Identification Performance : Cumulative Match Characteristic
The table shows for each institution and study the fraction
of probes whose gallery match was top ranked. This is effectively
the performance on forced identification (i.e. best guess). The
numbers are links to the full cumulative match characteristic
as a gif image.
The C++ source code and the linux binaries used to obtain
these results are archived here.
To use this code extract the source tree using
"tar zxf perf.tgz", then edit the path in the top level "Makefile",
execute "make depend" and finally "make install". The final exeutables are in "bin/".