Scribd Logo
Upload

Welcome to Scribd!

    • 40 views

    Seminar Thesis

    Uploaded by

    city cyber
    The document describes a proposed credit system that uses facial recognition technology. It would allow customers to automatically earn credit points during purchases that get added to their individual accounts, identified through facial recognition of the customer, rather than requiring manual entry of customer details. The system is designed to use OpenCV and deep learning for facial recognition processing to identify existing customers faster and more efficiently than the current manual system.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Seminar Thesis

    Uploaded by

    city cyber
    40 views12 pages
    The document describes a proposed credit system that uses facial recognition technology. It would allow customers to automatically earn credit points during purchases that get added to their individual accounts, identified through facial recognition of the customer, rather than requiring manual entry of customer details. The system is designed to use OpenCV and deep learning for facial recognition processing to identify existing customers faster and more efficiently than the current manual system.

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document describes a proposed credit system that uses facial recognition technology. It would allow customers to automatically earn credit points during purchases that get added to their individual accounts, identified through facial recognition of the customer, rather than requiring manual entry of customer details. The system is designed to use OpenCV and deep learning for facial recognition processing to identify existing customers faster and more efficiently than the current manual system.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    40 views12 pages

    Seminar Thesis

    Uploaded by

    city cyber
    The document describes a proposed credit system that uses facial recognition technology. It would allow customers to automatically earn credit points during purchases that get added to their individual accounts, identified through facial recognition of the customer, rather than requiring manual entry of customer details. The system is designed to use OpenCV and deep learning for facial recognition processing to identify existing customers faster and more efficiently than the current manual system.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 12

    CREDIT SYSTEM USING FACIAL

    RECOGNITION

    A Major Project Report Submitted


    In partial fulfillment of the requirements for the award of the degree of

    Bachelor of Technology
    in
    Computer Science and Engineering

    by
    M V N S Mukul Datta 16N31A05B3
    Rameshwaram Avinash 17N31A05K3
    Ambalam Sreekar 16N31A0508

    Under the esteemed guidance of

    Mr. P. BIKSHAPATHY
    Associate Professor

    Department of Computer Science and Engineering


    Malla Reddy College of Engineering & Technology
    (Autonomous Institution- UGC, Govt. of India)
    (Affiliated to JNTUH, Hyderabad, Approved by AICTE, NBA &NAAC with ‘A’
    Grade)
    Maisammaguda, Kompally, Dhulapally, Secunderabad – 500100
    website: www.mrcet.ac.in

    2017-2021
    INTRODUCTION

    • The system uses OpenCV to detect faces and recognise


    them and then creates a group for that particular face in
    the database which adds everything the customer
    purchases to that particular folder of the database.
    • Each customer has a separate folder to themselves which
    avoids confusion of adding and the credit points
    automatically.
    • This enables for faster processing and also gives the
    customers an advantage of benefit. As it reduces the need
    of entering of information from the customer because the
    system automatically identifies the customer and displays
    the details.
    ABSTRACT

    • Now a days every shopping mall or supermarket has


    credit points when we purchase anything from the store
    and we can later redeem them for benefits.
    • The process requires the customers to fill in a form and
    submit details which is why many of the customers
    refrain from becoming members, we plan to automate it
    using a facial recognition software which identifies
    customers.
    • The software identifies faces which are already
    recognised and automatically adds the credit points to the
    customers account.
    • If the customer is not found, then the system requests the
    customer picture and contact details for customer to be
    added to the database. The points can be redeemed as the
    company pleases.
    EXISTING SYSTEM

    • The system which currently exists is manual and it needs


    for the employee or executive to enter the details of the
    customers and the system then retrieves the data from the
    database.
    • The system needs to take many details to store or give
    membership to the customer which can make many
    customers have no interest or just be uninteresting to
    them which can make it a bother for them.
    • This also makes the processing slower as it delays the
    working of the order and slows the processing down,
    which can be avoided by our system.
    PROPOSED SYSTEM

    • The developed system consists of facial recognition


    which identifies the customers based on the webcam
    placed near the checkout which enables for faster
    checkout and reduction of unnecessary manual labour.
    • The system uses OpenCV and Deep learning to process
    the data and learn faster then uses a local database to
    store the collected data.
    • The system recognises the customer and then when a
    purchase is made it automatically adds the credit points
    to the customer’s data which helps in faster processing
    and less manual labour.
    • The system can also be expanded in future for more
    additions and can also be added to existing systems as a
    plugin.
    SYSTEM DESIGN

    • Recommended Software Requirements


    i. Python (Version 3).
    ii. Dlib v19.0 and above.
    iii. Cmake.
    iv. pip installation required.
    v. Face-recognition.
    vi. Operating System windows 8 or above.
    • Recommended Hardware Requirements
    i. A web camera(internal or external).
    ii. Ram: 1GB Ram and above.
    iii. Hard Disk Space: 50 GB and above (Windows 10
    requires a min of 32 GB of hard disk space).
    iv. Processor: Dual core and above.
    Note: Better hardware specs enable higher performance and
    faster frame collection.
    IMPLEMENTATION

    The following programming software / languages were used


    to implement the project:
    • Python: Python contributes as the main driver code. It
    implements the facial recognition as well as the main
    GUI of the application. It is supported by the other.
    • Dlib: Dlib is used to recognise faces as it helps us detect
    the side face as well as the frontal face.
    • PyQt5: We use PyQt to complete the GUI of the
    application to hold the mail components.
    • Face-recognition: This module will contain the essential
    functions which are help us recognise the faces.
    ALGORITHM
    • The algorithm used in the identification of faces is HOG
    which was developed by Dalal and Triggs during their
    seminar paper.
    • HOG algorithm is used to process the images and use
    their gradients to differentiate the images from each
    other.
    • As mentioned earlier HOG feature descriptor used for
    pedestrian detection is calculated on a 64×128 patch of
    an image. Of course, an image may be of any size.
    • To calculate a HOG descriptor, we need to first calculate
    the horizontal and vertical gradients; after all, we want to
    calculate the histogram of gradients.
    • We will learn about the histograms in a moment,
    but before we go there let us first understand why
    we have divided the image into 8×8 cells.
    FACIAL RECOGNITION
    • The recognition takes place by dividing the video into
    frames and then it processes each frame and then checks
    with existing processed images.
    • The accuracy is very high when recognising the faces
    and we can detect multiple faces at a time.
    • To enable human identification at a distance (HID) low-
    resolution images of faces are enhanced using face
    hallucination.
    • The emerging use of facial recognition is in the use of ID
    verification services. Many companies and others are
    working in the market now to provide these services to
    banks, ICOs, and other e-businesses.
    CONCLUSION

     This application will provide help not only to any


    shopping mall but will also help us in making faster
    transactions and identification of customers which is
    rewarding for the customer as well as the seller because
    it helps in faster processing and more rewards. The data
    can be shared across servers which can help make the
    customer feel easier and faster access.
     Considering impatience and restlessness of people
    nowadays the requirement of having faster and seamless
    transactions is more and is demanding this application
    which is developed aims to make the processing and
    checking in of customers easier and more accessable.
    FUTURE ENHANCEMENTS AND
    DEVEPOLMENT
    • We currently aren’t using any database storage for faster
    retrieval and storage so we would like to improve the
    project to use a global database which can be distributed
    across the servers.
    • The processing requires faster CPU as the performance
    was CPU bound and we plan to include more algorithms
    for faster processing and enable more efficient
    recognition.
    • The processing requires faster CPU as the performance
    was CPU bound and we plan to include more algorithms
    for faster processing and enable more efficient
    recognition
    • This enables the storage and access of data more easier
    and more efficient.
    REFERENCES
     "General Python FAQ — Python 3.9.2 documentation".
    docs.python.org. Retrieved 28 March 2021.
     Jump up to:a b Guttag, John V. (12 August 2016).
    Introduction to Computation and Programming Using
    Python: With Application to Understanding Data. MIT
    Press. ISBN 978-0-262-52962-4.
     Jump up to:a b "Python 3.8.10, 3.9.5, and 3.10.0b1 are
    now available". 3 May 2021. Retrieved 4 May 2021.
     "Why is Python a dynamic language and also a strongly
    typed language - Python Wiki". wiki.python.org.
    Retrieved 27 January2021.
     "PEP 483 -- The Theory of Type Hints". Python.org.
     "Download Python". Python.org. Retrieved 24 May
    2021.
     File extension .pyo was removed in Python 3.5. See PEP
    0488
     Holth, Moore (30 March 2014). "PEP 0441 -- Improving
    Python ZIP Application Support". Retrieved 12
    November 2015.

    You might also like