10; G06V30/24; G06V30/248; G06V30/2504
Claims Analysis
Total Claims: 20
Claim 1
Independent Claim
78 words
An image matching method for matching a first image and a second image, said method comprising: determining first critical points in said first image, said first critical points including at least three types of critical points; determining second critical points in said second image, said second critical points including said at least three types of critical points; detecting correspondence between said first image and said second image by matching said first critical points and said second critical points.
Claim 2
Dependent Claim
78 words
An image matching method for matching a first image and a second image, said method comprising: determining first critical points in said first image, said first critical points including at least three types of critical points; determining second critical points in said second image, said second critical points including said at least three types of critical points; detecting correspondence between said first image and said second image by matching said first critical points and said second critical points.
Claim 3
Dependent Claim
48 words
The image matching method of claim 1 , wherein said matching said first critical points and said second critical points comprises forming a mapping for each critical point type of said at least three types of critical points between said first critical points and said second critical points.
Claim 4
Dependent Claim
33 words
The image matching method of claim 2 , wherein said mapping for each critical point type is made in consideration of at least one other of said mappings for each critical point type.
Claim 5
Dependent Claim
27 words
The image matching method of claim 1 , wherein said at least three types of critical points comprise a maximum, a minimum, and two types of saddlepoints.
Claim 6
Dependent Claim
35 words
The image matching method of claim 1 , wherein said first critical points and said second critical points comprise local critical points determined in predetermined areas of said first image and said second image respectively.
Claim 7
Dependent Claim
24 words
The image matching method of claim 1 , wherein said first critical points and said second critical points are determined based on pixel value.
Claim 8
Dependent Claim
21 words
The image matching method of claim 6 , wherein said pixel value comprises a combination of a plurality of pixel attributes.
Claim 9
Dependent Claim
15 words
The image matching method of claim 6 , wherein said pixel value comprises pixel intensity.
Claim 10
Dependent Claim
103 words
An image matching method comprising: extracting a first set of critical points from a first image by conducting a two-dimensional search over said first image, said first set of critical points including at least three types of critical points; extracting a second set of critical points from a second image by conducting a two-dimensional search over said second image, said second set of critical points including said at least three types of critical points; detecting correspondence between said first image and said second image by matching said at least three types of critical points respectively between said first image and said second image.
Claim 11
Dependent Claim
103 words
An image matching method comprising: extracting a first set of critical points from a first image by conducting a two-dimensional search over said first image, said first set of critical points including at least three types of critical points; extracting a second set of critical points from a second image by conducting a two-dimensional search over said second image, said second set of critical points including said at least three types of critical points; detecting correspondence between said first image and said second image by matching said at least three types of critical points respectively between said first image and said second image.
Claim 12
Dependent Claim
52 words
The image matching method of claim 9 , wherein said matching said at least three types of critical points respectively comprises forming a mapping for each critical point type of said at least three types of critical points between said first set of critical points and said second set of critical points.
Claim 13
Dependent Claim
33 words
The image matching method of claim 10 , wherein said mapping for each critical point type is made in consideration of at least one other of said mappings for each critical point type.
Claim 14
Dependent Claim
25 words
The image matching method of claim 9 , wherein said at least three types of critical points comprise a maximum, a minimum, and a saddlepoint.
Claim 15
Dependent Claim
39 words
The image matching method of claim 9 , wherein said first set of critical points and said second set of critical points comprise local critical points determined in predetermined areas of said first image and said second image respectively.
Claim 16
Dependent Claim
28 words
The image matching method of claim 9 , wherein said first set of critical points and said second set of critical points are determined based on pixel value.
Claim 17
Dependent Claim
21 words
The image matching method of claim 14 , wherein said pixel value comprises a combination of a plurality of pixel attributes.
Claim 18
Dependent Claim
15 words
The image matching method of claim 14 , wherein said pixel value comprises pixel intensity.
Claim 19
Dependent Claim
62 words
An image matching method for matching a first image and a second image, said method comprising: for said first image, generating, through multiresolutional critical point filtering, first hierarchical images each having a different resolution; for said second image, generating, through multiresolutional critical point filtering, second hierarchical images each having a different resolution; matching said first hierarchical images and said second hierarchical images.
Claim 20
Dependent Claim
62 words
An image matching method for matching a first image and a second image, said method comprising: for said first image, generating, through multiresolutional critical point filtering, first hierarchical images each having a different resolution; for said second image, generating, through multiresolutional critical point filtering, second hierarchical images each having a different resolution; matching said first hierarchical images and said second hierarchical 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) | 2005-02-11 | 2005-08-13 | 2006-02-12 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2009-02-11 | 2009-08-13 | 2010-02-12 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2013-02-11 | 2013-08-13 | 2014-02-12 | $7700.00 | Window Closed / Lapsed |