US8805083B1
Active / In Force
US
⏱️ 4.4 years remaining
System and method for discriminating constituents of image by complex spectral signature extraction
Assignee: Reality Anaytics Inc
•
Filing: 2011-03-21
•
Granted: 2014-08-12
•
Expires: 2031-03-21
Abstract
Abstract A system and method are provided to operate upon image data electronically captured with complex spectral content in a plurality of image data pixels within a spatial image plane. A plurality of reference components are provided. A discovery processor is coupled to the general dictionary, and is programmably configured to execute a simultaneous sparse approximation process upon image data pixels of at least a portion of the captured image. The discovery processor discovers therefor a set of core spectral signatures defined in terms of selected reference components from the general dictionary. A match processor programmably configured to execute a selective matching process is also provided for transforming individual image data pixels into linear combinations of selected core spectral signatures. The constituent features of the captured image portion corresponding to the selectively matched core spectral signatures are discriminated according to the linear combination thereof.
Inventors
- 👤 Jeffrey M. Sieracki
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 10:17
CPC Classifications
G; G06; G06V; G06V40/00; G06V40/30; G06V40/33; G06V30/00; G06V30/10; G06V30/26; G06V30/262; G06V30/268
Claims Analysis
Total Claims: 31
Claim 1
Independent Claim
164 words
A system for processing electronically captured images formed by a plurality of spectral components comprising: a general dictionary having a plurality of reference components; a discovery processor coupled to said general dictionary, the discovery processor being programmably configured to execute a simultaneous sparse approximation process upon image data vectors of at least a portion of the captured image, the discovery processor further programmably configured to adaptively discover for the image data vectors a set of core spectral signatures defined in terms of reference components automatically selected from said general dictionary; and, a match processor programmably configured to selectively match at least one individual captured image data vector to at least a portion of said core spectral signature set to decompose said image data vector to a representation as a linear combination of the portion of said core spectral signature set; whereby constituent features of the captured image portion corresponding to said selectively matched core spectral signatures are discriminated according to said linear combination thereof.
Claim 2
Independent Claim
164 words
A system for processing electronically captured images formed by a plurality of spectral components comprising: a general dictionary having a plurality of reference components; a discovery processor coupled to said general dictionary, the discovery processor being programmably configured to execute a simultaneous sparse approximation process upon image data vectors of at least a portion of the captured image, the discovery processor further programmably configured to adaptively discover for the image data vectors a set of core spectral signatures defined in terms of reference components automatically selected from said general dictionary; and, a match processor programmably configured to selectively match at least one individual captured image data vector to at least a portion of said core spectral signature set to decompose said image data vector to a representation as a linear combination of the portion of said core spectral signature set; whereby constituent features of the captured image portion corresponding to said selectively matched core spectral signatures are discriminated according to said linear combination thereof.
Claim 3
Dependent Claim
39 words
The system as recited in claim 1 , wherein the image data is captured to include multi- or hyper-spectral pixels; and, said simultaneous sparse approximation process is executed upon at least one selectively grouped set of image data vectors.
Claim 4
Dependent Claim
44 words
The system as recited in claim 2 , wherein said simultaneous sparse approximation process is of a greedy adaptive decomposition (GAD) type, at least one set of selectively grouped image vectors being disposed in spatially contiguous manner with respect to a spatial image plane.
Claim 5
Dependent Claim
53 words
The system as recited in claim 3 , wherein predetermined environmental factors when present in the captured image portion are parametrically discriminated by said simultaneous sparse approximation for discovering said core spectral signatures responsive thereto, said predetermined environmental factors including local artifacts and lighting variations between different portions of the spatial image plane.
Claim 6
Dependent Claim
51 words
The system as recited in claim 3 , wherein said simultaneous sparse approximation process is executed jointly upon a plurality of said selectively grouped sets of image data vectors, a representative linear combination of said core spectral signatures being determined for each of said selectively grouped sets of image data vectors.
Claim 7
Dependent Claim
28 words
The system as recited in claim 3 , further comprising a spectral signature dictionary maintained responsive to said discovery processing to store said core spectral signatures discovered thereby.
Claim 8
Dependent Claim
46 words
The system as recited in claim 3 , wherein said match process includes: a matching pursuits decomposition to generate a linear combination of said core spectral signatures for an individual image data vector, and an adjustment of coefficients in said linear combination for statistical optimization thereof.
Claim 9
Dependent Claim
47 words
The system as recited in claim 3 , wherein said match process includes a simultaneous sparse approximation to decompose respective ones of said grouped image data vectors to generate a linear combination of said core spectral signatures for at least one of said grouped image data vectors.
Claim 10
Dependent Claim
31 words
The system as recited in claim 8 , wherein said match process further includes an adjustment of coefficients in said linear combination of said core spectral signatures for statistical optimization thereof.
Claim 11
Independent Claim
169 words
A system for discriminating constituents of an image electronically captured with complex spectral content by automatic spectral signature extraction comprising: a general dictionary having a plurality of reference components; a discovery processor coupled to said general dictionary, the discovery processor being programmably configured to execute a simultaneous sparse approximation process upon a set of image data pixels for at least a portion of the captured image, the discovery processor further programmably configured to adaptively discover for the image data vectors a set of core spectral signatures defined in terms of reference components automatically selected from said general dictionary; a spectral signature dictionary coupled to said discovery processor for storing said core spectral signatures discovered thereby; and, a detection processor programmably configured to execute a decomposition process for decomposing individual captured image data pixels to a representation as a linear combination of said core spectral signatures; whereby constituent features of the captured image portion corresponding to said linearly combined core spectral signatures are detected in the decomposed image data pixel.
Claim 12
Independent Claim
169 words
A system for discriminating constituents of an image electronically captured with complex spectral content by automatic spectral signature extraction comprising: a general dictionary having a plurality of reference components; a discovery processor coupled to said general dictionary, the discovery processor being programmably configured to execute a simultaneous sparse approximation process upon a set of image data pixels for at least a portion of the captured image, the discovery processor further programmably configured to adaptively discover for the image data vectors a set of core spectral signatures defined in terms of reference components automatically selected from said general dictionary; a spectral signature dictionary coupled to said discovery processor for storing said core spectral signatures discovered thereby; and, a detection processor programmably configured to execute a decomposition process for decomposing individual captured image data pixels to a representation as a linear combination of said core spectral signatures; whereby constituent features of the captured image portion corresponding to said linearly combined core spectral signatures are detected in the decomposed image data pixel.
Claim 13
Dependent Claim
45 words
The system as recited in claim 10 , wherein the image data is captured to include multi- or hyper-spectral pixels; and, said simultaneous sparse approximation process is of a greedy adaptive decomposition (GAD) type executed upon at least one selectively grouped set of image pixels.
Claim 14
Dependent Claim
53 words
The system as recited in claim 11 , wherein predetermined environmental factors when present in the captured image portion are parametrically discriminated by said simultaneous sparse approximation for discovering said core spectral signatures responsive thereto, said predetermined environmental factors including local artifacts and lighting variations between different portions of the spatial image plane.
Claim 15
Dependent Claim
49 words
The system as recited in claim 12 , wherein said simultaneous sparse approximation process is executed jointly upon a plurality of said selectively grouped sets of image pixels, a representative linear combination of said core spectral signatures being determined for each of said selectively grouped sets of image pixels.
Claim 16
Dependent Claim
44 words
The system as recited in claim 11 , wherein said decomposition process includes: a matching pursuits decomposition to generate a linear combination of said core spectral signatures for an individual pixel, and an adjustment of coefficients in said linear combination for statistical optimization thereof.
Claim 17
Independent Claim
174 words
A method for processing electronically captured images formed by a plurality of spectral components comprising the steps of: electronically capturing image data with complex spectral content, the image data including a plurality of image data vectors defined with respect to a spatial image plane; establishing a plurality of candidate spectral components; actuating a discovery processor to execute a simultaneous sparse approximation process upon image data vectors of at least a portion of the captured image, actuating the discovery processor to adaptively discover for the image data vectors a set of core spectral signatures defined in terms of candidate spectral components automatically selected from a general dictionary; and, selectively matching at least one individual captured image data vector to at least a portion of said core spectral signature set to decompose said image data vector to a representation as a linear combination of the portion of said core spectral signature set; whereby constituent features of the captured image portion corresponding to said selectively matched core spectral signatures are discriminated according to said linear combination thereof.
Claim 18
Independent Claim
174 words
A method for processing electronically captured images formed by a plurality of spectral components comprising the steps of: electronically capturing image data with complex spectral content, the image data including a plurality of image data vectors defined with respect to a spatial image plane; establishing a plurality of candidate spectral components; actuating a discovery processor to execute a simultaneous sparse approximation process upon image data vectors of at least a portion of the captured image, actuating the discovery processor to adaptively discover for the image data vectors a set of core spectral signatures defined in terms of candidate spectral components automatically selected from a general dictionary; and, selectively matching at least one individual captured image data vector to at least a portion of said core spectral signature set to decompose said image data vector to a representation as a linear combination of the portion of said core spectral signature set; whereby constituent features of the captured image portion corresponding to said selectively matched core spectral signatures are discriminated according to said linear combination thereof.
Claim 19
Dependent Claim
20 words
The method as recited in claim 15 , wherein the image data is captured to include multi- or hyper-spectral pixels.
Claim 20
Dependent Claim
27 words
The method as recited in claim 15 , wherein said simultaneous sparse approximation process is executed upon at least one selectively grouped set of image data vectors.
Claim 21
Dependent Claim
48 words
The method as recited in claim 17 , wherein said simultaneous sparse approximation is of a greedy adaptive decomposition (GAD) type, said candidate spectral components being established within the general dictionary, said candidate spectral components each being defined either as a continuous function or as a discrete vector.
Claim 22
Dependent Claim
30 words
The method as recited in claim 18 , wherein at least one set of selectively grouped image data vectors are disposed in spatially contiguous manner within the spatial image plane.
Claim 23
Dependent Claim
53 words
The method as recited in claim 19 , wherein predetermined environmental factors when present in the captured image portion are parametrically discriminated by said simultaneous sparse approximation for discovering said core spectral signatures responsive thereto, said predetermined environmental factors including local artifacts and lighting variations between different portions of the spatial image plane.
Claim 24
Dependent Claim
21 words
The method as recited in claim 20 , wherein said predetermined environmental factors include shadowing of light and local surface texture.
Claim 25
Dependent Claim
51 words
The method as recited in claim 18 , wherein said simultaneous sparse approximation process is executed jointly upon a plurality of said selectively grouped sets of image data vectors, a representative linear combination of said core spectral signatures being determined for each of said selectively grouped sets of image data vectors.
Claim 26
Dependent Claim
32 words
The method as recited in claim 18 , further comprising the step of maintaining a spectral signature dictionary updated responsive to said discovery processing to store said core spectral signatures discovered thereby.
Claim 27
Dependent Claim
46 words
The method as recited in claim 18 , wherein said selective matching includes: a matching pursuits decomposition to generate a linear combination of said core spectral signatures for an individual image data vector, and an adjustment of coefficients in said linear combination for statistical optimization thereof.
Claim 28
Dependent Claim
47 words
The method as recited in claim 18 , wherein said selective matching includes a simultaneous sparse approximation to decompose respective ones of said grouped image data vectors to generate a linear combination of said core spectral signatures for at least one of said grouped image data vectors.
Claim 29
Dependent Claim
30 words
The method as recited in claim 25 , wherein said selective matching includes an adjustment of coefficients in said linear combination of said core spectral signatures for statistical optimization thereof.
Claim 30
Dependent Claim
47 words
The method as recited in claim 18 , wherein said discovery processing includes selectively evaluating a set of candidate spectral components to discover said core spectral components therefrom, said selective evaluation including monitoring for disparity between coefficient values corresponding to respective ones of said candidate spectral components.
Claim 31
Dependent Claim
28 words
The method as recited in claim 18 , wherein said discovery processing includes hypothesis testing for adjustably optimizing said core spectral signatures with respect to predetermined statistical criteria.
References Cited (Backward Citations)
US5502764A
Cited
US5699121A
Cited
US5764921A
Cited
US6587507B1
Cited
US6016546A
Cited
US7020326B1
Cited
US6625213B2
Cited
US6985526B2
Cited
US6353673B1
Cited
US7120587B2
Cited
US7245659B2
Cited
US7003039B2
Cited
US6628300B2
Cited
US7006567B2
Cited
US6944222B2
Cited
EP1371958A1
Cited
US20050015600A1
Cited
US7526645B2
Cited
US7425693B2
Cited
US20050149296A1
Cited
US20060241916A1
Cited
US7511643B2
Cited
US20070156471A1
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2017-08-11 | 2018-02-10 | 2018-08-12 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2021-08-11 | 2022-02-10 | 2022-08-12 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2025-08-11 | 2026-02-10 | 2026-08-12 | $7700.00 | Window Closed / Lapsed |