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.


  dupI dupII fafb fafc
arl_cor 0.363 0.171 0.827 0.052
arl_ef 0.410 0.222 0.797 0.186
ef_hist_dev_ang 0.341 0.124 0.701 0.072
ef_hist_dev_anm 0.446 0.209 0.774 0.237
ef_hist_dev_l1 0.350 0.132 0.772 0.258
ef_hist_dev_l2 0.331 0.137 0.716 0.041
ef_hist_dev_md 0.422 0.167 0.741 0.232
ef_hist_dev_ml1 0.305 0.128 0.733 0.392
ef_hist_dev_ml2 0.346 0.128 0.772 0.309
excalibur 0.414 0.197 0.794 0.216
mit_mar_95 0.338 0.171 0.834 0.155
mit_sep_96 0.576 0.342 0.948 0.320
umd_mar_97 0.472 0.209 0.962 0.588
usc_mar_97 0.591 0.521 0.950 0.820

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/".