Scribd
Upload
159 views11 pages

Deep Learning Approach For Multimodal Bio-Metric Recognition System With Fusion Based On Face, Iris and Finger Vein Pattern (Batch Id: 2021/A/02)

The document proposes a deep learning approach for a multimodal biometric recognition system using face, iris, and finger vein patterns. It aims to develop a new multimodal identification model combining unimodal models for iris, face, and a new finger vein model. The proposed system architecture is based on convolutional neural networks and will be evaluated on the SDUMLA-HMT dataset. Hardware requirements include an Intel i3/i5 processor and 2GB RAM, while software requirements involve Python and Matlab.

Uploaded by

518Challa Lakshmi Prasanna
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
159 views11 pages

Deep Learning Approach For Multimodal Bio-Metric Recognition System With Fusion Based On Face, Iris and Finger Vein Pattern (Batch Id: 2021/A/02)

The document proposes a deep learning approach for a multimodal biometric recognition system using face, iris, and finger vein patterns. It aims to develop a new multimodal identification model combining unimodal models for iris, face, and a new finger vein model. The proposed system architecture is based on convolutional neural networks and will be evaluated on the SDUMLA-HMT dataset. Hardware requirements include an Intel i3/i5 processor and 2GB RAM, while software requirements involve Python and Matlab.

Uploaded by

518Challa Lakshmi Prasanna
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 11

Deep Learning approach for Multimodal Bio-metric

recognition System with Fusion based on Face , Iris and Finger


Vein Pattern
(batch id : 2021/A/02)

                                                                              PRESENT BY:
                                                                                                 CH.LAKSHMI PRASANNA-178X1A0518
                                                                                                 G.V.J.N.S.LAKSHMI KUMARI-178X1A0529
                                                                                                 KANAPARTHI.ANUSHA-178X1A0539
                                                                                                KUNCHALA.PADMAJA-178X1A0556
       GUIDE NAME:
       Mr.S.SURESH BABU
ASSOCIATE PROFESSOR
• Objective
• Abstract
• Existing system
         Contents • Proposed System
• Architecture
• Requirements
Objective
• To propose a new multimodal biometric human identification system using
deep learning algorithm.
                            Abstract 
• Increasing demand for information security and security regulations ,
biometric recognition technology has been widely used.
• Multimodal biometrics technology has gained interest and became popular.
• A multimodal based on a deep learning algorithm for recognizing humans
using biometric modalities of iris, face, and finger vein.
Continue..

• The structure of the system is based on convolutional neural networks.


• The performance of the proposed system is evaluated by conducting several
experiments on the SDUMLA-HMT dataset.
                        Existing system

• In general, deep learning models are not trained from scratch as deep
learning demands a large datasets.
• This is the reason why most researchers use pre-trained models, for
example: Inception,VGGNet, AlexNet, DenseNet
• Based on what has been observed in previous studies, this work develops an
model using CNN.
Proposed System

• Adopted the unimodal iris and face identification models


• Further ,a new finger vein unimodal will be developed
• The proposed multimodal model was developed using the three unimodal
models
                            Architecture
Software Requriments

• Programming languages – Python , Matlab


• Operating System – Windows 7 , Windows 10
Hardware Requirements

• Processor – Intel i3,i5


• RAM – 2GB
THANK YOU

You might also like