Fuzzy CMAC Takes a Bite Out of Crime

Every bullet has telltale marks identifying the gun from which it was fired. Yet, until recently, using one as evidence of a crime was a time-consuming task. Comparing the "striations" of a crime scene bullet with a sample fired by a suspect's gun had to be done visually, a one-day job. Intelligent Automation (IAI; Rockville MD) has developed a tool, called RotoScan, that digitizes and compares striations and returns the results within 30 minutes. RotoScan is the chief component of the DRUGFIRE® system, a ballistics analysis system developed and marketed by Mnemonic Systems, Inc., a wholly owned subsidiary of Nichols Research. Used by the FBI as well as by domestic and foreign crimelabs, DRUGFIRE has solved over 1,000 crimes and racked up more than $1.5 million in sales.

RotoScan includes an image capturing device and a high-speed, fuzzy logic-driven neural network, called Fuzzy CMAC, first developed for BMDO for potential applications in missile control, target classification, and satellite control. The fuzzy CMAC compares the digital images of the two bullets and determines if they match. At present, the system compares two dimensions, but IAI is developing a 3-D model that will be available in about one year. In addition to crime solving, IAI expects that the Fuzzy CMAC technology will have uses in the medical arena, where its can provide 3-D microscopic images more quickly and accurately than current technologies. The company welcomes inquires from interested medical firms.