Liveness Measurements Using Optical Flow for Biometric Person Authentication

Abstract

Biometric identification systems, i.e. the systems that are able to recognize humans by analyzing their physiological or behavioral characteristics, have gained a lot of interest in recent years. They can be used to raise the security level in certain institutions or can be treated as a convenient replacement for PINs and passwords for regular users. Automatic face recognition is one of the most popular biometric technologies, widely used even by many low-end consumer devices such as netbooks. However, even the most accurate face identification algorithm would be useless if it could be cheated by presenting a photograph of a person instead of the real face. Therefore, the proper liveness measurement is extremely important. In this paper we present a method that differentiates between video sequences showing real persons and their photographs. First we calculate the optical flow of the face region using the Farnebäck algorithm. Then we convert the motion information into images and perform the initial data selection. Finally, we apply the Support Vector Machine to distinguish between real faces and photographs. The experimental results confirm that the proposed approach could be successfully applied in practice.

Just look at to open it up:

“…We continue our work towards a more secure transfer of electronic documents exchanged in collaborative processes by incorporating effective methods for determining liveness of the subject in front of the camera [46] combined with identifying various emotional states of the subject [24] developed in another project to make the FYEO scheme resistant to physical attacks on users and to extend the catalogue of factors affecting tuning of the FAR/FRR rates by facial expressions. Another issue to be addressed is extension of biometric verification to lighting conditions for outdoor use.…”

“…Undoubtedly, the latter task will be at least as difficult as the former one, despite the use of the most efficient methods of generating artificially modified versions of input images. Finally, the ultimate protection against attacks using any acquired or generated images in steps #4, #5 and #6 in Figure 12 will be adding to the decrypting application a liveness verification module, making such attacks infeasible [46]. If, however, the attacker could still break all the barriers described above and somehow managed to pass the biometric verification process in step #7 the FYEO document has yet several more lines of defense.…”

Real-Time Evaluation of Breast Self-Examination Using Computer Vision

“…The palpation detection for each block is derived from the motion detection using the optical flow algorithm. There are many methods available to calculate optical flow, but the goal is always the same: for every pixel the velocity vector is calculated [ 28 ]. Originally, optical flow algorithms used gradient-based estimation.…”

Touchless typing with head movements captured in thermal spectrum

“…Moreover, in a broader biometrical context, such data are resistant to spoofing attempts (e.g. using previously captured photo or video stream [34]).…”