Scribd
Upload
25 views

Project Abstract

The document discusses a project focused on deep learning based feature extraction and recovery for finger-vein verification. The project is being conducted by Helene.S and Sujithra.R and aims to enhance security protection. The abstract then discusses how finger-vein biometrics have been extensively researched for personal verification and the project proposes a deep learning model combining known segmentation techniques to automatically identify clear and ambiguous regions in finger-vein images for biometric authentication.

Uploaded by

sujithrasuji773
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
25 views

Project Abstract

The document discusses a project focused on deep learning based feature extraction and recovery for finger-vein verification. The project is being conducted by Helene.S and Sujithra.R and aims to enhance security protection. The abstract then discusses how finger-vein biometrics have been extensively researched for personal verification and the project proposes a deep learning model combining known segmentation techniques to automatically identify clear and ambiguous regions in finger-vein images for biometric authentication.

Uploaded by

sujithrasuji773
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

TEAM MEMBERS : Helene.S(20TC0055),Sujithra.

R(20TC0069)
PROJECT TITLE : Deep Learning Based Feature Extraction And
Recovering For Finger-Vein Verification
PROJECT FOCUS : Extraction And Recovering Of Finger- Vein
Verification to Enhance The Protection For Security

ABSTRACT :
The Tremendous growth in the demand for secured
System, automatic personal verification using biometric has drawn
Increasing attention in today’s world. Finger-vein biometrics has been
Extensively investigated for personal verification to proposes a deep
learning model based on a combination of known state of the art
handcrafted finger-vein image segmentation techniques, we
automatically identify two regions: a clear region with high
separability between finger- vein patterns and background, and an
ambiguous region with low separability between them. A biometric
authentication system is a real time system to verify person’s identity
by measuring particular characteristic or behavior of the person’s
body biometric devices with all the registered pattern in the database.
Finger-vein recognition can be considered as an image classification
problem. It must be interesting to use CNN to handle the finger vein
recognition problem. CNN usually perform well even better
connectional computer vision method because they are very good at
extracting features from images automatically. we employ several
baselines approaches to extract segments of vein network from an
image and use their combined output automatically to assign a label
for each pixel. An automatic scheme to label pixels in vein regions
and background regions, given very limited human knowledge. It
consists of clear region and ambiguous region, employed to
automatically label pixels as vein or background in the image is clear.

You might also like