Professional Documents
Culture Documents
INFORMATION TECHNOLOGY
DEPARTMENT OF MECHATRONICS
TAIZ UNIVERSITY
BY:
01 Amer Al-basser
02 Amr Al-sabaeei
03 Hesham Al-khateeb
Supervisor:
04 Mohammed Moghalies Dr/ Ghazi Alnowaini
05 Alaa Alshargaby
Outline
01 Introduction
Overview, Problem statement, Objectives, Importance
02 Related Work
Review of The Previous Studies
05 Conclusion
What did We Conclude from Results
06 Future Work
1. Introduction
1.1 Overview
➢Secondary Objectives
❖Looking for an algorithm that can be used in attendance systems with the right
methods.
❖Allow the use of today's most advanced computer vision techniques and secure
software systems in any facility.
❖Real time detecting, recognizing and tracking faces.
1. Introduction
1.3 Scope
❖Using deep learning algorithms for detecting, recognizing and tracking faces in
real time.
01 FACE DETECTION
02 DATA GATHERING
04 TRAINING DATA
Training the Recognizer Face Tracking generally works when the camera catches
the person face. After tracking a face or faces, the
The images in the created list retrieved from the csv will haarCascade recognizer uses data from the
then be pumped into a recognizer which is the LPBH (Trainner.yml) file to predict whose face it is. The
Recognizer (a library provided by OpenCV) to do the LBPHFaceRecognizer in OpenCV takes a captured
training. portion of the face to be analyzed as a parameter and
returns its likely owner, including its id and how
confident the recognizer is in this match.
❖As we have a facial image in grayscale, each histogram (from each grid) will contain only
256 positions (0~255) representing the occurrences of each pixel intensity.
❖Then, we need to focus each histogram so that we can create a new histogram. Supposing
we’ve 8x8 grids, we will have 8x8x256=16.384 positions in the final histogram. The final
histogram represents the better characteristics of the initial image.
4. Design of the project and Results
Wooden Box
4. Design of the project and Results
Board
4. Design of the project and Results
❑ Operating voltage: 5V
Arduino
4. Design of the project and Results
4.3 Software
Front-End-Design
System Interface
4. Design of the project and Results
4.4 Results
Result 1
4. Design of the project and Results
4.4 Results
Result 2
5. Conclusion
➢Face tracking and attendance system, using deep learning based on face detection
➢HOG and CNN layers, were used for feature extraction and detecting faces in an image
or video respectively.
➢LBPH and OpenCV were combined together to successfully introduce face recognition.
➢Arduino Uno controls the motion of servo motors while camera tracks the face.
➢The Attendance process is done automatically and saved in excel sheet as a csv file.
6. Feature Work
➢For academic facilities we will add an electronic lock circuit to work with the proposed
system to be used in gates and doors.
Any Question?