US7123783B2
Expired / Lapsed
US
⏱️ 0.0 years remaining
Face classification using curvature-based multi-scale morphology
Assignee: Arizona State University Downtown Phoenix campus
•
Filing: 2003-01-21
•
Granted: 2006-10-17
•
Expires: 2023-01-21
Abstract
Abstract An image classification system uses curvature-based multi-scale morphology to classify an image by its most distinguishing features. The image is recorded in digital form. Curvature features associated with the image are determined. A structuring element is modulated based on the curvature features. The shape of the structuring element is controlled by making it a function of both the scaling factor and the principal curvatures of the intensity surface of the face image. The structuring element modulated with the curvature features is superimposed on the image to determine a feature vector of the image using mathematical morphology. When this Curvature-based Multi-scale Morphology (CMM) technique is applied to face images, a high-dimensional feature vector is obtained. The dimensionality of this feature vector is reduced by using the PCA technique, and the low-dimensional feature vectors are analyzed using an Enhanced FLD Model (EFM) for superior classification performance.
Inventors
- 👤 Madhusudhana Gargesha
- 👤 Sethuraman Panchanathan
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 13:05
CPC Classifications
G; G06; G06V; G06V40/00; G06V40/10; G06V40/16; G06V40/168
Claims Analysis
Total Claims: 29
Claim 1
Independent Claim
58 words
A method of classifying an image, comprising: recording the image in numeric format; determining curvature features of the image; modulating a structuring element based on the curvature features; applying a grid to the image; superimposing the structuring element on the grid; and formulating a feature vector for the image using a morphology calculation at points on the grid.
Claim 2
Independent Claim
58 words
A method of classifying an image, comprising: recording the image in numeric format; determining curvature features of the image; modulating a structuring element based on the curvature features; applying a grid to the image; superimposing the structuring element on the grid; and formulating a feature vector for the image using a morphology calculation at points on the grid.
Claim 3
Dependent Claim
13 words
The method of claim 1 , wherein the structuring element is a cylinder.
Claim 4
Dependent Claim
28 words
The method of claim 1 , wherein the step of determining curvature features of the image includes determining a gradient of intensity variation across pixels of the image.
Claim 5
Dependent Claim
40 words
The method of claim 3 , wherein the step of determining curvature features of the image further includes applying Gaussian derivative and filtering to the gradient of intensity variation across pixels of the image to form a principal feature map.
Claim 6
Dependent Claim
45 words
The method of claim 1 , further including: storing feature vectors for known images in a database; determining a feature vector for an unknown image; and comparing the feature vector for the unknown image to feature vectors stored in the database to find a match.
Claim 7
Dependent Claim
21 words
The method of claim 5 , wherein the step of comparing includes identifying a closest match based on a distance measure.
Claim 8
Dependent Claim
53 words
The image classification system of claim 1 , further including: means for storing feature vectors for known images in a database; means for determining a feature vector for an unknown image; and means for comparing the feature vector for the unknown image to feature vectors stored in the database to find a match.
Claim 9
Dependent Claim
25 words
The image classification system of claim 7 , wherein the means for comparing includes means for identifying a closest match based on a distance measure.
Claim 10
Independent Claim
115 words
A method of identifying an unknown image, comprising: building a database of known images, each known image having a feature vector; determining a feature vector for the unknown image by, (a) recording the unknown image in numeric format, (b) determining curvature features of the unknown image, (c) modulating a structuring element based on the curvature features of the unknown image, (d) applying a grid to the unknown image, (e) superimposing the structuring element on the grid, and (f) formulating the feature vector for the unknown image using a morphology calculation at points on the grid; and comparing the feature vector for the unknown image to feature vectors stored in the database to find a match.
Claim 11
Independent Claim
115 words
A method of identifying an unknown image, comprising: building a database of known images, each known image having a feature vector; determining a feature vector for the unknown image by, (a) recording the unknown image in numeric format, (b) determining curvature features of the unknown image, (c) modulating a structuring element based on the curvature features of the unknown image, (d) applying a grid to the unknown image, (e) superimposing the structuring element on the grid, and (f) formulating the feature vector for the unknown image using a morphology calculation at points on the grid; and comparing the feature vector for the unknown image to feature vectors stored in the database to find a match.
Claim 12
Dependent Claim
13 words
The method of claim 9 , wherein the structuring element is a cylinder.
Claim 13
Dependent Claim
28 words
The method of claim 9 , wherein the step of determining curvature features of the image includes determining a gradient of intensity variation across pixels of the image.
Claim 14
Dependent Claim
40 words
The method of claim 11 , wherein the step of determining curvature features of the image further includes applying Gaussian derivative and filtering to the gradient of intensity variation across pixels of the image to form a principal feature map.
Claim 15
Dependent Claim
21 words
The method of claim 9 , wherein the step of comparing includes identifying a closest match based on a distance measure.
Claim 16
Dependent Claim
68 words
An image classification system, comprising: means for recording the image in numeric format; means for determining curvature features of the image; means for modulating a structuring element based on the curvature features; means for applying a grid to the image; means for superimposing the structuring element on the grid; and means for formulating a feature vector for the image using a morphology calculation at points on the grid.
Claim 17
Dependent Claim
68 words
An image classification system, comprising: means for recording the image in numeric format; means for determining curvature features of the image; means for modulating a structuring element based on the curvature features; means for applying a grid to the image; means for superimposing the structuring element on the grid; and means for formulating a feature vector for the image using a morphology calculation at points on the grid.
Claim 18
Dependent Claim
15 words
The image classification system of claim 14 , wherein the structuring element is a cylinder.
Claim 19
Dependent Claim
32 words
The image classification system of claim 14 , wherein the means for determining curvature features of the image includes means for determining a gradient of intensity variation across pixels of the image.
Claim 20
Dependent Claim
44 words
The image classification system of claim 16 , wherein the means for determining curvature features of the image further includes means for applying Gaussian derivative and filtering to the gradient of intensity variation across pixels of the image to form a principal feature map.
Claim 21
Dependent Claim
50 words
A image classification method, comprising: recording an image in numeric format; determining curvature features of the image; modulating a structuring element based on the curvature features; superimposing the structuring element over the image; and formulating a feature vector for the image using a morphology calculation at points on the image.
Claim 22
Dependent Claim
50 words
A image classification method, comprising: recording an image in numeric format; determining curvature features of the image; modulating a structuring element based on the curvature features; superimposing the structuring element over the image; and formulating a feature vector for the image using a morphology calculation at points on the image.
Claim 23
Dependent Claim
15 words
The image classification method of claim 18 , wherein the structuring element is a cylinder.
Claim 24
Dependent Claim
30 words
The image classification method of claim 18 , wherein the step of determining curvature features of the image includes determining a gradient of intensity variation across pixels of the image.
Claim 25
Dependent Claim
42 words
The image classification method of claim 20 , wherein the step of determining curvature features of the image further includes applying Gaussian derivative and filtering to the gradient of intensity variation across pixels of the image to form a principal feature map.
Claim 26
Dependent Claim
47 words
The image classification method of claim 18 , further including: storing feature vectors for known images in a database; determining a feature vector for an unknown image; and comparing the feature vector for the unknown image to feature vectors stored in the database to find a match.
Claim 27
Dependent Claim
23 words
The image classification method of claim 22 , wherein the step of comparing includes identifying a closest match based on a distance measure.
Claim 28
Dependent Claim
62 words
A mass storage device including an image classification system, the image classification system comprising the steps of: recording an image in numeric format; determining curvature features of the image; modulating a structuring element based on the curvature features; superimposing the structuring element over the image; and formulating a feature vector for the image using a morphology calculation at points on the image.
Claim 29
Dependent Claim
62 words
A mass storage device including an image classification system, the image classification system comprising the steps of: recording an image in numeric format; determining curvature features of the image; modulating a structuring element based on the curvature features; superimposing the structuring element over the image; and formulating a feature vector for the image using a morphology calculation at points on the image.
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) | 2009-10-16 | 2010-04-17 | 2010-10-17 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2013-10-16 | 2014-04-17 | 2014-10-17 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2017-10-16 | 2018-04-17 | 2018-10-17 | $7700.00 | Window Closed / Lapsed |