Face Recognition-Based Attendance System Using Real-Time Computer Vision Algorithms

Sistem dapat menggunakan IP Camera maupun CCTV, IP Camera membutuhkan kabel UTP untuk melakukan komunikasi data, sementara CCTV membutuhkan kabel Coaxial. Pengenalan wajah dilakukan melalui tahap Face Detection, Feature Extraction dan Face Recognition, selanjutnya dicocokkan dengan data profil yang tersimpan di dalam Database. Untuk mendeteksi wajah diperlukan OpenCV yang ditanamkan ke dalam sistem. OpenCV adalah sebuah library (perpustakaan) yang digunakan untuk mengolah gambar dan video hingga kita mampu mengekstrak informasi di dalamnya. OpenCV dapat berjalan di berbagai bahasa pemrograman, seperti C, C++, Java, Python, dan juga didukung di berbagai platform seperti Windows, Linux, Mac OS, iOS dan Android. Setiap pengguna sistem Absensi Face Recognition perlu dilakukan registrasi terlebih dahulu 1 (satu) persatu, dan sistem melakukan Training dari video setiap pengguna yang didaftarkan dan dibuat Source Base dalam bentuk foto dan disimpan di komputer server sebagai menjadi pembanding dan mendeteksi wajah dari berbagai sudut kamera nantinya. Database digunakan adalah MySQL dengan data yang ditampung adalah informasi data wajah, data jadwal, data User serta data informasi absensi. Koneksi untuk CCTV menggunakan RTSP yang merupakan jaringan komputer yang dirancang untuk kebutuhan multimedia dan sistem komunikasi data, yang dapat yang dapat mengendalikan aliran media dari server. Protokol ini digunakan untuk menetapkan dan mengendalikan sesi media antara dua titik ujungnya. Sebagian besar server RTSP menggunakan Real-time Transport Protocol (RTP) yang saling melengkapi dengan Real-time Control Protocol (RTCP) untuk pengiriman aliran media. Sementara itu penggunaan IP Camera atau Kamera IP adalah kamera dengan basis Internet Protocol, jenis kamera video digital yang menerima data kontrol dan mengirimkan data gambar melalui jaringan IP. biasanya digunakan untuk pengawasan tetapi berbeda dengan kamera analog Closed-circuit Television (CCTV), yang mana tidak memerlukan perangkat perekaman lokal, namun hanya jaringan area lokal. Kebanyakan kamera IP adalah Webcam, tetapi istilah kamera IP atau Netcam biasanya hanya berlaku untuk kamera yang dapat langsung diakses melalui koneksi jaringan dan dapat digunakan untuk kamera pengawasan.

Download Full-text

Real Time Face Recognition in Group Images using LBPH

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.b2015.078219 ◽

2019 ◽

Vol 8 (2) ◽

pp. 1362-1367

Keyword(s):

Machine Learning ◽

Computer Vision ◽

Face Recognition ◽

Real Time ◽

Learning Algorithm ◽

Machine Learning Algorithm ◽

Testing Dataset ◽

Negative Images ◽

The Face ◽

Haar Cascade

Face recognition is a beneficial work in computer vision based applications. The goal of the proposed system is to provide complete face recognitions system capable of working a group of images. The faces are detected and verified the identity of an individual using a machine learning algorithm. The haar cascade detects the face from a group of images for training and testing dataset. The dataset contained positive and negative images for training and testing. The LBPH algorithm recognizes the faces from input images. The proposed system detects and recognizes faces with 98% accuracy

Download Full-text

Theoretical Foundation and GPU Implementation of Face Recognition

Advances in Wireless Technologies and Telecommunication - Enabling Real-Time Mobile Cloud Computing through Emerging Technologies ◽

10.4018/978-1-4666-8662-5.ch011 ◽

2015 ◽

pp. 322-341 ◽

Cited By ~ 1

Author(s):

William Dixon ◽

Nathaniel Powers ◽

Yang Song ◽

Tolga Soyata

Keyword(s):

Computer Vision ◽

Face Recognition ◽

Real Time ◽

Graphics Processing Units ◽

Theoretical Foundation ◽

Computational Power ◽

Data Types ◽

Matrix Manipulation ◽

Graphics Processing ◽

Gpu Implementation

Enabling a machine to detect and recognize faces requires significant computational power. This particular system of face recognition makes use of OpenCV (Computer Vision) libraries while leveraging Graphics Processing Units (GPUs) to accelerate the process towards real-time. The processing and recognition algorithms are best sorted into three distinct steps: detection, projection, and search. Each of these steps has unique computational characteristics and requirements driving performance. In particular, the detection and projection processes can be accelerated significantly with GPU usage due to the data types and arithmetic types associated with the algorithms, such as matrix manipulation. This chapter provides a survey of the three main processes and how they contribute to the overarching recognition process.

Download Full-text

Real Time Person Recognition and Attendance Marking Using Holistic Based Approach

International Journal of Advanced Research in Computer Science and Software Engineering ◽

10.23956/ijarcsse/v7i7/0220 ◽

2017 ◽

Vol 7 (7) ◽

pp. 302

Author(s):

Reshma P ◽

Muneer VK ◽

Muhammed Ilyas P

Keyword(s):

Face Recognition ◽

Real Time ◽

High Accuracy ◽

Efficient Technique ◽

Human Face ◽

Traditional Methods ◽

Person Recognition ◽

The Face

Face recognition is a challenging task for the researches. It is very useful for personal verification and recognition and also it is very difficult to implement due to all different situation that a human face can be found. This system makes use of the face recognition approach for the computerized attendance marking of students or employees in the room environment without lectures intervention or the employee. This system is very efficient and requires very less maintenance compared to the traditional methods. Among existing methods PCA is the most efficient technique. In this project Holistic based approach is adapted. The system is implemented using MATLAB and provides high accuracy.

Download Full-text

Real Time Gender and Age Prediction using Deep Learning Techniques

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.e2906.049620 ◽

2020 ◽

Vol 9 (6) ◽

pp. 797-801

Keyword(s):

Deep Learning ◽

Face Recognition ◽

Real Time ◽

Vital Role ◽

Learning Techniques ◽

Gender And Age ◽

The Face ◽

And Gender ◽

Gender Detection ◽

Age Prediction

Face recognition plays a vital role in security purpose. In recent years, the researchers have focused on the pose illumination, face recognition, etc,. The traditional methods of face recognition focus on Open CV’s fisher faces which results in analyzing the face expressions and attributes. Deep learning method used in this proposed system is Convolutional Neural Network (CNN). Proposed work includes the following modules: [1] Face Detection [2] Gender Recognition [3] Age Prediction. Thus the results obtained from this work prove that real time age and gender detection using CNN provides better accuracy results compared to other existing approaches.

Download Full-text