HP Labs India

Intelligent Document Cleanup

Document cleanup is a necessary preprocessing step for effective digitization of paper. Our research deals with the whole gamut of issues related to document cleanup including: How do you determine the type of noise that is present in a document? How do you optimize the cleanup of the documents to make them more suitable for downstream processing? How do you evaluate the goodness of the cleanup that has been carried out on a document? Our aim is to come up with a holistic approach for document cleanup that would work across the whole range of documents with all types of potential noise.

Paper Widgets

Enterprises have significant problems processing paper documents. There is significant amount of time and effort spent in terms of transcribing information from paper documents into IT systems. Our research here tries to come up with new ways to alleviate some of these problems. It includes work on new forms of machine readability and associated document image processing to help detect and deal with these new forms. We feel the research can ultimately have significant impact in terms of enterprise scanning workflows.

Secure Print Workflows

Typically the paper document is the weakest security link in enterprise’s information flows. The research on secure print workflows aims to provide the same level of security to the printing process that one has in terms of access to digital information in an enterprise. The research aims to come up with methods by which unauthorized printing can be prevented and even when it has been carried out can be subsequently detected.

 

Publications

Click here for recent Publications listing

This page was last updated on March 19, 2010