New Optical Methods for Liveness Detection on FingersDate:2021-09-17
FLDNet: Light Dense CNN for Fingerprint Liveness Detection
Internet fraud is increasing on a daily basis with new methods for extracting funds from government, corporations, businesses in general, and persons appearing almost hourly. The increases in on-line purchasing and the constant vigilance of both seller and buyer have meant that the criminal seems to be one-step ahead at all times. To pre-empt or to stop fraud before it can happen occurs in the non-computer based daily transactions of today because of the natural intelligence of the players, both seller and buyer. Currently, even with advances in computing techniques, intelligence is not the current strength of any computing system of today, yet techniques are available which may reduce the occurrences of fraud, and are usually referred to as artificial intelligence systems.This paper provides an overview of the use of current artificial intelligence (AI) techniques as a means of combating fraud.Initially the paper describes how artificial intelligence techniques are employed in systems for detecting credit card fraud (online and offline fraud) and insider trading.Following this, an attempt is made to propose the using of MonITARS (Monitoring Insider Trading and Regulatory Surveillance) Systems framework which use a combination of genetic algorithms, neural nets and statistical analysis in detecting insider dealing. Finally, the paper discusses future research agenda to the role of using MonITARS system.
In this paper, we exploit regional features for iris liveness detection. Regional features are designed based on the relationship of the features in neighbouring regions. They essentially capture the feature distribution among neighbouring regions. We construct the regional features via two models: spatial pyramid and relational measure which seek the feature distributions in regions with varying size and shape respectively. The spatial pyramid model extracts features from coarse to fine grid regions, and, it models a local to global feature distribution. The local distribution captures the local feature variations while the global distribution includes the information that is more robust to translational transform. The relational measure is based on a feature-level convolution operation defined in this paper. By varying the shape of the convolution kernel, we are able to obtain the feature distribution in regions with different shapes. To combine the feature distribution information in regions with varying size and shape, we fuse the results based on the two models at the score level. Experimental results on benchmark datasets demonstrate that the proposed method achieves an improved performance compared to state-of-the-art features.
|0||Digital Identity Verification||Default|