The document presents an embedded real-time finger-vein recognition system for mobile devices. The system uses finger vein patterns as a biometric for authentication through image acquisition of the finger veins, processing the images through segmentation, enhancement and feature extraction, and human-machine communication. It was found to have high security, low power consumption, small size, quick response time of 0.8 seconds, and high accuracy with a low equal error rate of 0.07%.

1. An Embedded Real-Time
Finger-Vein Recognition
System
for Mobile Devices
PRESENTED BY
N.LAKSHMI SHAMILI
III B.TECH,ECE
SVEW

2. BIOMETRICS


Unique measurable characteristics of a human being that
can be used to automatically recognize an individual or
verify an individual identity.
Used for security authentication.

3. FINGER VEIN
AUTHENTICATION
TECHNOLOGY
 A promising biometric
pattern for personal
identification in terms
of its security and
convenience.
 Uses
DSP platform.
 Takes
only about 0.8
seconds to verify one
input finger- vein
sample.

4. VEIN RECOGNITION
A system for
Identification using
a person’s unique
vein patterns.
 Veins as a
biometrics tool
involve the
measurement of
the blood vessels
on the back of
your palm or a
single finger of
hand.


5. OVERVIEW OF THE PROPOSED
SYSTEM

IMAGE
ACQUISITION

PROCESSING

HUMAN-MACHINE
COMMUNICATION
MODULE

6. IMAGE ACQUISITION
It uses four modules
 NIR
light source
 Transparent acryl
 Daylight cut-off
filters
 Monochromatic
camera

7. FLOW CHART OF PROPOSED
RECOGNITION ALGORITHM
Input finger-vein
images with
corresponding ID
Input finger-vein
images with
corresponding ID
Segmentation and
Alignment
Segmentation and
Alignment
Enhancement
Enhancement
Feature Extraction
Feature Extraction
Feature Templates
Matching
Accept or reject

8. IMAGE SEGMENTATION &
ALIGNMENT
Segmentation
Alignment
Between
two joints
Normalization
Canny
operator
Midline
Rotate

9. IMAGE ENHANCEMENT:
 Enhanced to
improve its
contrast.

Resized

Histogram
equalization

10. FEATURE EXTRACTION & MATCHING

Lacunarity

Quantify the denseness

Spatial heterogeneity

Matching (hamming distance)

11. EXPERIMENTAL RESULTS
DATA SET:
 100 subjects (55% male and 45%female)
 Images from the forefinger, middle
finger, and ring finger.

12. PERFORMANCE EVALUATION

Two types of errors
FALSE
REJECTION
RATE(FRR)
• which claims a
genuine pair as
impostor
FALSE
ACCEPTANCE
RATE(FAR)
• which claims an
impostor pair as
genuine
FRR
FAR
EER

13. APPLICATION AREAS

14. CONCLUSION








Highly Secure
Low power consumption
Low computational complexity
High Accuracy
Less Expensive
Small size
Quick response(0.8s)
Low EER (0.07%)