James R Rinker

US Patent:

7043079, May 9, 2006

Filed:

Jun 26, 2002

Appl. No.:

10/180800

Inventors:

Henrique S. Malvar - Sammamish WA, US
Patrice Y. Simard - Bellevue WA, US
James Russell Rinker - Kirkland WA, US

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

G06K 9/46

US Classification:

382195, 382264, 382283, 348586, 358448

Abstract:

A system and method facilitating image smoothing is provided. The invention includes an image processor having an image receptor and an image smoother. The invention provides for the image smoother to alter the value of a don't care pixel based, at least in part, upon a weighted average of care pixels.

US Patent:

7110596, Sep 19, 2006

Filed:

Jun 26, 2002

Appl. No.:

10/180771

Inventors:

Patrice Y. Simard - Bellevue WA, US
Erin L. Renshaw - Kirkland WA, US
James Russell Rinker - Kirkland WA, US

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

G06K 9/00
G06K 9/36

US Classification:

382166, 382232, 382243, 35842601

Abstract:

A system and method facilitating document image compression utilizing a mask separating a foreground of a document image from a background is provided. The invention includes a pixel energy analyzer adapted to partition regions into a foreground and background. The invention further provides for a merge region component adapted to attempt to merge regions if the merged region would not exceed a threshold energy. Merged regions are partitioned into a new foreground and new background. Thereafter, a mask storage component stores the partitioning information in a binary mask.

US Patent:

7120297, Oct 10, 2006

Filed:

Jun 26, 2002

Appl. No.:

10/180169

Inventors:

Patrice Y. Simard - Bellevue WA, US
Erin L. Renshaw - Kirkland WA, US
James Russell Rinker - Kirkland WA, US
Henrique S. Malvar - Sammamish WA, US

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

G06K 9/00
G06K 9/36

US Classification:

382166, 382232, 382243, 35842601

Abstract:

Systems and methods for encoding and decoding document images are disclosed. Document images are segmented into multiple layers according to a mask. The multiple layers are non-binary. The respective layers can then be processed and compressed separately in order to achieve better compression of the document image overall. A mask is generated from a document image. The mask is generated so as to reduce an estimate of compression for the combined size of the mask and multiple layers of the document image. The mask is then employed to segment the document image into the multiple layers. The mask determines or allocates pixels of the document image into respective layers. The mask and the multiple layers are processed and encoded separately so as to improve compression of the document image overall and to improve the speed of so doing. The multiple layers are non-binary images and can, for example, comprise a foreground image and a background image.

US Patent:

7251644, Jul 31, 2007

Filed:

Aug 2, 2004

Appl. No.:

10/909534

Inventors:

Paul Viola - Kirkland WA, US
Hiu Chung Law - East Lansing MI, US
James Rinker - Kirkland WA, US

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

G06F 17/30
G06F 7/00

US Classification:

707 1, 707 5

Abstract:

The present invention relates to a method of automatically processing an electronic document for routing over a computer network. The method includes recognizing text in the document to identify a candidate address, accessing a collection of potential destinations and comparing the candidate address to the collection of potential destinations to determine a destination for the document.

US Patent:

7376266, May 20, 2008

Filed:

Aug 16, 2006

Appl. No.:

11/465087

Inventors:

Erin L. Renshaw - Kirkland WA, US
James Russell Rinker - Kirkland WA, US
Henrique Malvar - Sammamish WA, US

Assignee:

Microsoft Corporation - Redmond CA

International Classification:

G06K 9/00
G06K 9/36

US Classification:

382166, 382232, 382243, 35842601

Abstract:

Systems and methods for encoding and decoding document images are disclosed. Document images are segmented into multiple layers according to a mask. The multiple layers are non-binary. The respective layers can then be processed and compressed separately in order to achieve better compression of the document image overall. A mask is generated from a document image. The mask is generated so as to reduce an estimate of compression for the combined size of the mask and multiple layers of the document image. The mask is then employed to segment the document image into the multiple layers. The mask determines or allocates pixels of the document image into respective layers. The mask and the multiple layers are processed and encoded separately so as to improve compression of the document image overall and to improve the speed of so doing. The multiple layers are non-binary images and can, for example, comprise a foreground image and a background image.

US Patent:

7392472, Jun 24, 2008

Filed:

Apr 25, 2002

Appl. No.:

10/133939

Inventors:

Patrice Y. Simard - Belleveue WA, US
James Russell Rinker - Kirkland WA, US

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

G06F 17/00

US Classification:

715243, 715255

Abstract:

A system and method facilitating layout analysis is provided. The invention includes a layout analyzer having a connected component organizer, a connected joiner, a word organizer and a word joiner. The invention provides for the connected component organizer to organize connected components based upon color, horizontal position and/or vertical position. The invention provides for the connected component joiner to join connected components based, at least in part, upon color, vertical position, horizontal position, a distance between the connected components, height of the connected components and/or width of the connected components. The word organizer organizes words and the word joiner joins words into lines. The joining of words into lines can cause the connected component joining to attempt to further join connected components into words.

US Patent:

7397952, Jul 8, 2008

Filed:

Nov 23, 2005

Appl. No.:

11/286622

Inventors:

Henrique S. Malvar - Sammamish WA, US
Patrice Y. Simard - Bellevue WA, US
James Russell Rinker - Kirkland WA, US

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

G06K 9/46

US Classification:

382195, 382264, 382283, 348586, 358448

Abstract:

A system and method facilitating image smoothing is provided. The invention includes an image processor having an image receptor and an image smoother. The invention provides for the image smoother to alter the value of a don't care pixel based, at least in part, upon a weighted average of care pixels.

US Patent:

7499588, Mar 3, 2009

Filed:

May 20, 2004

Appl. No.:

10/850335

Inventors:

Charles E. Jacobs - Bellevue WA, US
James R. Rinker - Kirkland WA, US
Patrice Y. Simard - Bellevue WA, US
Paul A. Viola - Kirkland WA, US

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

G06K 9/18

US Classification:

382182, 382173, 382229

Abstract:

A global optimization framework for optical character recognition (OCR) of low-resolution photographed documents that combines a binarization-type process, segmentation, and recognition into a single process. The framework includes a machine learning approach trained on a large amount of data. A convolutional neural network can be employed to compute a classification function at multiple positions and take grey-level input which eliminates binarization. The framework utilizes preprocessing, layout analysis, character recognition, and word recognition to output high recognition rates. The framework also employs dynamic programming and language models to arrive at the desired output.