FIGURE 3 - available via license: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Content may be subject to copyright.
![Some facial regions (i.e., mouth, nose, left and right eyes, left and right eyebrows, chin and jaw) computed from landmarks extracted from an image in REPLAY-MOBILE [47].](publication/372150502/figure/fig3/AS:11431281173193706@1688782310141/Some-facial-regions-ie-mouth-nose-left-and-right-eyes-left-and-right-eyebrows.png)
Some facial regions (i.e., mouth, nose, left and right eyes, left and right eyebrows, chin and jaw) computed from landmarks extracted from an image in REPLAY-MOBILE [47].
Source publication
![FIGURE 4: Example of BPs and APs in the CRMA database taken from [9].](publication/372150502/figure/fig4/AS:11431281173149912@1688782310350/Example-of-BPs-and-APs-in-the-CRMA-database-taken-from-9_Q320.jpg)
In the last decade, breakthroughs in the field of deep learning have led to the development of powerful presentation attack detection (PAD) algorithms which reported reliable performance across different realistic scenarios. Typically, most of these techniques analyse the full face to detect attack presentations (APs), ignoring that the attributes...
Context in source publication
Context 1
... Based on such landmarks, 14 different facial regions in Tab. 1 are defined. For a comprehensive analysis, these regions are divided into two groups: single (i.e., mouth, nose, chin, left eye, right eye, left eyebrow, and right eyebrow) and composite (i.e., both eyes, both eyebrows, central face, jaw, left face, and right face, full face). Fig. 3 shows an example of those landmarks together with some facial regions. Note that the left (right) region comprises the facial portion to the left (right) of landmark 27, bounded by the top of the forehead and landmark ...
Citations
... Furthermore, in order to benefit from the fine-grained spatial-frequency information given by wavelet decomposition, the system has moved the input data domain from the RGB space into the wavelet domain. L. J. Gonzalez-Soler et al [8] discusses the viability of employing various face regions for PAD was investigated in this paper. Specifically, 14 regions-both single and composite-were assessed using the parameters outlined in the ISO/IEC 30107-3 international standard [11] for biometric PADs. ...
The achievement of greater ease and dependability has been made possible by India's technical advancements. The banking industry has also prospered, achieving notable improvements that have benefited the consumer. Automated Teller Machines (ATMs) have transformed transaction capabilities and decreased the likelihood of human error. Cash can always be dispensed and deposited via ATMs. This can be done with the bank-issued cards, which make integration considerably simpler. However, there has been a rise in card theft and fraudulent transactions, which compromises the dependability and security of ATMs. Consequently, rather than recognizing the card as is the case with the current model, a methodology that identifies the person during the transaction is required to increase the security and dependability of Automated Teller Machines. Implementing a biometric authentication system will be necessary to realize user identification through a virtual ATM strategy. In order to create a very reliable and secure virtual ATM, this method covers the usage of face recognition in addition to fingerprint recognition using live streaming, Channel Boosted Convolutional Neural Networks, and One Time Password implementation. The research directives to come will provide a detailed explanation of the strategy.
