Generating a biometric feature from another is a challenging research topic. Especially, generating face characteristics from only fingerprints is a very interesting and attractive challenge for applications. It is thought that this might be used in many biometric applications. This challenging topic of generating face parts from only fingerprints has been recently introduced for the first time by the authors in the studies. The relationships among biometric features of the faces and fingerprints were experimentally showed in the studies.

This project presents a new and intelligent approach to predict face masks including eye, nose, mouth and face border from fingerprints without any information about faces. In order to achieve that a number of face parts have been used to establish the relationships among Fs&Fs.
These faces parts are:

  • generating the face borders [1],
  • the face contours including face border and ears [2],
  • the face models including eyebrows, eyes and mouth [3],
  • the inner face masks including eyes, nose and mouth [4],
  • the face parts including eyes, nose, mouth and ears [5],
  • the face models including eyes, nose, mouth, ears and face border [6],
  • the face parts including eyebrows, eyes, nose, mouth and ears [7],
  • only eyes [8] and
  • the face parts including eyebrows, eyes and nose [9]

These parts are predicted with the presented methods from only fingerprints without any need for face information or images introduced in the studies. The studies have experimentally demonstrated that there are close relationships among faces and fingerprints.

In order to achieve this research project easilly and efectivelly, a novel AISFF is designed, implemented and introduced for generating the face masks from fingerprints without any need for the face information. It is demonstrated that it is possible to achieve an unknown biometric feature from a known biometric feature, successfully.

The proposed approach may be used for efficiently generating any biometric feature from other biometric feature with minor modifications.

This concept might be applied to other applications. It is hoped that this approach would lead to create new concepts, research areas, and especially new applications in the field of biometrics.