← Back to Patent Explorer
US6862367B1 Expired / Lapsed US ⏱️ 0.0 years remaining

Artificial vision method and system

Assignee: Individual
•
Filing: 1999-06-10
•
Granted: 2005-03-01
•
Expires: 2019-06-10
📄 Original PDF 🌐 Google Patents 🔄 Sync Now

Abstract

Abstract An artificial vision system includes means ( 12, 14 ) for generating an image percept vector, means ( 16 ) for transforming this image percept vector into a feature vector, and means ( 16 ) for generating a response vector by multiplying the feature vector by a corresponding trained linkage matrix modeling a percept-response system.

Inventors

  • 👤 Gosta Granlund

Bibliographic Details

Application Number —
Jurisdiction US
Data Source google_patents
Last Synchronized 2026-11-09 12:01
CPC Classifications
G; G06; G06T; G06T7/00; G06V; G06V10/00; G06V10/20

Claims Analysis

Total Claims: 22
Claim 1
Independent Claim 39 words
An artificial vision method, characterized by: generating an image percept vector; transforming said image percept vector into a feature vector; and generating a response array by multiplying said feature vector by a trained linkage matrix modeling a precept-response system.
Claim 2
Dependent Claim 39 words
An artificial vision method, characterized by: generating an image percept vector; transforming said image percept vector into a feature vector; and generating a response array by multiplying said feature vector by a trained linkage matrix modeling a precept-response system.
Claim 3
Dependent Claim 20 words
The method of claim 1 , characterized by said feature vector including the covariance products of said image precept vector.
Claim 4
Dependent Claim 20 words
The method of claim 2 , characterized by said feature vector including the auto-covariance products of said image precept vector.
Claim 5
Dependent Claim 19 words
The method of claim 3 , characterized by said feature vector including the components of said image precept vector.
Claim 6
Dependent Claim 17 words
The method of claim 1 , characterized in that the elements of said linkage matrix are non-negative.
Claim 7
Dependent Claim 26 words
The method of claim 5 , characterized in that the elements of said linkage matrix are restricted to values between zero and a predetermined positive value.
Claim 8
Dependent Claim 35 words
The method of claim 1 , characterized by forming a coupled feature vector by coupling said feature vector to a response array, represented by a vector, using a Kronecker product before performing said matrix multiplication.
Claim 9
Dependent Claim 34 words
The method of claim 1 , characterized by forming a coupled feature vector by coupling said feature vector to several response arrays, represented by vectors, using repeated Kronecker products before performing said matrix multiplication.
Claim 10
Dependent Claim 29 words
The method of claim 1 , characterized by said response array being a coupled response vector formed by two response vectors coupled to each other by, a Kronecker product.
Claim 11
Dependent Claim 29 words
The method of claim 1 , characterized by said response array being a coupled response vector formed by two response vectors coupled to each other by, an outer product.
Claim 12
Dependent Claim 32 words
The method of claim 1 , characterized by said linkage matrix being a coupled linkage matrix formed by weighing a set of uncoupled linkage matrices with the elements of another response vector.
Claim 13
Dependent Claim 18 words
The method of claim 1 , characterized by converting, each response vector into a corresponding scalar response signal.
Claim 14
Dependent Claim 16 words
The method of claim 1 , characterized by discarding linkage matrix elements below a performed threshold.
Claim 15
Dependent Claim 38 words
The method of claim 1 , characterized by said precept vector being sparse, each non-zero precept vector element giving a continuos representation limited in definition range with respect to some variable property of an object in an image.
Claim 16
Dependent Claim 34 words
The method of claim 1 , characterized by said precept vector being sparse, each non-zero precept vector element giving a continuos representation, limited in spatial range, of the position an object in an image.
Claim 17
Dependent Claim 56 words
An artificial vision system characterized by: means ( 12 , 14 ) for generating an image percept vector; means ( 16 ) for transforming said image percept vector into a feature vector; and means ( 16 ) for generating, a response array by multiplying said feature vector by a trained linkage matrix modeling a percept-response system.
Claim 18
Dependent Claim 56 words
An artificial vision system characterized by: means ( 12 , 14 ) for generating an image percept vector; means ( 16 ) for transforming said image percept vector into a feature vector; and means ( 16 ) for generating, a response array by multiplying said feature vector by a trained linkage matrix modeling a percept-response system.
Claim 19
Dependent Claim 19 words
The system of claim 16 , characterized by means ( 18 , 20 ) for training said linkage matrix.
Claim 20
Dependent Claim 57 words
A precept-response system for sensing and control, characterized by: means ( 12 , 14 ) for generating a precept vector; means ( 16 ) for transforming said precept vector into a feature vector; and means ( 16 ) for generating a response array by multiplying said feature vector by a trained linkage matrix modeling said precept-response system.
Claim 21
Dependent Claim 57 words
A precept-response system for sensing and control, characterized by: means ( 12 , 14 ) for generating a precept vector; means ( 16 ) for transforming said precept vector into a feature vector; and means ( 16 ) for generating a response array by multiplying said feature vector by a trained linkage matrix modeling said precept-response system.
Claim 22
Dependent Claim 17 words
The system of claim 18 , characterized by means 18 , 20 for training said linkage matrix.

References Cited (Backward Citations)

US4282510A Cited
US5569907A Cited
US5726443A Cited
US5963667A Cited
US5901244A Cited
US6269354B1 Cited
US6751354B2 Cited

USPTO Annuity & Maintenance Windows

Annuity Stage Window Opens Payment Deadline Surcharge Period Until Estimated Fee Status
3.5 Years (Year 4) 2008-02-29 2008-08-30 2009-03-01 $2000.00 Window Closed / Lapsed
7.5 Years (Year 8) 2012-02-29 2012-08-30 2013-03-01 $3760.00 Window Closed / Lapsed
11.5 Years (Year 12) 2016-02-29 2016-08-30 2017-03-01 $7700.00 Window Closed / Lapsed

Assigned Categories & Tags

No categories assigned to this patent yet.

Assign Category Tag