Facial biometrics for 2D barcodes

This paper proposes a novel use of 2D barcodes to store biometric data, in particular for facial recognition, which represents one of the least invasive biometric techniques. To accomplish this, we deploy 2D color barcodes, which allow larger storage capabilities than traditional 2D barcodes. To improve the quality of facial recognition, we combine local feature descriptors, such as SURF descriptors, together with shape landmarks identified through statistical models for discriminating faces. The biometric information can be secured through digital signature algorithms, in order to protect biometric data from malicious tampering. The use of color barcodes is crucial in this setting, as traditional barcodes cannot store a suitable number of SURF descriptors for discriminating faces and cannot even afford to store an additional cryptographic payload. We report the results of an experimental evaluation of our system on real-world data sets (i.e., a face database).