This is an archived version of CCC's website. Please visit the new ccc website for the latest information.

Relevant Links

Link to Original Paper
Media Contact


handwriting, OCR, digital libraries, text recognition


feed icon

feed icon

feed icon


Using Handwriting Styles to Understand Historic Documents

The best text recognition tools struggle to reliably identify text in handwritten documents. By analyzing handwriting styles, Dr. Venu Govindaraju is working to improve the performance for digitizing text in handwritten documents. At the same time, his techniques could enable forensic analysis of handwriting to determine the author of documents whose writers are still unknown. Unlike other forms of optical character recognition, Dr. Govindaraju's technique doesn't rely on context or grammar rules, it can apply to all languages.

This would be a boon for historians, who currently painstakingly analyze documents to try to figure out if Madison really was the author of a hastily scribbled note, for instance. It might also have applications in law enforcement forensics, or even personal use for those of us looking to digitize our handwritten records. Medical records could also use this to handle text from different doctors with different handwriting styles, yet still accurately and speedily digitize the info.


Venu Govindaraju (SUNY at Buffalo)

Institution(s) (that have supported the research):
SUNY at Buffalo, National Science Foundation


Current Highlight | Past Highlights

Computing Research Highlight of the Week is a service of the Computing Community Consortium and the Computing Research Association designed to highlight some of the exciting and important recent research results in the computing fields. Each week a new highlight is chosen by CRA and CCC staff and volunteers from submissions from the computing community. Want your research featured? Submit it!.