Can we use minor finger knuckle images to identify humans?

Biometric identification using finger knuckle imaging has generated lot of promises with interesting applications in forensics and remote biometrics. Prior efforts in the biometrics literature have only investigated the `major´ finger knuckle patterns that are formed on the finger surface joining proximal phalanx and middle phalanx bones. This paper investigates the possible use of `minor´ finger knuckle patterns which are formed on the finger surface joining distal phalanx and middle phalanx bones. The `minor´ or `upper´ finger knuckle patterns can either be used as independent biometric patterns or employed to improve the performance from the major finger knuckle patterns. This paper investigates a completely automated approach for the `minor´ finger knuckle identification by developing steps of region of interest segmentation, image normalization, enhancement and robust matching to accommodate image variations. Comparative experimental results are presented for matching the normalized `minor´ finger knuckle images using LBP, ILBP and 1D log Gabor filter. The efforts to develop automated `minor´ finger knuckle patterns achieve promising results, with 1.04% equal error rate on the database of 202 subjects, and illustrate its simultaneous use to improve the performance for conventional finger knuckle identification.