Artificial Intelligence at the Post Office and the Police Department

 

by

Sargur Srihari

Department of Computer Science and Engineering

University at Buffalo, The State University of New York

Abstract

The methodology of Artificial Intelligence was first tested in toy problems and game playing, e.g., blocks world, chess and backgammon. Over the last two decades AI methodologies have found their way  into applications that are in the service of society. The talk will describe a long-term project that led to large scale deployment of systems for reading handwritten addresses on postal mail-pieces in the United States, Australia and the UK,. A brief description of the history of CEDAR,  where the work was performed, will be given.  The transition of the methodology into tools for crime scene investigation, particularly those involving questioned documents, latent fingerprints and shoe-prints , will also be described. Some contributions to statistical pattern recognition and machine learning methodologies from these applications will be highlighted.

Bio

Sargur Srihari is a SUNY Distinguished Professor in the Department of Computer Science and Engineering at the University at Buffalo, The State University of New York. He founded CEDAR, the Center of Excellence for Document Analysis and Recognition, with support from the United States Postal Service. Srihari currently teaches courses in machine learning and pattern recognition. He has  been involved in several start-up technology companies. Srihari is a Fellow of the IEEE and the International Association for Pattern Recognition. He received a B.E. in Electrical Communication Engineering from the Indian Institute of Science, Bangalore and a Ph.D. in Computer and Information Science from the Ohio State University, Columbus.