Justin K Romberg from 740 E Lake Dr, Decatur, GA 30030, age 49, Phone: 404 219-4906

Document Image Decoding Systems And Methods Using Modified Stack Algorithm
view source
US Patent:

7167588, Jan 23, 2007
Filed:

Aug 9, 2002
Appl. No.:

10/215041
Inventors:

Daniel H. Greene - Sunnyvale CA, US
Justin Romberg - Houston TX, US
Ashok C. Popat - San Carlos CA, US
Assignee:

Xerox Corporation - Stamford CT
International Classification:

G06K 9/72
US Classification:

382229
Abstract:

Methods and systems for document image decoding incorporating a Stack algorithm improve document image decoding. The application of the Stack algorithm is iterated to improve decoding. A provisional weight is determined for a partial path to reduce template matching. In addition, semantically equivalent hypotheses are identified to reduce redundant hypotheses.

Document Image Decoding Systems And Methods Using Modified Stack Algorithm
view source
US Patent:

20040028278, Feb 12, 2004
Filed:

Aug 9, 2002
Appl. No.:

10/215090
Inventors:

Daniel Greene - Sunnyvale CA, US
Justin Romberg - Houston TX, US
Ashok Popat - San Carlos CA, US
Assignee:

XEROX CORPORATION - Stamford CT
International Classification:

G06K009/62
G06K009/74
US Classification:

382/228000, 382/229000
Abstract:

Methods and systems for document image decoding incorporating a Stack algorithm improve document image decoding. The application of the Stack algorithm is iterated to improve decoding. A provisional weight is determined for a partial path to reduce template matching. In addition, semantically equivalent hypotheses are identified to reduce redundant hypotheses.

Methods And Apparatus For Imaging Of Layers
view source
US Patent:

20190050669, Feb 14, 2019
Filed:

Aug 9, 2018
Appl. No.:

16/059144
Inventors:

- Cambridge MA, US
- Atlanta GA, US
Ramesh Raskar - Cambridge MA, US
Alireza Aghasi - Chamblee GA, US
Justin Romberg - Decatur GA, US
International Classification:

G06K 9/46
G06K 9/20
G06K 9/00
Abstract:

A sensor may measure light reflecting from a multi-layered object at different times. A digital time-domain signal may encode the measurements. Peaks in the signal may be identified. Each identified peak may correspond to a layer in the object. For each identified peak, a short time window may be selected, such that the time window includes a time at which the identified peak occurs. A discrete Fourier transform of that window of the signal may be computed. A frequency frame may be computed for each frequency in a set of frequencies in the transform. Kurtosis for each frequency frame may be computed. A set of high kurtosis frequency frames may be averaged, on a pixel-by-pixel basis, to produce a frequency image. Text characters that are printed on a layer of the object may be recognized in the frequency image, even though the layer is occluded.