SVM classification for fake biometric detection using image quality assessment: Application to iris, face and palm print

The increasing interest in the evaluation of biometric systems security is an important issue to be considered. The different threats called direct or spoofing attacks where in these attacks, the intruder uses some type of synthetically produced artifact (e.g., gummy finger, printed iris image or face mask), or tries to mimic the behavior of the genuine user, to fraudulent access of the biometric system have motivated to new efficient protection measures. In this paper, we present a novel software-based fake biometric detection method that can be used in multiple biometric systems to detect different types of fraudulent access attempts. The use of image quality assessment for liveness detection is motivated by the assumption that: It is expected that a fake image captured in an attack attempt will have different quality than a real sample acquired in the normal operation scenario for which the sensor was designed. The proposed approach presents a very low degree of complexity, which makes it suitable for real-time applications, using general image quality features extracted from one image to differentiate between real and fake samples. This proposed work enhances the security of biometric recognitions, by using the liveness detection through image quality assessment and by fusion of multiple biometric traits. The SVM classifier is used for differentiating between the real and fake samples.