This document proposes an automatic attendance management system using face recognition. It begins by outlining the costs associated with employee tardiness and discusses existing attendance tracking methods like barcode readers and fingerprint scanners. It then proposes a system using face recognition for contactless, effortless tracking. The system would detect faces, recognize individuals, convert group photos to single photos, recognize faces, and export attendance data to an excel sheet. The document provides details on face detection and recognition methods, specifically PCA, and discusses advantages like reduced time and errors in attendance tracking.
2. WHY TO BUY ATTENDANCE
MANAGEMENT SYSTEM?
Have you ever thought how
much money Companies lose
because of employees being
late?
3. Let’s do a simple calculation…
In case you have 50 employees
working 5 days a week for 8 hours per day,
receiving 150 000 salary per month,
and being late for 15 minutes each day,
…you are losing
approximately 2 800 000 per year
+
money spent for manually calculating
employee’s worked hours
+
money spent for making reports
5. WHY FACE RECOGNITION?..
• Non contact process
• Zero effort from user
• Computer based digital technology
• Compare face of persons with training images
6. PROPOSED SYSTEM
Automatic Attendance Management System:
Is a user-friendly, flexible and full featured employee
or student attendance management tool which
allows controlling employees attendance OR
students attendance in college by automating time
keeping and attendance tracking.
captures data from Time and Attendance Terminals,
and simultaneously allows optional PC entry
8. BLOCK DIAGRAM
• Photo is taken.
• Image is processed
• Compare with training images in database
• For comparison group photo is divided into
single photos.
• System export attendance list into excel sheet
10. FIVE PHASES
1. Face detection of image
2. Face recognition of single face
3. Convertion of group photo to many single
photos
4. Recognition of all faces in a group photo
5. Export data to an excel sheet
11. Phase 1
Face detection of image
• Identifies human faces in digital image
• Computer technology
• Special case of object class detection
• Similar to image detection
• Viola jones algorithm is used
• Not size limited and it is able to detect faces
from group images and detect images rapidly
13. Phase 2
Face recognition of single face
• Computer application capable of identifying and
verifying a person from a digital image.
FACE RECOGNITION APPROACHES
• Analysis face in terms of local features
• LFA method-Better robustness against local variations
• Here uses PCA method for face recognition
14. • Principal Component Analysis(PCA)
a. Used in face recognition and image compression
b. Used for finding patterns in data
ADVANTAGE OF PCA
i. Simplest , used for data compression and face
recognition
ii. Operates at faster rate
15. FACE RECOGNITION USING PCA
• Face is considered to be one of the most
important visual objects for identification.
• Face recognition is an effective means of
authenticating a person.
• Highly efficient
• Used in security systems.
16. • Recognition of human face is complex
• Converts the face into a mathematical model.
17. PCA METHOD
• Uses orthogonal transformation.
• Reduced data size.
• Dimension reduces
• Removes unwanted information
• Decompose into principal components
• The test image can be constructed using
weighted sums of Eigen faces.
18. PCA METHOD
• Images in training set as a linear combination
of weighted Eigen vectors.
• The system receives the input face and it is
recognized from the training set.
• Test image weight are computed
• Distances are computed
• Stimulated by matlab
19. ALGORITHM
• Let {D1,D2,…DM} be the training data set. The
average
• Avg is defined by:
AVG=(1÷M)£Di
• Yi=Di-Avg.
• Covariance matrix is formed
23. Phase 4
Recognition of all faces in a group photo
• System will automatically select the test
images
• Find equivalent images for each images and
display it.
25. Key Features
Devices have different Security Levels thus ensuring
that only authorized persons can delete transactions
from them, enroll new employees or change
settings.
Is a CLIENT/SERVER system
Can be accessed also via INTERNET
26. Key Features
Has USER-FRIENDLY interface
Supports UNLIMITED number of users,
policies, shifts, divisions, departments and
other objects
Zero effort from the user
More secure and time efficient
27. ADVANTAGES
Attendance Management System can improve
company's productivity by:
Reducing time for calculating worked hours and
wages
Eliminating mistakes made during calculations
Reducing time needed to verify attendance data
Reducing time for making reports and sending
them to top management
28. REFERENCE
• [5] Mrunmayee Shirodkar,Varun Sinha,Urvi Jain and Bhushan Nemade, ”Automated
Attendance Management System using Face Recognition”, International
Conference and Work- shop on Emerging Trends in Technology (ICWET 2015)
• [2] Seema Verma Prof. Sonu Agrawal, ”A Study on A Soft Biometric Approach: Face
Recognition”, International Journal of Advanced Research in Computer Science and
Software Engineering, Volume 3, Issue 3, March 2013.
• [4] Faizan Ahmad, Aaima Najam and Zeeshan Ahmed, ”Image-based Face
Detection and Recognition: State of the Art”,IJCSI International Journal of
Computer Science Issues, Vol. 9, Issue 6, No 1, November 2012.
29. REFERENCE
• [3] William Robson Schwartz, Member, IEEE, HuiminGuo, Student
Member, IEEE, Jonghyun Choi, Student Member, IEEE, and Larry S. Davis,
Fellow, IEEE, ”Face Identi- fication Using Large Feature Sets”, IEEE
TRANSACTIONS ON IMAGE PROCESSING, VOL. 21, NO. 4, APRIL 2012
• 1] P. N. Belhumeur, J. P. Hespanha and D. J. Kriegman, ”Eigenfaces vs.
Fisherfaces: recog- nition using class specific linear projection”, Published
in: IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume:19 , Issue: 7 ,Aug 2002.