On a lip print recognition by the pattern kernels with multiresolution architecture

Biometric systems are technologies that use unique human physical characteristics to automatically identify a person in some way, and which have sensors to pick up some physical characteristics, convert them into digital patterns, and compare them with patterns stored for personal identification. However lip print recognition has been less developed than recognition of other human physical attributes such as fingerprints, voice patterns, retinal blood vessel patterns or the face. The merit of lip print recognition by CCTV camera is to be linked with other recognition systems such as eye retina/iris and face. A new method with multiresolution architecture is proposed to recognize a lip print by pattern kernels. A set of pattern kernels is a function of some local lip print masks. This function converts the information from a lip print into digital data. Recognition in a multiresolution system is more reliable than recognition in a single-resolution system. The multiresolution architecture allows us to reduce the false recognition rate from 15% to 4.7%. This paper shows that a lip print is sufficiently useful for of biometric system measurements