What is biometrics?

Biometrics refers to measurement and statistical analysis of people’s unique physical and behavioral characteristics for verification and identification purposes. A biometric system is mainly composed of acquisition, feature extraction and comparison modules.

During acquisition, the biometric trait of an individual to be recognized is collected via biometric sensors. The data can be captured under various conditions: controlled or uncontrolled environment, with or without subject knowledge or cooperation, close by or from a distance, indoor or outdoor, etc. These factors can introduce huge variations in the biometric samples which in return can deteriorate the matching performance.

In the feature extraction step, the collected raw data is processed to reduce the data dimensionality while preserving the identity information. Features are expected to be invariant to different acquisition conditions. Finally, the extracted features are compared against the template set in the database either for identification or verification.

Previously, the best features for a biometric recognition task were carefully and mostly manually crafted by researchers; but recently, instead of being engineered, they are automatically learned using deep neural networks. For this reason, there is no more a clear distinction between feature extraction and matching modules, since they are incorporated in a single network.

Research on Biometrics

The research in biometrics mostly follows a different path for each biometric trait, considering that there can be a huge difference between the acquired biometric data for different modes, such as voice and signature. On the other hand, if we analyze the general challenges in biometric systems that spans over different modes, we observe three main areas:

  1. Biometric Recognition: Biometric identification and verification system design and performance analysis using different biometric traits captured via different sensors
  2. Privacy in Biometrics: Protection of biometric templates for the users of a recognition system and prevention of unconsented identification of persons who give their biometric sample for other purposes or have their biometric sample captured unknowingly
  3. Biometric Anti-spoofing: Detection and prevention of spoofing attacks (presentation attacks) to biometric recognition systems at sensor level

CSIGB is particularly involved in face and fingerprint biometric modalities in all three areas.

Fields of Interest

Biometric recognition

Development and testing of biometric identification and verification algorithms for different modes

Privacy in biometrics

Protection of privacy for biometric system users and prevention of unconsented identification

Biometric anti-spoofing

Detection of spoofing attacks on biometric recognition systems at sensor level