Vous êtes sur la page 1sur 13

‫الجامعة التقنية الوسطى‬

‫الكلية التقنية الهندسية‬


‫قسم هندسة الميكاترونكس‬

Security system Design Based on Human Face


Detection And Recognition
By / Moneer Mohamed Adnan
Yousif Raad Abd Al-Ameer
Mohamed Monther Fhdail

Supervised By :- Ghaith Abd Al-Wadood


A biometrics is a unique, measurable
characteristic of a human being that can be used
to automatically recognize an individual or verify
an individual identity.
a.Finger-scan
b.Facial Recognition
c.Iris-scan
d. Retina-scan
e. Hand-scan
f. Voice-scan
g. Signature-scan
h. Keystroke-scan
Deep Learning And Machine learning

Reinforcement
Facial recognition is a form of computer vision
that uses faces to attempt to identify a person
or verify a person’s claimed identity. For face
recognition there are some steps to be done
in order to recognize a face :
Steps for Face Recognition
Method for Detecting Face :
Before recognizing a face we need to detect it
first , there are many methods to detect faces
in image such as
• Support Vector Machine )SVM)
• Haar Cascaded
• Histogram of Oriented Gradients (HOG)
• etc…..
Histogram of Oriented Gradients (HOG)
position and Projecting Faces
• To correctly position a face we need 68 specific points
(called landmarks)
Encoding Faces(embedding)
Identification of a person
we need to do is train a classifier that can take in the measurements
from a new test image and tells which known person is the closest
match. Running this classifier takes milliseconds. The result of the
classifier is the name of the person!
Project Details
Component to be used
Microcontroller
1- IP Camera
2-electrical Door Lock
3-PIR Sensor
4-Computer-with
python software

Wi-Fi
What we Have Done So far
• All steps for face recognition has been finished (50% of the Project !)

Vous aimerez peut-être aussi