An efficient face anti-spoofing and detection model using image quality assessment parameters
- PDF / 1,544,955 Bytes
- 22 Pages / 439.37 x 666.142 pts Page_size
- 58 Downloads / 204 Views
An efficient face anti-spoofing and detection model using image quality assessment parameters Aditya Bakshi 1
& Sunanda Gupta
1
Received: 1 May 2020 / Revised: 7 September 2020 / Accepted: 7 October 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Biometric authentication poses a significant problem as reconstructed sample or fake selfmanufactured samples used by intruders for accessing the actual real legitimate traits. The other prime concern for biometrics is the increasing demand for safety in mobile devices, such as smartphones and tablets etc. So, in the present scenario security for biometrics has gained considerable attention due to various inherent qualities of biometrics. For detection of valid user in a face recognition system with photographs, videos, and 3D models, face liveness detection system is a great technique against spoofing attacks for differentiating between the fake traits from the real traits. In this paper, a novel fake biometric detection technique utilizing liveness detection is proposed for detecting deceitful access attempts in the biometric face system. The prime objective of the paper is to propose a low-complexity fake biometric detection using different image quality assessment parameters i.e. Mean Square Error, Signal to Noise Ratio,SC etc. on the extracted features of the images. The authenticity of the proposed model is confirmed by analyzing the values of MSE, which are 5.8% and 8.49% more than the threshold value of nose and eye features. The same results have also been shown for other 11 different image quality assessment parameters. The experiments were done on the database prepared using the image samples of the 500 male and female students having age between 20 to 30 years. Keywords Fake biometric detection . Image quality assessment . Liveness
* Aditya Bakshi [email protected] Sunanda Gupta [email protected]
1
Department of Computer Science and Engineering, Shri Mata Vaishno Devi University, Jammu, Kashmir, India
Multimedia Tools and Applications
1 Introduction In recent years, a biometric security system has evolved at a faster rate, and now it is turning out to be a broad area of research. With the arrival of mobile devices such as smartphones, the demand for biometric security has increased tremendously. In a traditional biometric security system, first biometric data are acquired through sensors, and then features are extracted from the received data samples. In the end, the acquired characteristics match with a set of templates in a database through matching modules. But in the present world, fake biometrics are posing a much more significant threat to the existing biometric systems. Different types of fake biometrics like printed iris image, masked face, and gummy finger are used to capture the behavior of genuine users to access the biometric system. There are seven essential criteria for the biometric security system, as shown in Fig. 1 [23]. It comprises of uniqueness, universality, permanence, collectabilit
Data Loading...
