Search

Eduardo Kellerman Phones & Addresses

  • Ithaca, NY
  • 1047 Schuyler St, Endicott, NY 13760 (607) 754-4878
  • 213 Buttermilk Ln, Ithaca, NY 14850 (607) 754-4878

Work

Position: Educator

Education

Degree: High school graduate or higher

Publications

Us Patents

Method And Apparatus For Evaluating A Confidence Level Of A Decoded Barcode

View page
US Patent:
6648230, Nov 18, 2003
Filed:
May 22, 2002
Appl. No.:
10/154241
Inventors:
Eduardo Kellerman - Endicott NY
Richard C. Van Hall - Owego NY
Assignee:
Lockheed Martin Corporation - Bethesda MD
International Classification:
G06K 720
US Classification:
2354625, 23546211, 23546201, 235375, 705408, 705404, 705410
Abstract:
A method and apparatus for evaluating a confidence level of a decoded barcode value is disclosed. A digit score is assigned to a digit within a barcode. When decoding the barcode, if a deduction is required to decode the digit, then the digit score for the digit is reduced accordingly. After all the digits within the barcode have been decoded, a total score of a decoded barcode value can be determined by adding all the digit scores for all the digits within the barcode. The total score of the decoded barcode value is reduced if a checksum is used to ascertain the value of any digit within the barcode. The decoded barcode value can be accepted only if the total score exceeds a predetermined value.

Real-Time Recognition Of Mixed Source Text

View page
US Patent:
20070065003, Mar 22, 2007
Filed:
Sep 21, 2005
Appl. No.:
11/232260
Inventors:
Eduardo Kellerman - Endicott NY, US
Rosemary Paradis - Vestal NY, US
Alfred Rundle - Endwell NY, US
International Classification:
G06K 9/62
G06K 9/00
US Classification:
382159000, 382181000
Abstract:
Methods and computer program products are disclosed for the real-time classification of text from a region of interest within an image sample. A feature extractor extracts feature data associated with a plurality of region features from the region of interest. The plurality of region features are selected as to minimize the time necessary for feature extraction. A neural network preclassifier selects one of a plurality of associated source classes for the region of interest according to the extracted feature data. A plurality of classification systems are each associated with one of the plurality of source classes. Each of the plurality of classification systems are operative to classify individual characters within the region of interest when the associated source class of the classification system is selected.

Printed Circuit Board With Vias At Fixed And Selectable Locations

View page
US Patent:
47000163, Oct 13, 1987
Filed:
May 16, 1986
Appl. No.:
6/863850
Inventors:
Robert B. Hitchcock - Wappingers Falls NY
Eduardo Kellerman - Endicott NY
John P. Koons - Apalachin NY
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
H05K 100
US Classification:
174 685
Abstract:
A printed circuit board for electric circuits is formed of plural layers of electrical conductors and includes through holes and vias arranged in a regular pattern along points of a grid laid out along othorgonal axes of a Cartesian coordinate system. Electrical components such as circuit chips and discrete components are to be mounted to the through holes, while the vias connect electrical conductors of different layers. Conductors of a layer are grouped together as multiple-conductor channels which are routed among the through holes and the vias to make electrical connections among the electrical components. An additional via can be entered in a central portion of a grid cell by rerouting conductors of channels in the cell through arcuate segments, thereby permitting connection between conductors of channels on different layers while preserving the original grid pattern of through holes and vias.
Eduardo W Kellerman from Ithaca, NYDeceased Get Report