Tezislər / Theses



Yüklə 17,55 Mb.
Pdf görüntüsü
səhifə158/493
tarix02.10.2023
ölçüsü17,55 Mb.
#151572
1   ...   154   155   156   157   158   159   160   161   ...   493
BHOS Tezisler 2022 17x24sm

THE 3
rd
 INTERNATIONAL SCIENTIFIC CONFERENCES OF STUDENTS AND YOUNG RESEARCHERS 
dedicated to the 99
th
anniversary of the National Leader of Azerbaijan Heydar Aliyev
167
3. Detect face boundaries and face landmarks, which are the 
unique 
features
of each face. 
4. Make 
measurements
of specific parameters of faces, such as 
distance between eyes, etc. and compare with the previously 
trained data, using the Deep Convolutional Neural Network 
(DCNN) and support vector machine classifier (SVM) 
algorithms.
Design Architecture 
The attendance checking system will perform this face recognition 
algorithm to detect the attendees and will output the attendance list. The 
system architecture has been shown in the Figure 2.
Figure 2.
Attendance checking system architecture 
With a camera, a person’s image is captured, and the face 
recognition system detects face landmarks, encodes to the face 
measurements, and compares the results 
with
the database. If the 
matching face is found in the database, user’s name is written in the 
csv file together with the joining time. 
Methodology 
To achieve this system, Python is preferred. The required libraries 
for that project are: 
OpenCV-python: This library combines more than 10 modules, 2 
of which are used in this system: Image Processing and Video I/O.
1. Image Processing module 
is used for linear/non-linear filtering, 
geometric image transformation, color space conversion, etc. 
 
2. Video I/O module 
is utilized for taking video/video-codecs.
 
Dlib: 
This one is written for C++ and combines several ML algorithms. 
For example, we will use deep learning, SMO based regression, SURF, 
HOG, FHOG, etc. 
Face recognition: 
It is used to detect the patterns of faces. 



Yüklə 17,55 Mb.

Dostları ilə paylaş:
1   ...   154   155   156   157   158   159   160   161   ...   493




Verilənlər bazası müəlliflik hüququ ilə müdafiə olunur ©azkurs.org 2024
rəhbərliyinə müraciət

gir | qeydiyyatdan keç
    Ana səhifə


yükləyin