Casey A Smith

US Patent:

8139850, Mar 20, 2012

Filed:

Dec 5, 2008

Appl. No.:

12/315643

Inventors:

Bruce Allen Maxwell - Benton ME, US
Casey Arthur Smith - Grand Junction CO, US
David Allen Tolliver - Pittsburgh PA, US
James Andrew Bagnell - Pittsburgh PA, US
Andrew Neil Stein - Pittsburgh PA, US
Iljung Samuel Kwak - Pittsburgh PA, US
Kristin Jean Dana - Spring Lake NJ, US
Steven Joseph Bushell - Cranston RI, US
Bartholomeus Christianus Leonardus Nabbe - Hillsboro OR, US
Milan Diebel - Hillsboro OR, US
Richard Mark Friedhoff - San Francisco CA, US

International Classification:

G06K 9/00
G06K 9/48
G06K 9/36

US Classification:

382164, 382199

Abstract:

In an exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image, organizing spatio-spectral information for the image in a matrix equation expressed by: [A][x]=[b], wherein [A] expresses values determined by a constraining relationship imposed upon the spatio-spectral information, [b] expresses recorded information for the image, and [x] expresses an unknown material/illumination component of the image, and utilizing the matrix equation in an image segregation operation.

US Patent:

8139867, Mar 20, 2012

Filed:

Dec 5, 2008

Appl. No.:

12/315642

Inventors:

Bruce Allen Maxwell - Benton ME, US
Casey Arthur Smith - Grand Junction CO, US
David Allen Tolliver - Pittsburgh PA, US
James Andrew Bagnell - Pittsburgh PA, US
Andrew Neil Stein - Pittsburgh PA, US
Iljung Samuel Kwak - Pittsburgh PA, US
Kristin Jean Dana - Spring Lake NJ, US
Steven Joseph Bushell - Cranston RI, US
Bartholomeus Christianus Leonardus Nabbe - Hillsboro OR, US
Milan Diebel - Hillsboro OR, US
Richard Mark Friedhoff - San Francisco CA, US

Assignee:

Tandent Vision Science, Inc. - San Francisco CA

International Classification:

G06K 9/48
G06K 9/00

US Classification:

382199

Abstract:

In an exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of generating spatio-spectral information for the image, defining a constraint as a function of the spatio-spectral information, and performing an optimization operation as a function of the constraint to generate an intrinsic image corresponding to the image.

US Patent:

8175390, May 8, 2012

Filed:

Mar 28, 2008

Appl. No.:

12/079878

Inventors:

Bruce Allen Maxwell - Benton ME, US
Richard Mark Friedhoff - New York NY, US
Casey Arthur Smith - Ithaca NY, US

Assignee:

Tandent Vision Science, Inc. - San Francisco CA

International Classification:

G06K 9/40

US Classification:

382190, 382199, 382155, 382224

Abstract:

In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file, identifying a boundary in the image, calculating a representation of the boundary extending to segments of the image at either side of the boundary, performing feature calculations on the representation and classifying the boundary as caused by a material change, as a function of the feature calculations.

US Patent:

8437545, May 7, 2013

Filed:

Apr 18, 2012

Appl. No.:

13/449469

Inventors:

Bruce Allen Maxwell - Benton ME, US
Casey Arthur Smith - Grand Junction CO, US
Richard Mark Friedhoff - San Francisco CA, US

Assignee:

Tandent Vision Science, Inc. - San Francisco CA

International Classification:

G06K 9/36

US Classification:

382166, 382232

Abstract:

In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, generating an approximate intrinsic estimate representation of the image as an intrinsic image corresponding to the image, and compressing the intrinsic image to provide a compressed intrinsic image.