Fingerprint Liveness Detection Using an Improved CNN With Image Scale EqualizationDate:2021-09-10
Border Biometrics: "Zero Benefit?"
The article seeks to investigate the relationship between artificial intelligence and fraudulent claims in the inclusive insurance sector in developing countries. Although low-income cover has been classified as an important tool to combat poverty, fraudulent claims continue to escalate and is more a serious threat to the low-income cover market sustainability as fraudsters seem to be a step ahead of the game. Through a review of literature that has flagged to be scarce, the author advances the hypothesis that artificial intelligence is more likely to be successful where the increased use of online purchases of inclusive cover (micro-insurance), high cost of identifying claims fraud, lack of data and resources experienced by the providers of inclusive cover amongst others, are available. The study's drive is predicated on the argument that although with the advances of computing techniques and technology, artificial intelligence systems can be employed to reduce the frequency and severity of fraudulent claims. Despite some identified challenges, the findings reveal that leveraging use of artificial intelligent systems in the low-income cover market could promote the effective sustainability of the inclusive cover niche market as it is an uncertain profit business by nature of its low premium income and high transaction cost compared to the regular insurance market. Finally, the author points to some possible ways for combating fraudulent claims occurrences through the effective use of artificial intelligence systems in the midst of Industry 4.0.
face spoofing attacks deals with printing artifacts, electronic screens and ultra-realistic face masks or models. This paper proposes a liveness detection method based on diffusion speed. Diffusion speed of a single image is calculated as the difference of the original images and diffused images at each pixel. Face spoofing method based on diffusion speed does not require any user involvement and works with a single image. The key aspect of the proposed method is based on the difference in the illumination characteristics of live and fake faces. To solve the nonlinear, scalar valued diffusion equation, AOS (Additive Operator Splitting) approach, together with TDMA (Tri-Diagonal Matrix Algorithm) is applied. The local pattern of the diffusion speed is calculated at each pixel position (Local Diffused Patterns) and fed to linear Support Vector Machine for classification. Proposed approach performs well against the diverse malicious attacks, face display media (screen / paper) & varying illuminations and gives 90.83% accuracy.
|0||Digital Identity Verification||Default|