Automated Smart Attendance System Using Face Recognition

Abstract

In the human body, the face contains many important details, so the face is the most significant factor in identifying a person. There are several main ways to detect the presence of a person. Biometrics for capturing attendance. This is a time consuming process. In this paper, we will use a collection of rules to develop a model that classifies each character\'s face from the captured images. The HOG algorithm for recording student attendance. HOG (Histogram of Oriented Gradients) is one of the methods used to represent and classify images, is a common and effective method, and was chosen for its robustness against changes in pose and lighting. .. The proposed ASAS (Automated Smart Attendance System) captures images and compares them to the images stored in the databases. The database is updated during student enrollment using an automated process that also includes names and role numbers.

Introduction

I. INTRODUCTION

Images processing is a techniques for performing operations on an image to enhance it or obtain useful information. This is a method of signal processing where the inputs are an images and the outputs is either and images or an image property or functions. Imagesprocessing single of the fastest developing technologies nowadays and can be joined into some news applications. Biometrics or fingerprints scanning’s  ones of the existing methods that take time because students need to explicitly state their impressions on the machine. However, it does not takes long to explicitly recognize the face, and it is much shorter than other methods such as biometrics. Face recognition is knowledgeable and can classify or verify creatures based on digital images. Different kinds of faces recognitions techniques include [1] feature-based [2] knowledge-based [3] appearance-based [4] template matching. The image is just a two-dimensional statement. It is defined by the mathematically functions f (x, y). Where the two horizontal and vertical coordinates are x and y. The value of the function f (x, y) at each point indicates the pixel value of the images at that point.

A. Eigen Faces

The unique surface approach is based on the mathematical method PCA (Principal Component Analysis). This approach has been successfully used to reduce the dimensions of the image. Face detection and image identification primarily use principal component analysis by examining principal components that numerically decompose faces into feature vectors. The details of the feature vector can be found in the covariance matrix.

B. Fisher Faces

The implementation of the fisher’s faces technique is based on the principle of Eigen face. Fisher faces are based on the Linear Discriminant Analysis (LDA) technique, which is an appearances based methodology. LDA is based on the notion of labels such that when the requisite dimension is projected onto the image, PCA searches for the highest variance in the matrix. It is possible to maximize the disparity between class means. The keys ideas are to maximize the ratio between class’s scatters and its matrices, which is achieved using LDAs. Fisher's face has the disadvantage that it is more difficult to find a projection of the facial space than an eigenface. Calculating the ratio of interclass variation to infraclass variation takes a long time. The calculation of the average image for each class is performed first.

II. RELATED WORK

Most government and agency certification systems rely on behavioral and physical condition-based security data called biometrics. Biometric systems process raw data such as fingerprints and derive valuable properties from it. The characteristics describe the type of data provideds to the biometric system and make decisions accordingly. Much research has been done on the different methods available to implement effective attendance monitoring systems. These methods differ in the type of input method used, the type of data processing used, and the controller used to implement the system. In this section, we will look for different solutions with the strengths and weaknesses of each system.

The first system, an attendance system with NFC technology and integrated cameras on mobiles devices (Bhis, Khichi, Korde, Lokare, 2015). Near field communication is types of short-ranges radio communication that occurs among dual devices, ones actives and the others passives. The twos devices are mostly induction coils that can respond to electromagnetic induction. Active devices are used to create electromagnetic fields of a particular radius and intensity. It was used to implements attendances systems. For example, schools may give students uniquely programmed NFC tags with unique identification numbers. When attending a class, the instructor brings an NFC reader and the student needs to swipe the NFC tag near the leader, the instructor's phone says. This information is then sent to the school's database to mark student attendance. However, this system is vulnerable to spoofing, which allows one person to sign in to another. Other related systems that use biometrics (fingerprint recognition, RFID, etc.) to identify end users are time management systems used by many universities, institutions, and schools. However, these systems also pose privacy issues. These schemes are also physically damaged by the user. Therefore, additional maintenance costs are incurred. The idea we propose deprives everyone of physical access to automated systems.

III. PROPOSED METHOD

The main purpose of this project is to solve the problems of the old attendance system while recreating a whole new and innovative intelligent system that can bring convenience to the facility. In this projects, an applications is being developed that can recognize each person's identity and ultimately store the data in a database system. Apart form’s that, an excels sheets is created which demonstrations the students attendance and is directly mailed to the respected faculty. Histograms of Oriented Gradients, also known as HOGs, are a functional descriptor like Canny Edge Detector. SIFT (scale invariance and feature conversion). It is used in computers visions and image processing’s for object recognition purposes. This technique counts the occurrence of gradient directions in the localized part of the images. This methods is very similar to the Edge Histogram and Scale Invariant Feature Transformation (SIFT).

The HOGs descriptors focus on the structures or the shapes of objects. It is superior to any edge descriptor because it uses both gradient magnitude and angle to calculate features. For areas of the image, use the magnitude and direction of the gradient to generate a histogram.

IV. METHOD OF IMPLEMENTATION

A. Face Recognition Module

In this module, images with various facial expressions are saved in a folder, and the images are fetched and displayed from this folder. The Locals Directional’s Numbers Patterns (LDN) method has similarities on the face, but it is very difficult to artificially imitate because of the large differences in age, skin, color, and gender.

B. Administrator Function Module

Update laws, manage user information, send confirmations to users, cancel user registration, manage user accounts, and update news.

C. User Function Module

Register their information, create an account, select a demo test to pass this test, view the results of the demo test  at that time, view student information, and the law updated by the administrator Show the rules.

D. Specification Module

In this project, we have prepared student details to manage all records such as student profile issuance, registration, attendance, address, etc. Once all these get computerized to work efficiency of the employee will get increases.

E. Reporting Module

The Student Attendance Management System is designed to automate the processes of registering student profiles and publishing monthly attendance reports, including various reports. The system can carry out daily activities.

F. Preprocessing

This is primarily intended to reduce noise effects, lighting differences, color intensity, backgrounds and placement. The correct recognition of image depends upon quality of captured image; lighting condition. Recognitions rates can be improved by performing pre-processing’s on the captured images.

G. Student Management

This Constitutes The First Phase Of Our Project Module. This Section Consists Following Parameters: [1] Student Registration Form: The Student Appears As A New Candidate for Registration. Registrations Consists of Totaling Each Candidate’s Personals Details. [2] StudentsFacesDetection: The newlysregistereds candidate’s faces gets’ detected for the very firsts times and stored in the databases.

H. Attendance System

This is the next phases of the projects modules. Individual students are identified by extracting the common features of each individual using the image integration method. The candidate's presence is then flagged only if the face image is matchedsagainsts the image stored in the databases and the facial features of the newly captured images match’s the images already stored.

I. Faces Recognitions and Attendances

Next the faces detections phase the following is faces recognitions. This can be achieved by cropping the firsts detected faces from the images and compares it with the databases. This is called the selections of regions of interests. In this way faces of students are verified one by one with the faces databases using the Eigen’s Faces methods and attendances are marked on the servers. Faces Recognitions techniques are used in our systems.

J. Noise Filtering

Since the input image is captured by the camera, many noise sources can be present in the input image. There are many techniques for noise reduction. Low pass filtering in the frequency domain is a good choice, but it also removes some important information in the image. Our system uses median filtering to eliminate noises in histogram-normalized images.

V. EXPERIMENTAL RESULTS

We understand that the Eigen face and the fisherman's face are the calm life of two in two and the true life of two in two, respectively. We cannot guarantee the two best two gentle two conditions. HOG is an extension to overcome this framework. After testing the faces recognitions algorithms with a series of volunteers, we got highly accurate results. After performing all the steps of implementation, you will get the following results: The enrolled students will be successfully generated and saved in the records folder. Registered Student Face Recognition , the following are implementation tests and their results during the attendance registration process, where one student is recognized as attending and registered and another student is recognized as absent and registered. It is shown that it was not. Attendance registration user interface. Then an e-mail message is dispatched from the laptop to the teacher.

Conclusion

This model can be used to recognize a student\'s face and automatically mark the student\'s presence in real time without human intervention. Therefore, in a regulated environment, the proposed technique permits face identification and recognition. LBPH (Local Binary Pattern Histogram) for face detection and detection in specific areas within surveillance cameras. Reliable results have also been obtained for pose distribution and lighting, with good results from various experimental studies of this technique. This method reduces the time it takes to process the entire image. The future scope of this project can be extended to update the presence of multiple people.

References

[1] Prakash, U.M. and Thamaraiselvi, V.G., 2014, July. Detecting and tracking of multiple moving objects for intelligent video surveillance systems. In Second International Conference on Current Trends In Engineering and Technology-ICCTET 2014 (pp. 253-257). IEEE. [2] Prakash, U.M., Kottursamy, K., Cengiz, K., Kose, U. and Hung, B.T., 2021. 4x-expert systems for early prediction of osteoporosis using multi-model algorithms. Measurement, 180, p.109543. [3] Prakash, U.M., Srivathsav, D. and Kumar, N., 2019. Least Value Cloud Carrier Across a Handful of Cloud Vendors. In International Conference on Computer Networks and Communication Technologies (pp. 829-836). Springer, Singapore. [4] Prakash, U.M., Madan, P., GokulAnand, K.R. and Prabhakaran, S., 2018. Intelligent Lighting System and Garbage Monitoring System. [5] Face s Detection s using LBP s Featuress””Jo Chang-yeons CSs 229s Finals Projects Reports Decembers 12 ,2008s. [6] Naveeds KhansBalcohs, M.HaroonsYousafs, WaqarsAhmandsM.IramBaigs, Algorithms for efficients Attendances Managements: Faces Recognitions Baseds approach’s, Internationals Journals of Computers Sciences Issues, Vol.9, Issues 4, No 1, July 2012. [7] E.Varadharajans, R.Dharanis, S.Jeevithas, B.Kavinmathis, S.Hemalathas,Automatics attendances managements systems using’s faces detections, Onlines Internationals Conferences on Greens Engineering’s and Technologiess (IC-GET), 978-1-5090-4556-3/16/$31.00 ©2016 IEEE. [8] “Comparison Of Various Face Recognition Algorithms” International Journal of Advanced Research in Science, Engineering and Technology Vol. 4s, Issue 2, February 2017. [9] KhemPuthea, Rudy Hartanto and RisanuriHidayat, A Review Paper on Attendance Marking System based on Face Recognition, 5th Int\'l Conference on Image Processing, Communication, Engineering and Technology (IPCET-17) Oct. 11-12, 2017. [10] “Faces Recognitions Techniques Using’sIcas AND lbphs”, Khusbus Rani1s, Sukhbirs , kamboj2s, IRJETs, Volume-04s, issu08s, August-2017s. [11] Khan, Mubashir, Apeksha M. Gopale, ObaidChowdhary, Ali Punjani and YasirChoudhary. Automated attendance management system using face recognition. (2017). [12] Himanshus Tiwari1s “Lives Attendances Systems via Faces Recognitions” Internationals Journals for Research’s in Applieds Sciences& Engineering’s Technology’s (IJRASET) Volume 6s Issues IV, April 2018s. [13] Smart Attendance Management System Using Face Recognition KaneezLaila Bhatti1,*, LaraibMughal1 ,EAI Endorsed Transactions on Creative Technologies 10 2018 | Volume 5. [14] .VenkataKalyanPolamarasetty, Muralidhar Reddy Reddem, Dheeraj Ravi, MahithSaiMadala, Attendance System based on Face Recognition, International Research Journal of Engineering and Technology (IRJET), Volume: 05, Issue:04, April-2018. [15] Sathyanarayana, Ramya, Ruchitha, and ShwethaH S, Automatic Student Attendance Management System Using Facial Recognition, International Journal of Emerging Technology in Computer Science & Electronics (IJETCSE) ISSN: 0976-1353 Volume 25 Issue 6 MAY 2018.s [16] “LBPH s -Based s Enhanced s Real s Time s Face s Recognition s “International s Journal s of Advanced s Computer s Science s and Applications s Vol.10, No. 5, Published in 2019. [17] “Faces Recognitions Systems Based on LBPH Algorithm”, International Journal of Engineering & advanced technology(IJEAT),Volume-8,Issue- 5S,May,2019. [18] An Accurates Systems for Faces Detections and RecognitionsAbdelmgeids A. Ali1s, TareksAbd El-Hafeezs and YosraKhalafMohanys Journals of Advances’ in Mathematics’ and Computers Sciences33(3): 1-19, 2019; Article no.JAMCSs.49994 ISSNs: 2456-9968 [19] Nandhini R, Duraimurugan N, S. P. Chokkalingam, Face Recognition Based Attendance System, International Journal of Engineering and Advanced Technology (IJEAT) ISSN: 2249 8958, Volume-8, Issue-3S, February 2019. [20] Rajath S Bharadwaj, Tejus S Rao, Vinay T R, Attendance Management Using Facial Recognition, International Journal of Innovative Technology and Exploring Engineering (IJITEE) ISSN: 2278-3075, Volume-8 Issue-6, April 2019.

Copyright

Copyright © 2022 Dr. B. Shanthini, Gunasekaran M S. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.