Personal Recognition by Finger-Knuckle-Print Based on Log-Gabor Filter Response

Abstract

Biometrics technique is an important and effective solution for automatic personal verification/identification. Recently, a novel hand-based biometric feature, Finger-Knuckle- Print (FKP), has attracted an increasing amount of attention. Like any other biometric identifiers, FKPs are believed to have the critical properties of universality, uniqueness and permanence for personal recognition. This paper investigates a new approach for human FKP recognition using 1D Log- Gabor filter response. We employ 1D Log-Gabor wavelet to extract the information. Thus each finger is represented by a two finger codes (real and imaginary template). Those templates (finger codes) are compared with those in the database using Hamming distance. The experimental results showed that the designed system achieves an excellent recognition rate on the Hong Kong polytechnic university (PolyU) Finger-Knuckle-Print Database. The proposed technique is computationally effective with recognition rates of 99.71% and 99.91% for verification and identification, respectively.