Project Report

On
Identification for Advanced Monitoring
System.
Advisor :- Prof . Siddharth Routaray

Submitted byAnupam Garain Kashyap

Abhishek Mishra
Ankita Chandra
Anupriya Kisku
(School of Computer Science and Engineering)
KIIT UNIVERSITY

Abstract: Fingerprint based personal identification is becoming more and more popular in
everyday life. Designing an accurate real identification system is of time automatic fingerpr int
great importance in many circumstances, and this topic has attracted lot of attention in the recent

time. In this paper we present a real time fingerprint recognition system based on a novel
fingerpri nt minutiae matching algorithm.
This project can be mainly decomposed into image preprocessing, feature extraction and feature
match and final report generation.
Keywords:
Introduction:
A fingerprint is a specific pattern of ridges and furrows on a finger. Each person has his own
fingerprints which are permanently unique. So fingerprints have been used for identification and
forensic investigation for a long time. As explained earlier a fingerprint consists of ridges and
furrows but it has been seen through research on fingerprint recognition, fingerprints are not
distinguished by their ridges and furrows, but by Minutia, which are some abnormal points on the
ridges.

ABOUT HARDWARE

Swipe based fingerprint from laptops

Generally a laptop uses Validity Sensor fingerprint scanners such as the VFS010,
VFS301, or VFS495. (Validity Sensor was bought by Symmantec). For enrolling or
verifying the fingerprint we have to swipe our finger on the scanner 3-4 times approx.
until we get a good fingerprint image .

Portable fingerprint scanners may be used after some modification in application

ABOUT SOFTWARE

We are using MATLAB for fingerprint recognition and matching process and for GUI

JAVA for network programming

MY SQL for storing fingerprint data

WHY MY SQL

Scalability and Flexibility

High performance
High availability
Robust Transactional Support
Web and Data Warehouse Strengths
Strong Data Protection
Comprehensive Application Development
Management Ease
Open Source Freedom
Lowest Total Cost of Ownership

WHY MATLAB

A very large (and growing) database of built-in algorithms for image processing
and computer vision applications

The ability to read in a wide variety of both common and domain-specific image
formats

The ability to call external libraries, such as OpenCV

A large user community with lots of free code and knowledge sharing

WHY JAVA
o

Java is Easy to learn

o Java is an Object Oriented Programming Language

o Powerful development tools e.g. Eclipse , Netbeans
o Great collection of Open Source libraries

Implementation:

WiFi
connected
(To the system)

MAC
filtered
Router is
connected

It will restrict the wifi to

confined space.

Message is transferred to the main server

Main Server

The process of finger print recognition can be grouped into two sub-domains: one is fingerpr int
verification and the other is fingerprint identification. The following steps are involved : First the
user provides his fingerprint then fingerprint verification system retrieves the fingerprint template
and matches the template with the real-time acquired fingerprint from the user. Usually it is the
underlying design principle of AFAS (Automatic Fingerprint Authentication System). Then the
fingerprint identification system tries to match his fingerprint with those in the whole fingerpr int
database and then a final report may be generated. So the following are the main steps involved:
1. Accepting of Fingerprint Image: The user provides the input (fingerprint) to the system
for scanning and verification.
2. Fingerprint Recognition: Each fingerprint is unique and is composed of ridges and
furrows but fingerprint recognition is based on minutia which are some abnormal points
on the ridges.

3. Fingerprint Image Enhancement: Fingerprint Image enhancement is to make the image

clearer for easy and accurate further operations. This is done by increasing the contrast
between ridges and furrows and for connecting the false broken points of ridges due to
insufficient amount of clarity. There are two methods for this : Histogram Equalization
and Fourier Transform method.

After Histogram equalization

After enhancement

before

4. Fingerprint Image Binarization : It is done to transform the 8-bit Gray fingerprint image
to a 1-bit image with 0-value for ridges and 1-value for furrows. After the operation,
ridges in the fingerprint are highlighted with black color while furrows are white.

Binarized image(left), Enhanced gray image(right)

5. Fingerprint Image Segmentation: In this step, only a Region of Interest (ROI) which is
useful to be recognized for each fingerprint image is separated and the remaining image
area is discarded.
6. Fingerprint Ridge Thinning : It is done to eliminate the redundant pixels of ridges till the
ridges are just one pixel wide. For this an iterative, parallel thinning algorithm is used in

which during each scan of the full fingerprint image, the algorithm marks down redundant
pixels in each small image window (3x3). And finally removes all those marked pixels
after several scans. .
7. Minutia Marking: After the fingerprint ridge thinning, marking minutia points is
relatively easy. In general, for each 3x3 window, if the central pixel is 1 and has exactly
3 one-value neighbors, then the central pixel is a ridge branch. If the central pixel is 1
and has only 1 one-value neighbor, then the central pixel is a ridge ending
8. False Minutia Removal :- In previous steps False ridges which breaks due to insuffic ie nt
amount of ink and cross-connections of ridges due to over inking are not totally
eliminated. These false minutia will definitely affect the accuracy of matching if they
are simply regarded as genuine minutia. So we apply mechanisms for removing false
minutia are essential to keep the fingerprint verification system effective Different types
of False Minutia are below :-

FEW STEPS FOR REMOVING FALSE MINUTIA :

If the distance between two bifurcations is less than D and they are in the same
ridge, remove the two bifurcations. (2nd, 3rd cases).

If the distance between one termination and one bifurcation is less than D and
the two minutia are in the same ridge(1st case) . Remove both . Where D is the
average inter-ridge width representing the average distance between two parallel
neighboring ridges .

If there exist two terminations in a distance D and the directions of terminatio ns

are coincident with a small angle variation. And if they suffice the condition that
there exists no other termination between the two terminations. Then the two
terminations are considered as false minutia derived from a broken ridge and are
removed. ( 4th,5th, 6th case).

9. Minutia Matching: Given two set of minutia of two fingerprint images, the minutia match
algorithm determines whether the two minutia sets are from the same finger or not. An
alignment-based match algorithm is used in my project. It includes two consecutive
stages: one is alignment stage and the second is match stage.
9.1 Alignment stage. From the two fingerprint images which has to be matched, choose any
one minutia from each image Now calculate the similarity between the two ridges
associated with the two referenced minutia points. If similarity is larger than threshold
transform each set of minutia to a new coordination system whose origin is at the
referenced point and whose x-axis is coincident with the direction of the referenced point.
9.2 Match stage: After the first step we get two set of transformed minutia points then we use
the elastic match algorithm to count the matched minutia pairs by assuming two minutia
having nearly the same position and direction. If the final match ratio is the number of
total matched pair over the number of minutia of the template fingerprint. The score is

100*ratio and ranges from 0 to 100. If the score is larger than a pre-specified threshold,
the two fingerprints are from the same finger .
10. Verification message sending :- If a successful match is found from the database and
the device is connected to a unique private wireless connection (i.e the wireless
connection which is established by institution for use in this purpose ) then a unique key
(i.e id no, roll no etc. ) is sent to the main server through wifi . For use in hostel
attendance from room the time interval is also fixed.
11. Report generation :- As per the user requirement a report is generated by the main system
which can be used in many ways.
CONCLUSION :My project has combined many methods to build a minutia extractor and a minutia matcher. These
multiple methods were combined through a wide investigation and thus concluded properly through our
presentation.. Also some changes like segmentation using Morphological operations, minutia marking
with special considering the triple branch counting, minutia unification by decomposing a branch into
three terminations, and matching in the unified x-y coordinate system after a two-step transformation
are used in my project, which are not reported in other google, thesis, presentations that we referred to.

Also a program coding with MATLAB going through all the stages of the fingerprint recognition is built.
It is helpful to understand the procedures of fingerprint recognition. And thus easily demonstrate the
important issues of fingerprint recognition. Thus we tried to save the time of students as they can give
their attendance through their respective rooms in hostels.

REFRENCES

 From google
From matlab student support and lectures