ABOUT THE PROJECT

When the literature has been reviewed, there are thousands of articles available on fingerprints and faces.

For fingerprints; there are a number of steps to be followed on selecting the image area, detecting the singular points, enhancing, improving and thinning the fingerprint image, extracting the minutiae points and calculating their parameters, eliminating the false minutiaes, properly representing the fingerprint images with their feature sets, recording the feature sets into a database, matching the feature sets and testing the system.

For face recognition; there are also many steps on detecting faces in complicated backgrounds, localizing faces by extracting features from the face regions, identifying faces, verifying faces, or classifying faces.

Most of the efforts and studies in biometrics recently have focused on improving the accuracy and processing time of the biometric systems, designing more intelligent, hybrid and complex systems, and developing effective and robust techniques and algorithms for biometric applications in recent years.

Opposite to those studies in the literature, we have focused on investigating relationships among biometric features especially fingerprints and faces in this work. In order to achieve this relationship, we first time introduced an intelligent system of which is capable of establishing the relationships among faces and fingerprints (Fs&Fs) in this project.

Achieving a biometric feature of a person from the other biometric feature of the same person is a challenging idea. It is also desirable and useful transformation for many applications. It is hard to believe that there is really a relationship among biometric features because of their characteristics such as their uniqueness. It was also difficult as well as challenging study for us to start such a research.
From the literature, we investigated biological and physiological evidences regarding to the relationships among biometric features to support this study. The evidences given below help us to believe that it is worth investigating these relationships.

1. It is known that the phenotype of the biological organism is uniquely determined by the interaction of a specific genotype and a specific environment. Physical appearances of faces and fingerprints are also a part of an individual’s phenotype. In the case of fingerprints, the genes determine the general characteristics of the pattern. In dermatoglyphics studies, the maximum generic difference among fingerprints was found among individuals of different races. Unrelated persons of the same race have very little generic similarity in their fingerprints, parent and child have some generic similarity as they share half of the genes, siblings have more similarity and the maximum generic similarity is observed in the identical twins, which is the closest genetic relationship.

2. Some of the scientists in biometrics have focused on analyzing the similarities in fingerprint minutiae patterns in identical twin fingers. They absolutely confirmed that the identical twin fingerprints have a large class correlation. In addition to this class correlation, correlation based on other generic attributes of the fingerprint such as ridge count, ridge width, ridge separation and ridge depth was also found to be significant in identical twins.

3. In the case of faces, the situation is very similar with the circumstances of fingerprints. The general characteristics of the face patterns were determined by the genes and the maximum generic difference among faces has been found among individuals of different races. A very little generic similarity was found in the faces of unrelated persons of the same race. Parent and child have some generic similarity as they share half of the genes, siblings have more similarity and the maximum generic similarity is observed in the identical twins, which is the closest genetic relationship.

4. A number of studies have especially focused on analysing the significant correlation among faces and fingerprints of the identical twins. The large correlation among biometrics of identical twins was repeatedly indicated in the literature by declaring that identical twins would cause vulnerability problems in security applications. The similarity measure of identical twin fingerprints is reported as 95%. The reason of this high degree similarity measure was explained in some studies as follows: identical twins have exactly identical DNA except for the generally undetectable micro mutations that begin as soon as the cell starts dividing. Fingerprints of identical twins start their development from the same DNA, so they show considerable generic similarity.

5. Our hypothesis starts from this point that if similar faces or fingerprints have close relationships; we think that there must be close relationships among fingerprints and faces.

The results achieved from our studies have shown that this new hypothesis could be true. This web site would help us to prove this hypothesis worldwide with the help of researchers around the world.

The recent results have experimentally proved that predicting face masks partially and fully from fingerprints without having any information about faces are very promising.

Please visit the links (LiveTest and RecentResults) and let us know your opinions about the tests to support our hypothesis.