A mobile-based face verification system

Abstract

Intelligent mobile phones equipped with camera are very popular in human daily lives now. Face verification running on mobile phone provides not only a tool for protection of owner's authority but also an approach for verification from a distance. The combination of biometrics and telecommunication technologies possesses broad application potentials in information exchanges. However, there are also some critical issues needed solving. Usually the processing power and memory size of a mobile phone system are limited, and the acquisition images are suffered from the illumination changes. Based on the invariant property of the ratio of illumination at a pixel to its surrounding neighbor illuminations, an illumination normalization technique was analyzed and adapted to the mobile system. A dedicated scheme composed with special wavelets called Gab features was proposed for representation of human faces. The number of Gabor nodes was effectively reduced by an optimization processing. A mobile based face verification system was developed and embedded in Lenovo ET980 mobile phone. The experiments testing on FERET fafb dataset show that the performance of this system is quite well.