C-DAC tool to detect data duplication in documents
Indian Express - Pune News line
April 3, 2011
The city-based Centre for Development of Advanced Computing (C-DAC) has come up with a tool that can help in detecting the problem of data duplication where a single individual is issued more than one copy of a document. The tool is currently being used in Aadhaar Unique Identification Number project.
The tool, Namescape, was invented by GIST research Lab of C-DAC and can help in detecting names which can be spelling variants or sound-alikes. The areas in which the tool can be used, according to the team at C-DAC, are public distribution system, election commission, IT department, passport and visa offices, banks, insurance and credit card companies and mobile phone providers.
Mahesh Kulkarni, in-charge of the project said, "Namescape can handle a large number of cases and find different names and address variants. Different spellings of a given name, such as Chaudhary which can be spelled in 68 different manners can be found easily. Regional spellings like Jyoti and Jyothi are also identified. This is especially useful in projects like Aadhaar."