Attendance System Using Face Recognition Presentation u have to do the intro and problem statement Introduction [Max 2 pages] Problem Statement [1 page]

Attendance System Using Face Recognition Presentation u have to do the intro and problem statement

Introduction [Max 2 pages]

Problem Statement [1 page]

the intro has been written just read it and if u feel It needs any edit or add do it

and the start on the problem statement

the full doc will be submitted 1
ATTENDANCE SYSTEM USING FACE RECOGNITION
Introduction
Taking attendance is a boring task and in conventional attendance system there are some
issues like fake attendance, lot of time consumption, manipulation of attendance and information
cannot be secure. These issues can be overcome by automating the attendance system.
Biometric access control are automated methods of verifying or recognizing the identity of
a living person based on some physiological characteristics, such as fingerprints or facial features,
or some aspects of the person’s behavior, like his/her handwriting style or keystroke patterns. Since
biometric systems identify a person by biological characteristics, they are difficult to forge. Face
recognition is one of the few biometric methods that possess the merits of both high accuracy and
low intrusiveness. It has the accuracy of a physiological approach without being intrusive. For this
reason, since the early 70’s (Kelly, 1970), face recognition has drawn the attention of researchers
in fields from security, psychology, and image processing, to computer vision.
This project main aim is to automate the attendance system by integrating the face
recognition technology using Python, React and SQL. For the front end, we use React and for the
backend, we use Python to create API which request and receive data. To maintain the data in a
database we use SQL. With the help of face recognition, we can save time and effort and it handles
the data securely. It stores the faces that are recognized and automatically marks the attendance.
Limitations: There are some limitations in this approach, it is more expensive, strong influence of
the camera angels, image quality and lighting which could be moving and missed to check the
similarity.
Scope: The face recognition is popular in recent times. Most of the devices are having this feature.
Many organizations, universities and schools are using this technology to recognize and verify the
candidates. In most of the exams like GMAT, GRE, IELTS and other professional certification
exams, this technology is most useful and gives the most accurately recognize the candidates.
Deliverables: We can easily and efficiently mark the attendance through face recognition. Security
of the data is maintained throughout the process.
Non–Deliverables: If the person is moving all the time while recognition, it may lead to some of
the fault results and if the person went through some kinds of face surgery, then the database could
not able to find the person.
2
Problem Statement
Identify the problem behind the project. This section should briefly describe why you are
conducting the study. It should NOT describe the goal of your project.
Objective & Scope
Aim: The aim of this project is to offer system that simplify and automate the process of recording
and tracking students’ attendance through face recognition technology. It is biometric technology
to identify or verify a person from a digital image.
Objectives: Our primary goal is to help the institutions to improve the process of tracking and
managing the student attendance. Additionally, we seek to:
1. Provide a valuable attendance service for both lecturers and students.
2. Reduce manual process errors by providing automated and a reliable attendance system by
using face recognition technology.
3. Produce monthly reports for lecturers.
4. Increase the flexibility of editing attendance records.
5. Calculate absenteeism percentage and send reminder messages to students.
6. Automate the update in the database without human intervention.
Literature Review
Face recognition is one of the few biometric methods that possess the merits of both high accuracy
and low intrusiveness. Many researchers have proposed different face recognition techniques,
motivated by the increased number of real-world applications requiring the recognition of human
faces. There are several problems that make automatic face recognition a very difficult task.
However, the face image of a person inputs to the database that is usually acquired under different
conditions. The importance of automatic face recognition is much be cope with numerous
variations of images of the same face due to changes in the following parameters such as
1. Pose
2. Illumination
3. Expression
3
4. Motion
5. Facial hair
6. Glasses
7. Background of image.
Face recognition can be done in both a still-image and video sequence which has its origin in stillimage face recognition. Different approaches of face recognition for still images can be
categorized into three main groups such as
1. Holistic approach
2. Feature-based approach
3. Hybrid approach product
1. Holistic approach: – In holistic approach, the whole face region is considered as input data into
face detection system. Examples of holistic methods are eigenfaces (most widely used method for
face recognition), probabilistic eigenfaces, fisher faces, support vector machines, nearest feature
lines (NFL) and independent-component analysis approaches. They are all based on principal
component-analysis (PCA) techniques that can be used to simplify a dataset into lower dimension
while retaining the characteristics of dataset.
2. Feature-based approach: – In feature-based approach that is the features on face such as nose,
and then eyes are segmented and then used as input data for structural classifier. Pure geometry,
dynamic link architecture, and hidden Markov model methods belong to this category. One of the
most successful of these systems is the Elastic Bunch Graph Matching (EBGM) system, which is
based on DLA. Wavelets, especially Gabor wavelets, play a building block role for facial
representation in these graph matching methods. A typical local feature representation consists of
wavelet coefficients for different scales and rotations based on fixed wavelet bases. These locally
estimated wavelet coefficients are robust to illumination change, translation, distortion, rotation,
and scaling and serves to represent the pattern classes. Recognition of a new image takes place by
transforming the image into the grid of jets, and matching all stored model graphs to the image.
Conformation of the DLA is done by establishing and dynamically modifying links between
vertices in the model domain.
4
3. Hybrid approach: – The idea of this method comes from how human vision system perceives
both local feature and holistic. The key factors that influence the performance of hybrid approach
include how to determine which features should be combined and how to combine, so as to
preserve their advantages and avert their disadvantages at the same time. These problems have
close relationship with the multiple classifier system and ensemble learning in the field of machine
learning. Unfortunately, even in these fields, these problems remain unsolved. In spite of this,
numerous efforts made in these fields indeed provide us some insights into solving these problems,
and these lessons can be used as guidelines in designing a hybrid face recognition system. hybrid
approach that use both holistic and local information for recognition may be an effective way to
reduce the complexity of classifiers and improve their generalization capability.
When the Student images are stored the database. the raspberry pi camera module is placing the
student entering in the class room. the USB camera module will capture the student image. the
system will automatically update the student presence in the class to the student database and sends
message to guardians of absentees and also to head of department. The laptop of web camera is
captured the image. Each student faces are stored to the database. The image of the students for
further process and then detected face images are compared with the image of student database
and the recognition process. If the image is matched with the database then the student is marked
as present. The students entering in the classroom or everybody already occupies in the classroom
then the student attendance automatically recognized. And the student data base is collected and
store to the pi. The camera will be connected to the raspberry pi module camera will be placed in
front of the class and it captures the image of the student. Students who are present in the class is
used for face detection. Then the detected face is compared with the stored data of every student
then recognize and mark the attendance. The camera will now capture your image. If the image
detected matches to the sample image for the database. The attendance marked as present on the
LCD. The student ID is instantly capture by the reader after that the data is sent to the online server
for recording.
The system will help to compute the percentage of attendance of each individual student. The GUI
of user list function for adding and removing the student personal details. The student to mark his
5
attendance after recognizing the faces of the students. The face recognition information of students
is updated in MySQL database. The database retrieved for the comparison and attendance is
managed automatically in the server where each students voice is recognized from its vocals and
then the data is stored to the database. The students face is pre-stored in the databases. Raspberry
pi camera captures the student face and compare to the database image. If it is matched the student
attendance register with time. The absentees face will be sent to the authorized mail id. The
raspberry pi camera module is placed for student entering in the classroom. Camera module is
capturing the video form. Which contains the many frames from which any one of the frames can
be used for face recognition and marking the attendance. When face recognize operation is started
and find out the nearest matched images from SD card. After completion of your time amount a
file generated with student details like roll number, date, time, present or absent. someone will
absent the message send to the parent mobile numbers using GSM. This system provides accurate
attendance information of the students in easy and efficient. The student will carry a phone having
GPS system which sends the GPS location of campus latitude & longitude values are sent to the
raspberry pi module. The raspberry pi module the students is seating in classroom and GPS
coordinate already stored for classroom database with specific range will match with student.
Using GUI, the faculty can add a student remove a student and also import or export data from the
portable scanner. This attendance system for using of employers and students in general. The
system makes attendance individual in time along with data information thumb impression will be
taken as signature for the system entry. The captured images are stored in jpeg format and then ear
part in cropped from the images. The images include the following operations like edge detection
and timing.
A Counterpart Approach to Attendance using Machine Learning Techniques: The idea of
technology such as Student Attendance system has been implemented with a machine learning
approach. This system automatically detects the student performance and maintains the student’s
records like attendance. Therefore, the attendance of the student can be made available by
recognizing the face. On recognizing, the attendance details of the student are obtained as
feedback.
6
Automated Attendance System Using Face Recognition: Automated Attendance System using
Face Recognition proposes that the system is based on face detection and recognition algorithms,
which is used to detect the student face when he/she enters into the class and the system is capable
to marks the attendance by recognizing him. Viola-Jones Algorithm has been used for face
detection which detect human face using cascade classifier and PCA algorithm for feature selection
and SVM for classification. When it is compared to traditional attendance marking this system
saves the time and helps to monitor the students.
Student Attendance System Using Iris Detection: (Iris recognition is an automated method of
biometric identification) In this proposed system the student is requested to stand in front of the
camera to detect and recognize the iris, for the system to mark attendance for the student. Some
algorithms like Gray Scale Conversion, Six Segment Rectangular Filter, Skin Pixel Detection is
being used to detect the iris. It helps in preventing the proxy issues and it maintains the attendance
of the student in an effective manner, but in one of the time-consuming process for a student or a
staff to wait until the completion of the previous members.
Face Recognition-based Lecture Attendance System: The system takes the attendance
automatically recognition obtained by continuous observation. Continuous observation helps in
estimating and improving the performance of the attendance. To obtain the attendance, positions
and face images of the students present in the classroom are captured. Through continuous
observation and recording the system estimates seating position and location of each student for
attendance marking. The effectiveness of the picture is also being discussed to enable the faster
recognition of the image.
Design
A throughout survey has revealed that various methods and combination of these methods
can be applied in development of a new face recognition system. Among the many possible
approaches, we have decided to use a combination of knowledge-based methods for face detection
part and neural network approach for face recognition part.
The main reason in this selection is their smooth applicability and reliability issues. Our
face recognition system approach is given in Figure.
7
Input Part: is prerequisite for face recognition system. Image acquisition operation is
performed in this part. Live captured images are converted to digital data for performing
image-processing computations. These captured images are sent to face detection algorithm.
Face Detection Part: Face detection performs locating and extracting face image operations for
face recognition system. Face detection part algorithm is given in Figure given below. Our
experiments reveal that skin segmentation, as a first step for face detection, reduces computational
time for searching whole image. While segmentation is applied, only segmented region is searched
weather the segment includes any face or not.
For this reason, skin segmentation is applied as a first step of detection part. RGB color
space is used to describe skin like color [4]. White balance of images differs due to change in
8
lighting conditions of the environment while acquiring image. This situation creates non-skin
objects that belong to skin objects.
Therefore, white balance of the acquired image should be corrected before segmenting it [18].
Results of segmentation on original image and white balance corrected image is given in Figure 4
and 5.
After “and operation” is applied on segmented images, some morphological operations are
applied on final skin image to search face candidate. Noisy like small regions elimination, closing
operations are performed. Then, face candidates are chosen with two conditions which are ratio of
bounding box of candidate and covering some gaps inside the candidate region. Ratio of bounding
box should lie between 0.3 and 1.5.
Based on these conditions, face candidates are extracted from input image with modified
bounding box from original bounding box. The height of bounding box modified as 1.28 times
bigger than width of bounding box because chest and neck parts will be eliminated if candidate
includes them This modification value have been determined experimentally.
9
These face candidates will be sent to facial feature extraction part to validate the candidates. Final
verification of candidate and face image extraction, facial feature extraction process is applied.
Facial feature is one of the most significant features of face. Facial features are eyebrows, eyes,
mouth, nose, nose tip, cheek, etc. The property is used to extract the eyes and mouth which, two
eyes and mouth generate isosceles triangle, and distance between eye to eye and midpoint of eyes
distance to mouth is equal [2]. Laplacian of Gaussian (LoG) filter and some other filtering
operations are performed to extract facial feature of face candidate.
Methodology
The proposed automated attendance management system is based on face recognition.
Using the camera, we will take a picture of the person, followed by detecting the face in the image,
recognizing the person and then updating their attendance in database.
An e?cient face detection algorithm enhances the performance of face recognition
systems. Some of the algorithms proposed for face detection are Face geometry-based methods,
Feature Invariant methods, Machine learning based methods. Out of all these methods we chose
10
Viola and Jones framework which makes use of Integral Image and AdaBoost learning algorithm
as classi?er that gives better results in different lighting conditions to achieve a better detection
rate.
Face region is then extracted and pre-processed for further processing. This pre-processing
step involves with histogram equalization of the extracted face image and is resized. Histogram
Equalization is the most common Histogram Normalization technique. This improves the contrast
of the image by making it clearer as it stretches the range of the intensities in an image.
As we chose face recognition-based system enrollment of every individual is required i.e.
we must take the images of individuals in different angles, different expressions and create a
dataset which is used by LBPH classifier to recognize the face. We need to also set an ID (it may
be a number or the name of the person) for each image, so the algorithm will use this information
to recognize an input image and gives ID as output.
Intended Experiments
The steps of the experiments process are:
Face Detection: Start capturing images through camera of the client side.
Begin:
1. Pre-process the captured image and extract face image
2. calculate the eigen value of the captured face image and compared with eigen
values of existing faces in the database.
3. If eigen value does not matched with existing ones, save the new face image
information to the face database (xml file).
4. If eigen value matched with existing one, then recognition step will be done.
End;
Face Recognition: Using PCA algorithm the following steps would be followed in for face
recognition.
Begin:
1. Find the face information of matched face image in from the database.
2. Update the log table with corresponding face image and system time that makes
completion of attendance for an individual.
end;
11
This section presents the results of the experiments conducted to capture the face into a grey scale
image of 50×50 pixels.
Source Code
Python code.
Results
Output of the code.
Conclusion & Recommendations
Face recognition systems are part of facial image processing applications and their
significance as a research area are increasing recently. Implementations of system are crime
prevention, video surveillance, person verification, and similar security activities.
The goal is reached by face detection and recognition methods. Knowledge-Based face
detection methods are used to find, locate and extract faces in acquired images. Implemented
methods are skin color and facial features. Neural network is used for face recognition. RGB color
space is used to specify skin color values, and segmentation decreases searching time of face
images. Facial components on face candidates are appeared with implementation of LoG filter.
LoG filter shows good performance on extracting facial components under different illumination
conditions.
FFNN is performed to classify to solve pattern recognition problem since face recognition
is a kind of pattern recognition. Classificatio…
Purchase answer to see full
attachment