The emergence of biometric-based authentication using modern sensors on electronic devices has led to an escalated use of face recognition technologies. While these technologies may seem intriguing, they are accompanied by numerous implicit drawbacks. In this paper, we look into the problem of face anti-spoofing (FAS) on a frame level in an attempt to ameliorate the risks of face-spoofed attacks in biometric authentication processes. We employed a bi-directional feature pyramid network (BiFPN) that is used for convolutional multi-scaled feature extraction on the EfficientDet detection architecture, which is novel to the task of FAS. We further use these convolutional multi-scaled features in order to perform deep pixel-wise supervision. For all of our experiments, we performed evaluations across all major datasets and attained competitive results for the majority of the cases. Additionally, we showed that introducing an auxiliary self-supervision branch tasked with reconstructing the inputs in the frequency domain demonstrates an average classification error rate (ACER) of 2.92% on Protocol IV of the OULU-NPU dataset, which is significantly better than the currently available published works on pixel-wise face anti-spoofing. Moreover, following the procedures of prior works, we performed inter-dataset testing, which further consolidated the generalizability of the proposed models, as they showed optimum results across various sensors without any fine-tuning procedures.
Face Anti Spoofing (FAS) systems are used to identify malicious spoofing attempts targeting face recognition systems using mediums such as video replay or printed papers. With increasing adoption of face recognition technology as a biometric authentication method, FAS techniques are gaining in importance. From a learning perspective, such systems pose a binary classification task. When implemented with Neural Network based solutions, it is common to use the binary cross entropy (BCE) function as the loss to optimize. In this study, we propose a variant of BCE that enforces a margin in angular space and incorporate it in training the DeepPixBis model [1]. In addition, we also present a method to incorporate such a loss for attentive pixel wise supervision applicable in a fully convolutional setting. Our proposed approach achieves competitive scores in both intra and inter-dataset testing on multiple benchmark datasets, consistently outperforming vanilla DeepPixBis. Interestingly, in the case of Protocol 4 of OULU-NPU, considered to be the hardest protocol, our proposed method achieves 5.22% ACER, which is only 0.22% higher than the current State of the Art without requiring any expensive Neural Architecture Search.
Unlike long ago information storage in recent times heavily relies on technology. Physical representations like paper-based documents of data have minimized to a negligible amount. But relying on technology has also its drawbacks. These drawbacks can essentially be in terms of security and security breaches can result in compromising data worth a lot of money. In order to tackle this problem, this research looks into the state-of-the-art cryptographic algorithms and data storing paradigms, more specifically focus on the form of data storage known as Blockchains. Currently no such system is available where the user has the capability to create dynamic schemas to store their data in Blockchains along with the its integration with their existing system. Leveraging the concepts of Smart Contracts and Blockchain, on this paper a novel data storing engine by which users can create dynamic data schemas is proposed and also the data query abstractions to manage the data, integration of this system with the users existing system will also be an unchallenging problem. Finally, the results are presented by building an application which is built using the proposed engine and thus evaluate the solution.
5 August 2023 in International Journal on Document Analysis and Recognition (IJDAR)
The dye-dilution assay is a powerful tool to study lymphocyte expansion dynamics. By combining time course dye-dilution experiments with computational analysis, quantitative information about cell biological parameters, such as percentage of cells dividing, time of division, and time of death, can be produced. Here, we describe the method to generate quantitative cell biological insights from dye-dilution experiments. We describe experimental methods for generating dye-dilution data with murine lymphocytes and then describe the computational data analysis workflow using a recently developed software package called FlowMax. The aim is to interpret the dye-dilution data quantitatively and objectively, such that cell biological parameters can be reported with an appropriate measure of confidence, which in turn depends on the quality and quantity of available data.