Neil G Alldrin

US Patent:

8452109, May 28, 2013

Filed:

Jan 11, 2010

Appl. No.:

12/655930

Inventors:

Neil Alldrin - Pittsburgh PA, US
Kshitiz Garg - Pittsburgh PA, US
Andrew Neil Stein - Pittsburgh PA, US
Kristin Jean Dana - Spring Lake NJ, US
Bruce Allen Maxwell - Benton ME, US
Casey Arthur Smith - Grand Junction CO, US
Youngrock Yoon - Knoxville TN, US
Besma Roui Abidi - San Francisco CA, US

Assignee:

Tandent Vision Science, Inc. - San Francisco CA

International Classification:

G06K 9/62

US Classification:

382225, 382159, 382165, 382224, 382190, 345 20, 345 63, 345 77

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, assembling a feature vector for the image file, the feature vector containing information regarding a likelihood that a selected pair of regions of the image file are of a same intrinsic characteristic, for example, a same texture, providing a classifier derived from a computer learning technique, computing a classification score for the selected pair of regions of the image file, as a function of the feature vector and the classifier and classifying the regions as being of the same intrinsic characteristic, as a function of the classification score.

US Patent:

8478029, Jul 2, 2013

Filed:

May 26, 2009

Appl. No.:

12/454926

Inventors:

David Allen Tolliver - Pittsburgh PA, US
Kristin Jean Dana - Spring Lake NJ, US
Andrew Neil Stein - Pittsburgh PA, US
Neil Alldrin - Pittsburgh PA, US

Assignee:

Tandent Vision Science, Inc. - Dan Francisco CA

International Classification:

G06K 9/00
G06K 9/40

US Classification:

382162, 382254

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, forming a set of selectively varied representations of the image file and performing an image segregation operation on at least one preselected representation of the image of the image file, to generate intrinsic images corresponding to the image. According to a feature of the exemplary embodiment of the present invention, the selectively varied representations comprise multi-resolution representations such as a scale-spaced pyramid of representations. In a further feature of the exemplary embodiment of the present invention, the intrinsic images comprise a material image and an illumination image.

US Patent:

8483480, Jul 9, 2013

Filed:

Dec 18, 2009

Appl. No.:

12/653846

Inventors:

Casey Arthur Smith - Grand Junction CO, US
Andrew Neil Stein - Pittsburgh PA, US
Neil Alldrin - Pittsburgh PA, US

Assignee:

Tandent Vision Science, Inc. - San Francisco CA

International Classification:

G06K 9/34
G06K 9/18
G06K 9/66
G06K 9/46
G06K 9/48

US Classification:

382173, 382185, 382190, 382191, 382195, 382199

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 illumination image from the image; and factoring the illumination image to generate a diffuse illumination image and a harsh shadow illumination image.

US Patent:

8577135, Nov 5, 2013

Filed:

Nov 17, 2009

Appl. No.:

12/590949

Inventors:

Kshitiz Garg - Pittsburgh PA, US
Neil Alldrin - Pittsburgh PA, US

Assignee:

Tandent Vision Science, Inc. - San Francisco CA

International Classification:

G06K 9/00
G06K 9/62

US Classification:

382165, 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 depicting an image, in a computer memory, assembling a feature vector for the image file, the feature vector containing information regarding a likelihood that a selected region of the image file is specular, providing a classifier derived from a computer learning technique, computing a classification score for the selected region of the image file, as a function of the feature vector and the classifier and classifying the region as being specular, as a function of the classification score.

US Patent:

20100278448, Nov 4, 2010

Filed:

Apr 30, 2009

Appl. No.:

12/387258

Inventors:

Richard Mark Friedhoff - San Francisco CA, US
Casey Arthur Smith - Grand Junction CO, US
Bruce Allen Maxwell - Benton ME, US
Neil Alldrin - Pittsburgh PA, US
Steven Joseph Bushell - Cranston RI, US

Assignee:

Tandent Vision Science, Inc. - San Francisco CA

International Classification:

G06K 9/40
G06K 9/36

US Classification:

382274, 382282

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, performing an image segregation operation on the image file to generate a set of intrinsic images corresponding to the image, modifying a preselected one of the set of intrinsic images according to a set of preselected operations and merging the modified one of the set of intrinsic images relative to the set of intrinsic images to provide a modified output image.

US Patent:

20110222742, Sep 15, 2011

Filed:

Mar 10, 2010

Appl. No.:

12/661052

Inventors:

Andrew Neil Stein - Pittsburgh PA, US
Neil Alldrin - Pittsburgh PA, US
Kshitiz Garg - Pittsburgh PA, US

Assignee:

Tandent Vision Science, Inc. - San Francisco CA

International Classification:

G06K 9/00

US Classification:

382118, 382167

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, identifying shadow edges in the image, computing gradient information for the image and modifying the gradient information relative to the shadow edges for improved performance of computer functionality in an image processing operation.

US Patent:

20130156315, Jun 20, 2013

Filed:

Feb 1, 2013

Appl. No.:

13/757143

Inventors:

Casey Arthur Smith - Grand Junction CO, US
Bruce Allen Maxwell - Benton ME, US
Neil Alldrin - Pittsburgh PA, US
Steven Joseph Bushell - Cranston RI, US

Assignee:

Tandent Vision Science, Inc. - San Francisco CA

International Classification:

G06T 5/00

US Classification:

382173

Abstract:

An automated, computerized method is provided for processing an image. The method includes the steps of providing an image file depicting an image, in a computer memory, performing an image segregation operation on the image file to generate a set of intrinsic images corresponding to the image, modifying a preselected one of the set of intrinsic images according to a set of preselected operations and merging the modified one of the set of intrinsic images relative to the set of intrinsic images to provide a modified output image.

US Patent:

20140314318, Oct 23, 2014

Filed:

Jul 1, 2014

Appl. No.:

14/321141

Inventors:

- San Francisco CA, US
Casey Arthur Smith - Grand Junction CO, US
Bruce Allen Maxwell - Pittsfield ME, US
Neil Alldrin - Pittsburgh PA, US
Steven Joseph Bushell - Cranston RI, US

International Classification:

G06T 5/00
G06T 5/50
G06T 7/00

US Classification:

382173

Abstract:

An automated, computerized method is provided for processing an image. The method includes the steps of providing an image file depicting an image, in a computer memory, performing an image segregation operation on the image file to generate a set of intrinsic images corresponding to the image, modifying a preselected one of the set of intrinsic images according to a set of preselected operations and merging the modified one of the set of intrinsic images relative to the set of intrinsic images to provide a modified output image.