"For years, we have worked with
the State University of New York (SUNY) at Buffalo to improve the technology
we use to recognize handwritten addresses. While the technology we use
to electronically read typed or printed addresses has been very successful,
we have had only limited success in recognizing handwritten addresses
because there is such variation in styles of handwriting. When we first
deployed them, Remote Computer Readers could fully resolve about one-third
of the printed images they received but less than two percent of the handwritten
ones. For handwritten mail, the Readers could partially resolve some of
the five-digit ZIP Code mail. Then we conducted a pilot test of an early
version of handwritten address interpretation technology. This early version
could fully barcode about one of every eight handaddressed images it received.
This year, our research has started to pay off as we began deploying the
latest software and equipment designed to electronically read, decipher,
and automatically barcode many of the billions of pieces of handwritten
addressed mail we process each year."