A Toolset to facilitate transparent exchange and querying of digitizeddocumen

Digitizing paper records facilitates efficient storage and lookup of information. It is

o,lten necessary to support advanced keyword-based querying features that allow

extraction of specific information and filtering of digitized documents. However, this

often requires manual intervention since records might have vastly different formats

even though they essentially contain the same information. This makes digitization

time consuming and increases costs for organizations that want to digitize their

records. This project will develop tools to scan a group of paper records serving a

similar function, e.g., representing invoices, and automatically indexing them through a

common set of metadata. This metadata would allow access and querying of digitized

records in a manner that is transparent to the formatting differences of the underlying

paper records. Automating this task can result in significant cost savings for those

undertaking digitization efforts.

Faculty Supervisor:

Behrouz Far

Student:

Partner:

IDOCZ

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

University of Calgary

Program:

Accelerate

Current openings

Find the perfect opportunity to put your academic skills and knowledge into practice!

Find Projects