Search

Rakesh Kandpal Phones & Addresses

  • Fremont, CA
  • Milpitas, CA
  • Sunnyvale, CA

Publications

Us Patents

Image Quality Assessment And Improvement For Performing Optical Character Recognition

View page
US Patent:
20190050675, Feb 14, 2019
Filed:
Sep 21, 2018
Appl. No.:
16/138669
Inventors:
- Mountain View CA, US
Rakesh KANDPAL - Mountain View CA, US
Priya KOTHARI - Mountain View CA, US
Sheldon PORCINA - Alberta, CA
Pavlo MALYNIN - Edmonton, CA
International Classification:
G06K 9/62
G06K 9/00
G06K 9/18
Abstract:
Techniques are disclosed for performing optical character recognition (OCR) by assessing and improving quality of electronic documents to perform the OCR. For example a method for identifying information in an electronic document includes obtaining a reference image of the electronic document, distorting the reference image by adjusting different sets of one or more parameters associated with a quality of the reference image to generate a plurality of distorted images, analyzing each distorted image to detect the adjusted set of parameters and corresponding adjusted values, determining an accuracy of detection of the set of parameters and the adjusted values, and training a model based at least on the plurality of distorted images and the accuracy of the detection, wherein the trained model determines at least a first technique for adjusting a set of parameters in a second image to prepare the second image for optical character recognition.

Image Quality Assessment And Improvement For Performing Optical Character Recognition

View page
US Patent:
20180121756, May 3, 2018
Filed:
Oct 28, 2016
Appl. No.:
15/337285
Inventors:
- Mountain View CA, US
Rakesh KANDPAL - Mountain View CA, US
Priya KOTHARI - Mountain View CA, US
Sheldon PORCINA - Alberta, CA
Pavlo MALYNIN - Alberta, CA
International Classification:
G06K 9/62
G06K 9/18
G06K 9/00
Abstract:
Techniques are disclosed for performing optical character recognition (OCR) by assessing and improving quality of electronic documents to perform the OCR. For example a method for identifying information in an electronic document includes obtaining a reference image of the electronic document, distorting the reference image by adjusting different sets of one or more parameters associated with a quality of the reference image to generate a plurality of distorted images, analyzing each distorted image to detect the adjusted set of parameters and corresponding adjusted values, determining an accuracy of detection of the set of parameters and the adjusted values, and training a model based at least on the plurality of distorted images and the accuracy of the detection, wherein the trained model determines at least a first technique for adjusting a set of parameters in a second image to prepare the second image for optical character recognition.
Rakesh Kandpal from Fremont, CA Get Report