You are on page 1of 4

DIGITAL SIGNAL PROCESSING PROJECT

FINGERPRINT RECOGNITION USING MATLAB

TEAM MEMBERS:
Advaith.S: AM.EN. U4ECE21105
Vaishnav.C. Sajkumar: AM.EN. U4ECE21159

INTRODUCTION:
Fingerprint recognition refers to the automated method of identifying or confirming the
identity of an individual based on the comparison of two fingerprints. Fingerprint recognition
is one of the most well-known biometrics, and it is by far the most used biometric solution for
authentication on computerized systems. The reasons for fingerprint recognition being so
popular are the ease of acquisition, established use and acceptance when compared to other
biometrics, and the fact that there are numerous sources of this biometric on each individual.
THEORY:
Fingerprint recognition is a computerized system that uses fingerprint images to identify and
verify human fingerprint similarities. It is widely used in real-world authentication
applications due to its simplicity, global acceptance, and ease of image acquisition.
Fingerprint recognition systems consist of four stages: image acquisition, preprocessing,
feature extraction, and feature matching. The main goal is to compare fingerprint images to
verify if the impression belongs to the same individual. Fingerprint recognition systems are
popular among researchers and industrial professionals due to their consistency, uniqueness,
and permanency. Fingerprint recognition processes involve image acquisition, preprocessing,
feature extraction, and matching. Fingerprint patterns are crucial for narrowing search areas
and are inherited from generation to generation. Fingerprint recognition systems use various
types of fingers, including S-type, tent, whorl, balloon, arch, left loop, eddy loop, and right
loop. Fingerprint patterns are inherited and can be passed down from generation to
generation. Fingerprint recognition is a challenging task due to distortion and noise in
fingerprints, making it crucial to develop accurate matching techniques. The Automatic
Fingerprint Recognition System (AFRS) relies on minutiae features, which can be improved
through pre-processing algorithms, feature extraction algorithms, post-processing algorithms,
image enhancement algorithms, and image quality. Parameters, such as pre-processing,
feature extraction, post-processing, image enhancement, and image quality, play a crucial
role in enhancing the performance of fingerprint recognition systems.
Fingerprint recognition performance is influenced by several parameters, including pixel
number, resolution, and area. Challenges include low image quality, inaccurate performance,
and insufficient automated classification techniques. To improve performance, new
fingerprint recognition systems should include image enhancement modules, reduce false
reject and false accept rates, and improve the accuracy of the system. Additionally,
advancements in computing abilities are needed to enhance the classification methods of
Automated Fingerprint Authentication Systems (AFIS).
Our developers analyze emerging research challenges in fingerprint recognition using Matlab
and design algorithms to tackle complexity effectively. Fingerprint features are extracted
from friction ridges, classified into ridge features, macroscopic ridge patterns, and minutiae
features. These unique patterns have characteristics like uniqueness, permanence,
consistency, and reliability.
Fingerprint recognition features include ridge contour, pores, flow patterns, and minutiae
features. Our developers use advanced feature extraction techniques to analyze these features,
guiding clients on the right path for their project goals. We offer methods like radius feature-
oriented, correlation-oriented, coefficient of correlation, minutiae-oriented, gray-scale, and
binarization. We also support other developing techniques and algorithms, ensuring accurate
extraction of essential features even in low-quality images. Image enhancement and feature
extraction are essential operations in fingerprint recognition systems, with image
enhancement and feature extraction being the most important functions.
MATLAB is a sophisticated tool for developing fingerprint recognition systems, offering
open-source support for Python, OpenCV, TensorFlow, and OnnX. It supports various
programming languages, including Java, C++/C, Python, and Fortran. MATLAB allows for
the integration of code from other languages, allowing for error-free programming for
hardware and inter-responsive websites. It supports various cameras, including Matrix
Vision, Lumenera, and Point Grey, for real-time image and video collection. The Image
Acquisition Toolbox from Matlab projects supports various cameras, making it suitable for
real-time image and video collection.

ALGORITHM:
1.Acquire fingerprint images from any source and load the image into MATLAB variables.
2.Perform preprocessing – Do image enhancement to both images and implement
binarization.
3.Extract features from the enhanced images by using MATLAB library.
4.Compare the extracted feature to determine the similarity score
5.Display the output
CODE:
% Step 1: Load the fingerprint images
image1 = imread('jk.jpg');
image2 = imread('kl.jpg');

% Step 2: Preprocessing - Enhance the fingerprint images


enhancedImage1 = preprocess(image1);
enhancedImage2 = preprocess(image2);

% Step 3: Feature extraction - Extract features from the enhanced images


features1 = extractFeatures(enhancedImage1);
features2 = extractFeatures(enhancedImage2);

% Step 4: Matching - Compare the extracted features to determine similarity


similarity = matchFeatures(features1, features2);

% Step 5: Result - Display the similarity score


fprintf('Similarity score: %.2f\n', similarity);

% Display results
imshow(image1);
title('Fingerprint 1');
figure;
imshow(image2);
title('Fingerprint 2');
fprintf('Similarity: %.2f%%\n', similarity * 100);

% Preprocessing function
function enhancedImage = preprocess(image)
enhancedImage = histeq(image);
end

% Feature extraction function


function features = extractFeatures(image)
[~, features] = extract_minutiae(image, 'FINGERPRINT', true);
end

% Matching function
function similarity = matchFeatures(features1, features2)
similarity = match(features1, features2);
end

You might also like