PERSONAL IDENTIFICATION SYSTEM USING MULTIPLE PARAMETERS HAVING LOW CROSS-CORRELATION

摘要

A personal identification system for use in security and various other types of pattern matching application provides accurate recognition of a known person. This system uses a large quantity of course but inexpensive sensors (100) to create a profile of a person seeking to enter the controlled space (104). The sensors measure different statistically independent characteristics of the person, such as height, weight, stride, voice tembre, and time to perform various functions. The measurement are used to search a data base patterns related to admissible individuals (108). Active agent methods are used to support learning and adaptation of the sensor set to address sensor drift and changes over time. A combination of many parameters will identify a person with very low probability of both false negative and false positive errors (110).