AUTOMATED CRIMINAL IDENTIFICATION

SYSTEM
USING FACE DETECTION AND
RECOGNITION
Presented by:
1)Akanksha veer
Roll No:30
Enrollment no:2207100773
Div:C

2) Rajshri yadav
Roll No:69
Enrollment No:2207100131
Div:A

3) Riya Lawange
Roll No:62
Enrollment No:2207100222
Div: B

4) Vishakha khaladkar
Roll No:66
Enrollment No: 2207100672
Div: B
CONTENTS
• INTRODUCTION

• ALGORITHM

• FLOWCHART

• ER DIAGRAM

• CLASS DIAGRAM

• DFD LEVEL

• CODE WITH OUTPUT

• KEY POINTS AS ADVANTAGES

• REFERENCES
 INTRODUCTION
• The face is crucial for human identity. It is the feature which best distinguishes a person. Face
detection and recognition is the technology which is used to identify a person from a video or
image .
• we propose a face detection and recognition system for criminal identification using python
along with OpenCV package.
• Most of the common facial recognition techniques include target matching method, geometric
feature recognition method, and principal component analysis method and so on. Most of the
criminals are mingled with us in our society and they are much hard to identify.
• Traditionally, repeated criminals are identified by their biometrics such as thumbprint. But
criminals are smart enough to not to leave their biometrics in crime scene .
• In developed countries, the government create dataset which is helpful for recognize the human
face which compares the suspicious act with trained dataset and information stored in database .
• This technology is a widely used biometrics system for authentication, authorization,
verification and identification .
• Applying principal component analysis for finding distinguishable features from many images to
get the similarity for the target image.
 ALGORITHMS

• Convolutional Neural Networks (CNNs):

CNNs excel in image processing, making them ideal for face recognition tasks.

• Principal Component Analysis (PCA):

PCA reduces dimensionality, enhancing the efficiency of facial feature extraction.

• NIST Findings:
NIST reports highlight algorithm efficiency, particularly in complex environments.

• DeepFace Technology:
Achieving a remarkable 97% accuracy, DeepFace sets a benchmark in face
recognition.
FLOWCHART
ER DIAGRAM
CLASS DIAGRAM
DFD LEVEL 0
DFD LEVEL 1
DFD LEVEL 2
 CODE WITH OUTPUT
// CPP program to detects face in a video

// Include required header files from OpenCV

#include "/usr/local/include/opencv2/objdete

#include "/usr/local/include/opencv2/highgui

#include "/usr/local/include/opencv2/imgproc

#include <iostream>

using namespace std; using namespace cv;

// Function for Face Detection void detectAndDraw( Mat& img,

CascadeClassifi CascadeClassifier& nestedCas );

string cascadeName,
nestedCascadeName;

int main(int argc, const char** argv)

{

// VideoCapture class for playing video be detected VideoCapture capture;

Mat frame, image;
 // PreDefined trained XML classifiers wi CascadeClassifier cascade,
nestedCascade double scale=1;

// Load classifiers from "opencv/data/ha directory

nestedCascade.load( "../../haarcascade_eye_tree_eyeglasses.xml"

// Change path before execution

cascade.load( "../../
haarcascade_frontal

// Start Video..1) 0 for WebCam 2) "Path Local Video capture.open(0);

if(capture.isOpened())

// Capture frames from video and det cout << "Face Detection Started...."
while(1)

capture >> frame; if(frame.empty()) break;

Mat frame1 frame.clone(); detectAndDraw(frame1, cascade, scale );

}

char c = (char) waitKey(10);

\\Press q to exit from window if(c== 27 || c == 'q' || c == break;

else
cout<<"Could not Open Camera";

return 0;

}
 KEY POINTS AS ADVANTAGES
 Increased Accuracy:
Automated systems enhance the precision of criminal identification, reducing human error
significantly.

 Faster Processing Time:

These systems enable rapid processing, leading to quicker decision-making compared to
traditional manual methods.

 Efficient Data Handling:

Automated systems can manage and analyze large datasets efficiently, improving overall
operational effectiveness.
 REFERENCES
 NIST Report on Facial Recognition:
A comprehensive report detailing the performance and evaluation of facial recognition
systems.

 Facial Recognition Statistics:

Provides key statistics on market trends and user adoption of facial recognition technologies

 CompTIA Ethical Issues in Technology:

Explores the ethical implications of using facial recognition in various sectors, including law
enforcement.

 Additional Academic and Industry Sources:

Incorporates various research papers and articles that further elaborate on the technology’s
applications.
 WHERE WE USE THIS SYSTEM

Fraud detection:
Companies use facial recognition to uniquely identify users creating a new account on an online platform.
After this is done, facial recognition can be used to verify the identity of the actual person using the
account in case of risky or suspicious account activity.
Cyber security:
Companies use facial recognition technology instead of passwords to strengthen cybersecurity measures. It
is challenging to gain unauthorized access into facial recognition systems, as nothing can be changed about
your face. Face recognition software is also a convenient and highly accurate security tool for unlocking
smartphones and other personal devices.
Airport and border control:
Many airports use biometric data as passports, allowing travellers to skip long lines and walk through an
automated terminal to reach their gate faster. Face recognition technology in the form of e-Passports
reduces wait times and improves security.
Banking:
Individuals authenticate transactions by simply looking at their phone or computer instead of using one-
time passwords or two-step verification. Facial recognition is safer as there are no passwords for hackers to
compromise. Similarly, some ATM cash withdrawals and checkout registers can use facial recognition for
approving payments.
Healthcare:
Facial recognition can be used to gain access to patient records. It can streamline the patient registration process in
a healthcare facility and autodetect pain and emotion in patients
How does facial recognition work?
Facial recognition works in three steps: detection, analysis, and recognition.
Detection:
Detection is the process of finding a face in an image. Enabled by computer vision, facial recognition can detect
and identify individual faces from an image containing one or many people's faces. It can detect facial data in
both front and side face profiles.

Computer vision:
Machines use computer vision to identify people, places, and things in images with accuracy at or above human
levels and with much greater speed and efficiency. Using complex artificial intelligence (AI) technology,
computer vision automates extraction, analysis, classification, and understanding of useful information from
image data. The image data takes many forms, such as the following:
Single images
Video sequences
Views from multiple cameras
Three-dimensional data
1. Start page:
2. Register a Criminal
3. Detect Multiple persons from photo
4. Details of criminal
5. Detect criminal from photo
6. Detect criminals from video survellance
Thank
You