Professional Documents
Culture Documents
Document Content
Document Content
FacePIN is a sophisticated biometric authentication system designed to enhance security and streamline the
user authentication process at Automated Teller Machines (ATMs). The system analysis of FacePIN involves
a detailed examination of its various components, functionalities, and operational processes, ensuring a
comprehensive understanding of its requirements and capabilities.
Users interact with FacePIN by approaching an ATM equipped with facial recognition capability. By
conducting a systematic analysis of FacePIN, stakeholders can gain valuable insights into its functionality,
usability, security, and performance characteristics. This analysis serves as a foundation for the design,
development, and deployment of a robust and effective Face Biometric Authentication System for ATM
security and user authentication.
ExistingSystem
QR cash withdrawals were enabled so customers could ditch their ATM cards and
simply scan a QR-code on ATMs using the QR app to withdraw cash.
A QRcode scanner is required to detect code and decrypt information in stored inQRcode.
Scanner need to be installed in the ATM machine to take input credentials from the user. We
will provide extra featureto an existing system, so traditional withdrawing option is also
there. On other end, ATM machine will scan the QRcode generated by 'GetNote'-android
application and decrypt it with the key stored in the database. After decryption ATM will get
required credentials such as card number, amount, pin, cvv number on card etc. Itwill
authenticate all the details with the banks database. After successful authentication, cash will
be dispensed by the ATM machine.
The algorithms used in the existing system for biometric authentication are Gaussian
Mixture Models (GMMs), Artificial Neural Networks (ANNs), Fuzzy Expert Systems
(FESs), andSupport Vector Machines (SVMs). LDA, PCA.
Disadvantages
ProposedSystem
This project proposes an automatic teller machine multi modal security model that would
combine a physical access cardand electronic facial recognition using Deep Convolutional
Neural Network.
FacialBiometricAuthenticationSystemusingDeepLearning Techniques
Deep learning is a subset of machine learning, which, in turn, is a subset of artificial
intelligence (AI). When it comes to Face recognition, deep learning enables us to achieve
greater accuracy than traditional machine learning methods.
Deep FR system with face detector and alignment. First, a face detector is used to localize
faces. Second, the faces are aligned to normalized canonical coordinates. Third, the FR
moduleis implemented.In FR module, faceanti-spoofing recognizes Whethertheface is live or
spoofed; face processing is used to handle variations before training and testing, e.g.,poses,
ages; Different architectures and loss functions are used to extract discriminative deep feature
when training; face matching methods are used to do feature classification after the deep
features of testing data are extracted.
UnknownFaceVerificationLinkGenerator–
When the stored image and the captured image don't match, it means that he is an
unauthorizeduser.FaceVerificationLinkwillbegeneratedandsenttousertoverifythe
identity of unauthorized user through some dedicated artificial intelligent
agents, for remote certification, which either authorizes the transaction
appropriately or signals a security- violation alert to the banking security
system.
Advantages
Operational Feasibility
Technical Feasibility
Economic Feasibility
Operational Feasibility:
Operational feasibility assesses whether the proposed system can be effectively implemented
within the existing operational framework. In the case of FacePIN, several factors contribute
to its operational feasibility:
Technical Feasibility:
Technical feasibility evaluates whether the proposed system can be successfully developed
and implemented from a technological perspective. For FacePIN, the following factors
indicate its technical feasibility:
Economic Feasibility:
Economic feasibility examines whether the proposed system is financially viable and offers a
favorable return on investment. Key considerations for FacePIN's economic feasibility
include:
1. Cost of Development: The development costs for FacePIN primarily include expenses
related to software development, deep learning model training, and system integration.
However, these costs may be offset by potential savings from reduced fraud losses and
operational efficiencies.
2. Implementation Costs: Retrofitting existing ATMs with FacePIN capability may incur
upfront costs for hardware upgrades and installation. However, these costs should be weighed
against the long-term benefits of improved security and reduced fraud.
3. Operational Costs: Ongoing operational costs for FacePIN include maintenance, technical
support, and updates to the deep learning algorithms. However, these costs may be
outweighed by the potential cost savings from mitigating fraud and enhancing efficiency.
4. Return on Investment (ROI): Calculating the ROI for FacePIN involves comparing the
projected benefits, such as reduced fraud losses and improved customer satisfaction, against
the total investment. A positive ROI would indicate the economic feasibility of implementing
FacePIN.
ANOTHER CONTENT FOR FEASIBILITY STYUDY(USE THIS ONE)
The feasibility study for the FacePIN project, which proposes a Face Biometric
Authentication System for ATMs using Deep Learning, evaluates its viability from
operational, technical, and economic perspectives.
Technical Feasibility: Technical feasibility evaluates whether the proposed system can be
effectively developed and implemented from a technological standpoint. Key considerations
include the availability of suitable deep learning algorithms, hardware requirements,
scalability, and data security. FacePIN utilizes mature deep learning techniques, minimal
hardware requirements, scalable cloud infrastructure, and robust data security measures,
indicating strong technical feasibility.
Economic Feasibility: Economic feasibility examines the financial viability and potential
return on investment of the FacePIN project. Factors analyzed include development costs,
implementation expenses, ongoing operational costs, and the projected ROI. While initial
development and implementation costs may exist, potential benefits such as reduced fraud
losses and operational efficiencies could yield a favorable ROI, indicating economic
feasibility.
Overall, the feasibility study suggests that FacePIN is operationally, technically, and
economically viable as an advanced biometric authentication solution for ATM security.
However, careful planning, compliance with regulations, and thorough consideration of costs
are essential for successful implementation and adoption.
SYSTEM SPECIFICATION
INTRODUCTION
The system specification for the FacePIN project outlines the technical
requirements, functionalities, and performance benchmarks necessary for
the successful development and implementation of the biometric
authentication system for ATMs. At its core, the system must be capable of
capturing, processing, and analyzing facial biometric data in real-time to
verify the identity of users with a high degree of accuracy and reliability.
This entails the development of sophisticated facial recognition algorithms,
leveraging deep learning techniques such as convolutional neural networks
(CNNs) to extract and match facial features against stored templates.
Additionally, the system must incorporate robust security measures to
protect sensitive biometric data and ensure compliance with regulatory
standards governing data privacy and security. Integration with existing
ATM infrastructure is essential, requiring compatibility with hardware
components such as cameras and processors, as well as software interfaces
for communication with backend systems. Usability and accessibility are
also key considerations, necessitating an intuitive user interface and
support for users of all abilities. Overall, the system specification serves as a
blueprint for the design, development, and deployment of a reliable and
effective biometric authentication solution that enhances ATM security and
user experience.
HARDWARE SPECIFICATIONS(ABSTRACT)
Logical design
Logical design plays a crucial role in the development of the FacePIN project, serving as the
foundation upon which the system's architecture, functionalities, and workflows are
conceptualized and structured. This introduction provides an overview of the logical design
phase, outlining its objectives, methodologies, and key considerations in the context of
FacePIN.
The FacePIN project aims to revolutionize ATM security through the implementation of
advanced biometric authentication using facial recognition technology and deep learning
algorithms. The logical design phase is instrumental in translating the project's objectives into
a coherent and efficient system architecture that meets the requirements of security, usability,
and scalability.
PHYSICAL DESIGN
the introduction to physical design sets the stage for the implementation
and deployment of the FacePIN system by defining its hardware and
software architecture, selecting appropriate components, and configuring
them to meet the project's requirements. By aligning with project
objectives, employing rigorous methodologies, and considering key design
considerations, the physical design phase lays the groundwork for the
successful realization of FacePIN as a state-of-the-art biometric
authentication solution for ATMs.
The physical design process is guided by the overarching objectives of the FacePIN
project, which include enhancing ATM security, improving user authentication,
minimizing fraudulent transactions, ensuring regulatory compliance, and fostering
technological innovation. The physical design phase aims to translate these objectives
into a robust and scalable system architecture that meets the project's requirements.
Physical design for FacePIN follows a systematic and iterative approach, beginning
with an assessment of hardware and software requirements and culminating in the
deployment and configuration of the selected components. The methodology involves
collaboration between hardware engineers, software developers, system integrators,
and other stakeholders to ensure that the physical design aligns with the project's
objectives and constraints.
The scope of physical design encompasses various aspects of the FacePIN system,
including the selection and configuration of hardware components such as cameras,
processors, memory modules, and network interfaces. Additionally, the physical
design phase involves the deployment and configuration of software components,
including facial recognition algorithms, data processing pipelines, and user interface
modules.
In designing the physical architecture of the FacePIN system, several key
considerations must be taken into account, including hardware compatibility,
scalability, reliability, power consumption, and environmental factors. The design
must also adhere to regulatory standards and data privacy laws governing the handling
of biometric data and financial transactions.
4.3.1 Design Methodology
Design Methodology is a way to transform the "art" of system analysis and design
into an "engineering - type" discipline. It explains the relationship amongst various modules
and programs with in the system. It standardizes the approach to analysis and design,
simplifies design by segmentation, improves documentation and subsequent maintenance and
enhancements.
The following structured diagram can appropriately represent the relationship between
various modules.
In analyzing the present system a great deal of information was collected during the
investigation and feasibility phases through list of problems and requirements, interview
reports, questionnaires, onsite observations, manuals and determining potential solutions.
Structured analysis is a set of techniques and graphical tools that allow the analyst to
develop a new kind of system specification that are easily understandable to the user. The
traditional approach of organizing data through flowcharts support future developments and
simplify communication with the user but focus on the cost/ benefit and feasibility
analysis, project management,hardware and software selection, and personal considerations.
In contrast, structured analysis considers new goals and structured tools for analysis, which
provide the basis for design and implementation.