automated attendance system based on facial recognition

Project Guide : Asst. Prof. Chethan R

Team Members

Automated Attendance System based on Facial

Recognition

Rakshitha Suvarna S R DhanushShreeraksha Shetty Sushmitha Acharya

4MW12EC059 4MW12EC065 4MW12EC075 4MW12EC088

• Objective

• Literature Survey

• Methodology

• MATLAB toolbox

• Viola-Jones algorithm

• Eigenface approach to face recognition

• System implementation

• Results and analysis

• Pros and cons

• Applications

• Future scope and conclusion

• References

Contents

In this project we aim to build an Attendance marking system with the help of facial recognition owing to the difficulty in the manual as well as other traditional means of attendance system.

Objective

• “Eigenfaces for Recognition” [1],(Matthew Turk and Alex Pentland)

• “Fast Face Recognition Using Eigen Faces” [2], (Arun Vyas, Rajbala Tokas)

• “ Robust Real-Time Face Detection” [3], ( Paul Viola and Michael J. Jones)

Literature Survey

Methodology

• Camera captures the image of a classroom

• The faces are detected and cropped

• Cropped images are processed using Eigen face recognition algorithm

• The students whose faces are recognized are marked as present and the results are transferred to an excel sheet automatically

MATLAB (matrix laboratory) is a multi-paradigm numerical computing environment and fourth-generation programming language. Its one of the easiest and most productive software development environment for engineers.

MATLAB

• Image processing toolbox

• Image acquisition toolbox

• Computer vision toolbox

• Spreadsheet Link Ex

MATLAB toolboxes used

• This is used for face detection process Three basic steps of algorithm

1. Integral image for feature computation

2. Adaboost algorithm for feature selection

3. Cascade classifiers

Viola-Jones Algorithm

First step of the Viola-Jones face detection algorithm is to turn the input image into

an integral image. This is done by making each pixel equal to the entire sum of all

pixels above and to the left of the concerned pixel.

1 1 1

1 1 1

1 1 1

Input image

1 2 3

2 4 6 Sum of gray value = D-(B+B) + A

3 6 9

Integral image

Integral Image

• As stated above there can be calculated approximately 160.000 feature values within a detector at base resolution.

• AdaBoost is a machine learning boosting algorithm capable of constructing a strong classifier through a weighted combination of weak classifiers. A weak classifier is mathematically described as:

h(x,f,p,t)=1 pf(x)>t

0 else

• Where x is a 24*24 pixel sub-window, f is the applied feature, p the polarity and t the threshold that decides whether x should be classified as a positive (a face) or a negative (a non-face)..

AdaBoost Algorithm

• In stead of finding faces, the algorithm should discard non-face

Cascade Classifiers

• Face is a typical multidimensional structure and needs good computational analysis for

recognition

• Many face features make development of facial recognition systems difficult.

• This problem is solved by the method called Principal Component Analysis or so called

eigen face approach.

• This approach transforms faces into a small set of essential characteristics, eigenfaces,

which are the main components of the initial set of learning images (training set).

• Recognition is done by projecting a new image in the eigenface subspace, after which the

person is classified by comparing its position in eigenface space with the position of

known individuals

Eigenface approach to Face Recognition

• The first thing we need to do is to form a training data set. 2D image Ii can be represented as a 1D vector by concatenating rows . Image is transformed into a vector of length N = mxn.

• Let M such vectors xi (i = 1, 2... M) of length N form a matrix of learning images, X.

• First we determine the vector of mean values Ψ, and then subtract that vector from each image vector.

• Averaged vectors are arranged to form a new training matrix (size NxM)

• The next step is to calculate the covariance matrix C, and find its eigenvectors and eigenvalues

Where

• Covariance matrix C has dimensions NxN .

• From that we get N eigen values and eigenvectors.

• If νi and μi are eigenvectors and eigen values of matrix C, eigenvector associated with the

highest eigenvalue reflects the highest variance, and the one associated with the lowest

eigenvalue, the smallest variance.

• Therefore, the vectors should be sorted by eigenvalues so that the first vector corresponds to

the highest eigenvalue .

• These vectors are then normalized. They form the new matrix E so that each vector is a column

vector. The dimensions of this matrix are NXD, where D represents the desired number of

eigenvectors.

• The last step is the recognition of faces.

• Image of the person we want to find in training set is transformed into a vector P, reduced by the mean value Ψ and projected with a matrix of eigenvectors (eigenfaces)

•

• Classification is done by determining the distance, εi, between ω and each vector of

matrix Y.

• Where

• The most common is the Euclidean distance.

• If A and B are two vectors of length D, the Euclidean distance between them is

determined as follows

• If the minimum distance between test face and training faces is higher than a

threshold θ, the test face is considered to be unknown; otherwise it is known and

belongs to the person in the database.

• System Flowchart

System Implementation

Start

Image Processing

Update the attendance sheet in MS Excel

• Image Processing

Start

Capture image

Face Detection and cropping

Face recognition using Eigenfaces

Store recognized entries

Collection of training set

Results and Analysis

Image capturing, Face detection and Cropping

Face Recognition

Output in MS Excel

• Easy integration

• Simple algorithm

• Easy to use output format

• Proxy attendance is eliminated

• Saves time

Pros

• Sensitive to lighting variations

• Initial investment could be high

Cons

• All educational institutions

• Virtual classrooms

Applications

The system we have developed has successfully able to accomplish the task of marking the attendance in the classroom automatically and output obtained in an excel sheet as desired in real time. Another important aspect where we can work is towards creating an online data base of the attendance and its automatic updating, keeping in mind growing popularity of internet of things.

Future Scope

In the system we have implemented an attendance system for a lecture, section or laboratory by which lecturer or teaching assistant can record student attendance. Its saves time and effort, especially if it is a lecture with huge number of students.

Conclusion

[1] M. T. a. A. Pentland, "Eigenfaces For Recognition," Journal of Cognitive Neuroscience, vol. 3, no. 1, 1991.

[2] A. V. a. R. Tokas, "Fast Face Recognition Using Eigen Faces," IJRITCC, vol. 2, no. 11, pp. 3615-3618, November 2014.

[3] Paul Viola and Michael J. Jones, "Robust Real-Time Face Detection," International Journal of Computer Vision, vol. 57, no. 2, pp. 137-154, May 2004.

[4] N. J. M. M. K. a. H. A. Mayank Agarwal, "Face Recognition Using Eigenface approach," IRCSE, vol. 2, no. 4, pp. 1793-8201, August 2010.

References

Thank You