An article in Discover magazine reports UB computer
scientist Yi Tang and colleagues have developed a way to automate
footwear forensics to make it easier to match shoe tread patterns
obtained from crime scenes. The article notes Tang compared 300
real crime-scene prints and tried to match them with a database of
2,660 known prints and found that 99 percent of the time, the
correct match was within the top 5 percent of results.