US8565536B2
Active / In Force
US
⏱️ 3.4 years remaining
Material recognition from an image
Assignee: Microsoft Technology Licensing LLC
•
Filing: 2010-04-01
•
Granted: 2013-10-22
•
Expires: 2030-04-01
Abstract
Abstract A method of operating a computer system to perform material recognition based on multiple features extracted from an image is described. A combination of low-level features extracted directly from the image and multiple novel mid-level features extracted from transformed versions of the image are selected and used to assign a material category to a single image. The novel mid-level features include non-reflectance based features such as the micro-texture features micro jet and micro-SIFT and the shape feature curvature, and reflectance-based features including edge slice and edge ribbon. An augmented Latent Dirichlet Allocation (LDA) model is provided as an exemplary Bayesian framework for selecting a subset of features useful for material recognition of objects in an image.
Inventors
- 👤 Ce Liu
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 09:59
CPC Classifications
G; G06; G06V; G06V20/00; G06V20/80; G06F; G06F18/00; G06F18/20; G06F18/21; G06F18/211; G06F18/2111; G06F18/29; G06F18/295; G06V10/00; G06V10/40; G06V10/46; G06V10/462; G06V10/70; G06V10/84; G06V10/85
Claims Analysis
Total Claims: 18
Claim 1
Independent Claim
103 words
A method implemented by at least one computer processing device, the method comprising: extracting a plurality of features from an image; combining at least two of the plurality of features to generate a model comprising distributions for the at least two of the plurality of features across groups of pixels in the image, wherein the at least two of the plurality of features include one or more mid-level features; and categorizing a material of an object in the image based, at least in part, on the distributions in the model, wherein an individual mid-level feature is a texture-based feature that is not reflectance-based.
Claim 2
Independent Claim
103 words
A method implemented by at least one computer processing device, the method comprising: extracting a plurality of features from an image; combining at least two of the plurality of features to generate a model comprising distributions for the at least two of the plurality of features across groups of pixels in the image, wherein the at least two of the plurality of features include one or more mid-level features; and categorizing a material of an object in the image based, at least in part, on the distributions in the model, wherein an individual mid-level feature is a texture-based feature that is not reflectance-based.
Claim 3
Dependent Claim
37 words
The method of claim 1 , wherein the at least two of the plurality of features comprise a reflectance-based edge slice feature representing image changes along a direction normal to at least one edge in the image.
Claim 4
Dependent Claim
33 words
The method of claim 2 , wherein the image changes comprise changes in a distribution of gradient orientations determined for an individual group of pixels oriented normal to the at least one edge.
Claim 5
Dependent Claim
56 words
The method of claim 1 , wherein combining at least two of the plurality of features comprises: selecting the at least two of the plurality of features to combine based, at least in part, on a trained model in which combinations of features are analyzed to determine the at least two of the plurality of features.
Claim 6
Dependent Claim
34 words
The method of claim 1 , wherein the at least two of the plurality of features used to generate the model are less than all of the plurality of features extracted from the image.
Claim 7
Dependent Claim
137 words
A hardware computer-readable storage medium storing a plurality of instructions that, when executed by a computer processing device, cause the computer processing device to perform acts comprising: extracting at least one reflectance-based feature and at least one non-reflectance based feature from an image; and categorizing a material in the image based, at least in part, on the at least one reflectance-based feature and the at least one non-reflectance based feature, wherein the at least one reflectance-based feature is associated with image changes relative to at least one edge in the image and comprises: an edge slice feature representing the image changes along a direction normal to the at least one edge in the image, or an edge ribbon feature that describes the image changes along another direction tangent to the at least one edge of the image.
Claim 8
Dependent Claim
137 words
A hardware computer-readable storage medium storing a plurality of instructions that, when executed by a computer processing device, cause the computer processing device to perform acts comprising: extracting at least one reflectance-based feature and at least one non-reflectance based feature from an image; and categorizing a material in the image based, at least in part, on the at least one reflectance-based feature and the at least one non-reflectance based feature, wherein the at least one reflectance-based feature is associated with image changes relative to at least one edge in the image and comprises: an edge slice feature representing the image changes along a direction normal to the at least one edge in the image, or an edge ribbon feature that describes the image changes along another direction tangent to the at least one edge of the image.
Claim 9
Dependent Claim
21 words
The hardware computer-readable storage medium of claim 6 , wherein the at least one reflectance-based feature comprises the edge slice feature.
Claim 10
Dependent Claim
21 words
The hardware computer-readable storage medium of claim 6 , wherein the at least one reflectance-based feature comprises the edge ribbon feature.
Claim 11
Dependent Claim
21 words
The hardware computer-readable storage medium of claim 6 , wherein the at least one non-reflectance based feature is a texture-based feature.
Claim 12
Dependent Claim
70 words
The hardware computer-readable storage medium of claim 6 , the acts further comprising: combining a first dictionary created for the at least one reflectance-based feature and a second dictionary created for the at least one non-reflectance based feature to generate a joint dictionary; and training a bag-of-words model using the joint dictionary, wherein the material in the image is categorized based, at least in part, on the trained bag-of-words model.
Claim 13
Dependent Claim
19 words
The method of claim 1 , wherein the texture-based feature is extracted from a filtered version of the image.
Claim 14
Dependent Claim
19 words
The method of claim 1 , wherein the texture-based feature is a micro-jet feature obtained using a residual image.
Claim 15
Dependent Claim
21 words
The method of claim 1 , wherein the texture-based feature is a micro-SIFT (scale-invariant feature transform) obtained using a residual image.
Claim 16
Independent Claim
89 words
A system comprising: logic configured to: extract at least two features from an image, combine the at least two features to generate a model comprising distributions for the at least two features across groups of pixels in the image, wherein an individual one of the at least two features describes reflectance variations along edges in the image, and categorize a material of an object in the image based, at least in part, on the distributions in the model; and one or more processing devices configured to execute the logic.
Claim 17
Independent Claim
89 words
A system comprising: logic configured to: extract at least two features from an image, combine the at least two features to generate a model comprising distributions for the at least two features across groups of pixels in the image, wherein an individual one of the at least two features describes reflectance variations along edges in the image, and categorize a material of an object in the image based, at least in part, on the distributions in the model; and one or more processing devices configured to execute the logic.
Claim 18
Dependent Claim
18 words
The system of claim 14 , wherein the individual feature describes a reflectance property of glossiness or transparency.
References Cited (Backward Citations)
US5794788A
Cited
US6711293B1
Cited
US6140643A
Cited
US20040213459A1
Cited
US20050036690A1
Cited
US7706918B2
Cited
US20060133650A1
Cited
US7519200B2
Cited
US20070091320A1
Cited
US20070133866A1
Cited
US20090304280A1
Cited
US20080075361A1
Cited
US8194953B2
Cited
US20090208106A1
Cited
US8218913B1
Cited
US20110182477A1
Cited
US20110243450A1
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2016-10-21 | 2017-04-22 | 2017-10-22 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2020-10-21 | 2021-04-22 | 2021-10-22 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2024-10-21 | 2025-04-22 | 2025-10-22 | $7700.00 | Window Closed / Lapsed |