Computing That Serves

Developing Multilingual OCR at Google: A Researcher's Perspective


Thursday, December 14, 2017 - 11:00am


Ashok Popat


Bill Barrett

Colloquium presented by Ashok Popat, Research Scientist at Google Inc.

Thursday, December 14, 2017 at 11:00 A.M.

Location: 1170 TMCB

Optical character recognition (OCR) is an old problem but continues to be a limiting factor in large-scale digitization efforts.
In this talk I'll describe the approach my team has been following in Google Research: our teams origins in the Translate project, and will describes some lessons learned (and some things I think I'm learning now).


Ashok C. Popat received the SB and SM degrees from the Massachusetts Institute of Technology in Electrical Engineering in 1986 and 1990, and the PhD from the MIT Media Lab in 1997. He is a Senior Staff Research Scientist and manager at Google in Mountain View, California. Prior to joining Google in 2005 he worked at Xerox PARC for 8 years, as a researcher and later as a research area manager. Between 2002 and 2005 he was also a consulting assistant professor of Electrical Engineering at Stanford, where he taught a course "Electronic documents: paper to digital." He has also worked at Motorola, Hewlett Packard, PictureTel, and the EPFL in Switzerland. His areas of interest include signal processing, data compression, machine translation, and pattern recognition. He enjoys running, skiing, sailing, hiking, and spending time with his wife and two daughters.