scholarly journals Comparative analysis of selected facial recognition algorithms

2020 ◽  
Vol 39 (3) ◽  
pp. 896-904
Author(s):  
J.A. Popoola ◽  
C.O. Yinka-Banjo
Keyword(s):  
Face Recognition ◽  
Comparative Analysis ◽  
Facial Recognition ◽  
Research Work ◽  
Cost Effective ◽  
Facial Symmetry ◽  
Face Matching ◽  
Computer Based ◽  
Haar Cascade ◽  
Detection And Recognition

Systems and applications embedded with facial detection and recognition capabilities are founded on the notion that there are differences in face structures among individuals, and as such, we can perform face-matching using the facial symmetry. A widely used application of facial detection and recognition is in security. It is important that the images be processed correctly for computer-based facial recognition, hence, the usage of efficient, cost-effective algorithms and a robust database. This research work puts these measures into consideration and attempts to determine a cost-effective and reliable algorithm out of three algorithms examined. Keywords: Haar-Cascade, PCA, Eigenfaces, Fisherfaces, LBPH, Face Recognition.

scholarly journals ANÁLISE DE MÉTODOS DE DETECÇÃO E RECONHECIMENTO DE FACES UTILIZANDO VISÃO COMPUTACIONAL E ALGORITMOS DE APRENDIZADO DE MÁQUINA

2021 ◽  
Vol 13 (2) ◽  
pp. 01-11
Author(s):  
Lucas José da Costa ◽  
Thiago Luz de Sousa ◽  
Francisco Assis da Silva ◽  
Leandro Luiz de Almeida ◽  
Danillo Roberto Pereira ◽  
...  
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Comparative Analysis ◽  
Execution Time ◽  
Digital Images ◽  
Facial Recognition ◽  
Detection Algorithm ◽  
Ambient Lighting ◽  
The Face ◽  
Haar Cascade

The advancement in technology in recent decades has provided many facilities for humanity in various applications, and facial recognition technology is one of them. There are several problemsto be solved to perform face recognition from digital images, such as varying ambient lighting, changing the face physical characteristics and resolution of the images used. This work aimed to perform a comparative analysis between some of thedetection and facial recognition methods, as well as their execution time. We use the Eigenface, Fisherface and LBPH facial recognition algorithms in conjunction with the Haar Cascade facedetection algorithm, all from the OpenCV library. We also explored the use of CNN neural network for facial recognition in conjunction with the HOG facial detection algorithm, these from the Dlib library. The work aimed, besides analyzing the algorithms in relation to hit rates, factors such as reliability and execution time were also considered

scholarly journals Attendance Management System using Google Facenet for Facial Recognition

2021 ◽  
Vol 9 (VI) ◽  
pp. 5029-5036
Author(s):  
Rakesh Duggempudi
Keyword(s):  
Image Processing ◽  
Face Recognition ◽  
Open Source ◽  
Management System ◽  
Facial Recognition ◽  
Cost Effective ◽  
Source Image ◽  
Student Attendance ◽  
Manual Work ◽  
View Update

Attendance management system is a required tool for attaining attendance in any habitat where attendance is essential. Yet, many of the available techniques consume time, are invasive and it demands manual work from the users. This research is directed at building a less invasive, cost effective and more efficient automated student attendance management system using face recognition that leverages on OpenCV functions for facial recognition. The system provides a GUI for marking attendance. It provides an interface for updating attendance using facial recognition libraries of OpenCV. The system stores attendance in a database which is maintained by the administrator. The administrator can view, update, and change the attendance of the students. The students can view and update their attendance. The system is developed on Open-Source image processing library and the interface is developed using Python Tkinter module. The Tkinter module is an open-source module by which we can develop GUI screens hence, it is not software dependent nor vendor hardware. The OpenCV module used for image processing is interfaced using python.

Face Recognition and Face Detection Using Open Computer Vision Classifiers and Python

2021 ◽  
pp. 185-207
Author(s):  
Priyank Jain ◽  
Meenu Chawla ◽  
Sanskar Sahu
Keyword(s):  
Computer Vision ◽  
Face Recognition ◽  
Face Detection ◽  
Local Binary Pattern ◽  
Research Work ◽  
Modern World ◽  
The Face ◽  
Haar Cascade

Identification of a person by looking at the image is really a topic of interest in this modern world. There are many different ways by which this can be achieved. This research work describes various technologies available in the open-computer-vision (OpenCV) library and methodology to implement them using Python. To detect the face Haar Cascade are used, and for the recognition of face eigenfaces, fisherfaces, and local binary pattern, histograms has been used. Also, the results shown are followed by a discussion of encountered challenges and also the solution of the challenges.

scholarly journals PENERAPAN EIGENFACE UNTUK COMPUTER BASED TEST (CBT) PENERIMAAN MAHASISWA BARU SEKOLAH TINGGI TEKNOLOGI ADISUTJIPTO

Compiler ◽  
2017 ◽  
Vol 6 (2) ◽  
Author(s):  
Haruno Sajati ◽  
Astika Ayuningtyas ◽  
Dwi Kholistyanto
Keyword(s):  
Face Recognition ◽  
Computer Technology ◽  
Digital Image ◽  
Facial Recognition ◽  
Security System ◽  
The Internet ◽  
Accuracy Rate ◽  
The Face ◽  
Computer Based ◽  
Or Applications

One of the development of computer technology is the availability of systems or applications that help human work everyday so that can be resolved quickly and correctly. The system, one of which is Computer Based Test (CBT). CBT is an application used for tests conducted using computers that are in the application there are some features of CBT security when working on the problem. CBT can use a stand-alone computer, a computer connected to a network or a computer connected to the internet. Facial recognition is a type of biometric application that can identify specific individuals in a digital image by analyzing and developing face patterns. In its implementation, CBT has a weakness in the security system that becomes the gap of CBT users to commit fraud, therefore required a good security system with the creation of CBT applications that use eigenface algorithm. It is necessary to have a security system that overcomes the problem that is required identification of face recognition of participants during the test so that cheating can be reduced. The results of the test using eigenface algorithm accuracy rate reached 82%, some things that affect the level of accuracy is, the intensity of light, facial position and the use of accessories on the face.

IMPROVING FACE RECOGNITION MODELS USING METRIC LEARNING, LEARNING RATE SCHEDULERS, AND AUGMENTATIONS

2021 ◽  
Vol 6 ◽  
pp. 93-101
Author(s):  
Andrey Litvynchuk ◽  
◽  
Lesia Baranovska ◽  
◽  
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Face Recognition ◽  
Comparative Analysis ◽  
Convolutional Neural Networks ◽  
Facial Recognition ◽  
Metric Learning ◽  
Learning Rate ◽  
Training Dataset ◽  
Wide Range

Face recognition is one of the main tasks of computer vision, which is relevant due to its practical significance and great interest of wide range of scientists. It has many applications, which has led to a huge amount of research in this area. And although research in the field has been going on since the beginning of the computer vision, good results could be achieved only with the help of convolutional neural networks. In this work, a comparative analysis of facial recognition methods before convolutional neural networks was performed. A metric learning approach, augmentations and learning rate schedulers are considered. There were performed bunch of experiments and comparative analysis of the considered methods of improvement of convolutional neural networks. As a result a universal algorithm for training the face recognition model was obtained. In this work, we used SE-ResNet50 as the only neural network for experiments. Metric learning is a method by which it is possible to achieve good accuracy in face recognition. Overfitting is a big problem of neural networks, in particular because they have too many parameters and usually not enough data to guarantee the generalization of the model. Additional data labeling can be time-consuming and expensive, so there is such an approach as augmentation. Augmentations artificially increase the training dataset, so as expected, this method improved the results relative to the original experiment in all experiments. Different degrees and more aggressive forms of augmentation in this work led to better results. As expected, the best learning rate scheduler was cosine scheduler with warm-ups and restarts. This schedule has few parameters, so it is also easy to use. In general, using different approaches, we were able to obtain an accuracy of 93,5 %, which is 22 % better than the baseline experiment. In the following studies, it is planned to consider improving not only the model of facial recognition, but also detection. The accuracy of face detection directly depends on the quality of face recognition.

scholarly journals REAL TIME FACE DETECTION AND RECOGNITION SYSTEM USING HAAR CASCADE CLASSIFIER AND NEURAL NETWORKS

2021 ◽  
Vol 9 (1) ◽  
pp. 224-231
Author(s):  
Anirban Chakraborty, Shilpa Sharma
Keyword(s):  
Face Detection ◽  
Facial Recognition ◽  
Recognition System ◽  
Recognition Algorithm ◽  
Smart Device ◽  
Cascade Classifier ◽  
Face Detection And Recognition ◽  
Haar Cascade ◽  
The Times ◽  
Detection And Recognition

Home protection and privacy have become one of the most critical aspects in today's world. As technology progresses at an exponential pace, the times are not far ahead for each house to be fitted with sophisticated security systems to deal with regular burglary and theft. But as one side of the tech progresses, so do its detrimental counterparts. DES encryption can be an indicator of how easily an encrypted piece of information can be deciphered. Not long after its release, DES encryption was referred to as 'unsafe' and with today's modern application, anything like DES might be an open invitation to hack. With many developments in the field, the technology has, in many respects, surpassed the use of biometrics (finger prints). Face recognition, nowadays, is present in almost every smart device that has some piece of information stored that holds importance to its users. With facial recognition gaining popularity, many tech companies have come with their own patent to make a technology related to Facial Recognition on the market. This paper suggests a somewhat related concept as to how home protection can be improved by using a face detection and recognition algorithm (Haar Cascade Classifier).

scholarly journals Tempus-A Facial Recognition Technology in Attendance Monitoring

2020 ◽  
Vol 3 (2) ◽  
pp. 175-176
Author(s):  
Melanie M. Reynoso ◽  
Ariane M. Torres
Keyword(s):  
Information System ◽  
Face Recognition ◽  
Radio Frequency Identification ◽  
Facial Recognition ◽  
Raspberry Pi ◽  
Mobile Platforms ◽  
Frequency Identification ◽  
Hardware Component ◽  
Haar Cascade ◽  
Smart Technologies

Attendance monitoring has strategic importance for every organization. It has shifted from utilizing paper-based attendance monitoring to biometrics, radio-frequency identification, Bluetooth and smart technologies, Internet of Things (IoT), cloud computing, or face recognition technology. Tempus is an automated attendance monitoring system that uses face recognition technology for input, real-time IoT capabilities for processing, and portability of mobile platforms for output. It has hardware and software components. The core of the hardware component is Raspberry Pi 3, which serves as a communication medium between the camera sensor and the information system. Tempus uses Haar Cascade for facial detection and Linear Binary Pattern Histogram (LBPH) for facial recognition. The software component is further divided into two: 1) the information system for administrators, an attendance monitoring which allows encoding of data, creating new user accounts, managing schedules, recording attendance, and generating reports; and 2) mobile platform for end-users, the teachers, that is provided for communication and notification purposes only.

scholarly journals Implementasi Convolutional Neural Network untuk Facial Recognition

2021 ◽  
Vol 20 (2) ◽  
pp. 66-79
Author(s):  
Dhanny Setiawan ◽  
Andikha Dwi Putra ◽  
Kezia Stefani ◽  
Jenisa Felisa
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Face Recognition ◽  
Convolutional Neural Network ◽  
Facial Recognition ◽  
Haar Cascade

Facial recognition merupakan salah satu teknik biometrik. Teknik yang dapat disebut juga pengenalan wajah ini telah menjadi topik yang cukup diminati untuk diteliti. Pada peneitian ini dilakukan proses pengenalan wajah dengan menggunakan metode CNN (Convolutional Neural Network). Penelitian ini memiliki tujuan untuk mengimplementasikan metode CNN ke dalam pengenalan wajah dengan menggunakan library Tensorflow. Metode ini digunakan karena proses pembelajaran dilakukan dengan mendalam (deep learning). Metode CNN yang digunakan memiliki beberapa lapisan pada proses training yang dilakukan, yaitu lapisan Conv2D, MaxPooling2d, Flatten, dan Dense. Face recognition yang dihasilkan terdapat pendeteksi wajah menggunakan Haar Cascade dengan bantuan library Opencv di dalamnya. Jumlah dataset juga diketahui dapat mempengaruhi hasil pengenalan dan proses pengenalan wajah dengan CNN juga memerlukan dataset yang besar. Adapun jumlah citra wajah yang digunakan dalam penelitian ini sebanyak 90.000 gambar wajah yang berasal dari 36 himpunan gambar dan menghasilkan tingkat akurasi sebesar 97%.

scholarly journals Identification of Gender from Facial Features

2021 ◽  
pp. 323-329
Author(s):  
Prof. Khemutai Tighare ◽  
Prof. Rahul Bhandekar ◽  
Rashmi Kannake
Keyword(s):  
Face Recognition ◽  
Good Accuracy ◽  
Research Work ◽  
Confidence Score ◽  
Project Work ◽  
Facial Features ◽  
Cascade Classifier ◽  
Machine Learning Model ◽  
Haar Cascade ◽  
Facial Images

Increasing population and changing lifestyle become a more confusing task for detecting gender from facial images. To solve such a fragile problem several handy approaches are readily available in computer vision. Although, very few of these approaches achieve good accuracy. The features like lightning, illumination, noise, ethnicity, and various facial expression hamper the correctness of the images. Keeping these things in mind, we propose our research work on the identification of gender from facial features. The major component of face recognition is to develop a machine learning model which will classify the images this can be done by haar-cascade-classifier. To train the model with images more accurately we would perform few image processing concepts for the data to perform data analysis and preprocessing for structuring our data. This can be done by OpenCV. After that, we have used PCA ( Principle Comprehend Analysis ) to compute Eigenvalues and for the optimal components, we will get the class name from the knowledge base and confidence score from the SVM-based face recognition model. In our project work, we get good accuracy.

scholarly journals Face Recognition Techniques: A Survey

2021 ◽  
Vol 10 (2) ◽  
pp. 697-700
Keyword(s):  
Face Recognition ◽  
Face Detection ◽  
Research Work ◽  
Recognition Process ◽  
Face Detection And Recognition ◽  
Detection And Recognition

A lot of research work and development is taking place in being carried in field of face recognition, now a days. A face recognition process has two pillars: face detection and face recognition. A number of techniques are being used these purposes. The accuracy of all those techniques vary and separate techniques for detection and recognition are in practice at present. In this paper we will give an insight to accuracies of different face detection and recognition techniques which are being widely used by researchers and developers.

Sign in / Sign up

Export Citation Format

Share Document