Volume 14, Issue 8, 2021
Published on: 23 April, 2020
Article ID: e180122181249
Background: In recent history, fingerprint presentation attack detection (FPAD) proposal came out in a variety of ways. A close-set approach uses a pattern classification technique that best suits a specific context and goal. The Open-set approach works fine in a wider context, which is relatively robust with new fabrication material and independent of sensor type. In both cases, results were promising but not too generalizable because of unseen conditions not fitting into the method used. It is clear that the two key challenges in the FPAD system, sensor interoperability and robustness with new fabrication materials are not addressed to date.
Objective: To address the above challenges, a liveness detection model is proposed using a live sample using transient liveness factor and one-class CNN.
Methods: In our architecture, liveness is predicted by using the fusion rule, score level fusion of two decisions. Here, ‘n’ high-quality live samples are initially trained for quality. We observed that fingerprint liveness information is ‘transitory’ in nature, a variation in the different live sample is natural. Thus, each live sample has a ‘transient liveness’ (TL) information. We use no-reference (NR) image quality measure (IQM) as a transient value corresponding to each live sample. A consensus agreement is collectively reached in transient value to predict adversarial input. Further, live samples at the server are trained with augmented inputs on the one-class classifier to predict the outlier. So, by using the fusion rule, score level fusion of consensus agreement and appropriately characterized negative cases (or outliers) predicts liveness.
Results: Our approach uses high-quality 30-live samples only, out of 90 images available in the dataset to reduce learning time. We used Time Series images from the LivDet competition 2015. It has 90-live images and 45-spoof images made from Bodydouble, Ecoflex and Playdoh of each person. Fusion rule results in 100% accuracy in recognising live as live.
Conclusion: We have presented an architecture for liveness-server for extraction/updating transient liveness factor. Our work explained here a significant step forward towards a generalized and reproducible process with consideration towards the provision for the universal scheme as a need of today. The proposed TLF approach has a solid presumption; it will address dataset heterogeneity as it incorporates wider scope-context. Similar results with other datasets are under validation. Implementation seems difficult now but has several advantages when carried out during the transformative process. Read now: https://bit.ly/3oTElLV