Automated Separation of Handwritten and Machine-Printed Images

Automated Separation of Handwritten and Machine-Printed Images

Method of Distinguishing Handwritten and Machine-Printed Images

This language-agnostic technology automatically characterizes documents as handwritten, machine-printed, or unknown, enabling quick scoring and storing of images. The technology can be useful in maximizing the accuracy of optical character recognition (OCR) applications, resulting in the capability to more accurately search and sort large document collections.

 

Abstract: 

Click to view PDFs of these patents on the US Patent and Trademark Office website: Patent #7,027,514

applications: 
  • Document image collection
  • Document indexing
  • Records management
Patent Number: 
7,072,514
Patent Issue Date: 
July 4, 2006
Email: 
tech_transfer@nsa.gov
Lab Representatives
Share to Facebook Share to Twitter Share to Google Plus Share to Linkedin