scholarly journals Analysis of Face Recognition Algorithm: Dlib and OpenCV

2020 ◽  
Vol 4 (1) ◽  
pp. 173-184
Author(s):  
Suwarno Suwarno ◽  
Kevin Kevin
Keyword(s):  
Face Recognition ◽  
Facial Recognition ◽  
Real Life ◽  
Recognition Algorithm ◽  
Speed Test ◽  
Recognition Algorithms ◽  
Image Dataset ◽  
In The Wild ◽  
Speed Accuracy ◽  
Speed And Accuracy

In face recognition there are two commonly used open-source libraries namely Dlib and OpenCV. Analysis of facial recognition algorithms is needed as reference for software developers who want to implement facial recognition features into an application program. From Dlib algorithm to be analyzed is CNN and HoG, from OpenCV algorithm is DNN and HAAR Cascades. These four algorithms are analyzed in terms of speed and accuracy. The same image dataset will be used to test, along with some actual images to get a more general analysis of how algorithm will appear in real life scenarios. The programming language used for face recognition algorithms is Python. The image dataset will come from LFW (Labeled Faces in the Wild), and AT&T, both of which are available and ready to be downloaded from the internet. Pictures of people around the UIB (Batam International University) is used for actual images dataset. HoG algorithm is fastest in speed test (0.011 seconds / image), but the accuracy rate is lower (FRR = 27.27%, FAR = 0%). DNN algorithm is the highest in level of accuracy (FRR = 11.69%, FAR = 2.6%) but the lowest speed (0.119 seconds / picture). There is no best algorithm, each algorithm has advantages and disadvantages.Keywords: Python, Face Recognition, Analysis, Speed, Accuracy.

Comparison of Face Recognition Algorithms for Human-Robot Interactions

2015 ◽  
Vol 72 (2) ◽  
Author(s):  
Mohamed Tahir Ahmed ◽  
Shamsudin H. M. Amin
Keyword(s):  
Face Recognition ◽  
Recognition Algorithm ◽  
Robotic Systems ◽  
Human Being ◽  
Recognition Algorithms ◽  
Speed And Accuracy

Face recognition is a cornerstone of many robotic systems in which a robot has to identify and interact with a human being. Choosing a face recognition algorithm arbitrarily may not yield the best results for a researcher and may produce undermined results. In this paper we compare three widely used algorithms in terms of speed and accuracy. Such data can be very useful in choosing an algorithm for a particular task. The algorithms were applied to 36 different situations, and the results indicate the strengths, advantage and limitations of each of the three recognition methods in a certain setting.

scholarly journals Illumination Normalization Algorithm Combination Analysis in Face Recognition

2017 ◽  
Vol 9 (3) ◽  
pp. 334-339
Author(s):  
Rokas Semėnas
Keyword(s):  
Face Recognition ◽  
Large Scale ◽  
Real Life ◽  
Direct Approach ◽  
Small Scale ◽  
Test Results ◽  
Illumination Normalization ◽  
Recognition Algorithms ◽  
Life Problems

Face recognition programs have many practical usages in various fields, such as security or entertainment. Existing recognition algorithms must deal with various real life problems – mainly with illumination. In practice, illumination normalization models are often used only for Small-scale futures extraction, ignoring Large-scale features. In this article, new and more direct approach to this problem is offered, used algorithms and test results are given.

scholarly journals On the Robustness of Face Recognition Algorithms Against Attacks and Bias

2020 ◽  
Vol 34 (09) ◽  
pp. 13583-13589
Author(s):  
Richa Singh ◽  
Akshay Agarwal ◽  
Maneet Singh ◽  
Shruti Nagpal ◽  
Mayank Vatsa
Keyword(s):  
Face Recognition ◽  
Recognition Performance ◽  
Recognition Algorithm ◽  
Future Research ◽  
Research Directions ◽  
Recognition Algorithms ◽  
Future Research Directions ◽  
And Gender ◽  
Gender Variations ◽  
Very High

Face recognition algorithms have demonstrated very high recognition performance, suggesting suitability for real world applications. Despite the enhanced accuracies, robustness of these algorithms against attacks and bias has been challenged. This paper summarizes different ways in which the robustness of a face recognition algorithm is challenged, which can severely affect its intended working. Different types of attacks such as physical presentation attacks, disguise/makeup, digital adversarial attacks, and morphing/tampering using GANs have been discussed. We also present a discussion on the effect of bias on face recognition models and showcase that factors such as age and gender variations affect the performance of modern algorithms. The paper also presents the potential reasons for these challenges and some of the future research directions for increasing the robustness of face recognition models.

scholarly journals Comparisons of Facial Recognition Algorithms Through a Case Study Application

2020 ◽  
Vol 14 (14) ◽  
pp. 121
Author(s):  
Amir Dirin ◽  
Nicolas Delbiaggio ◽  
Janne Kauttonen
Keyword(s):  
Object Recognition ◽  
Open Source ◽  
Facial Recognition ◽  
Real Life ◽  
Mobile Object ◽  
Recognition Algorithms ◽  
Processing Power ◽  
Neural Network Algorithm ◽  
High Processing

<p class="affiliations"><strong>Abstract— </strong>Computer visions and their applications have become important in contemporary life. Hence, researches on facial and object recognition have become increasingly important both from academicians and practitioners. Smart gadgets such as smartphones are nowadays capable of high processing power, memory capacity, along with high resolutions camera. Furthermore, the connectivity bandwidth and the speed of the interaction have significantly impacted the popularity of mobile object recognition applications. These developments in addition to computer vision’s algorithms advancement have transferred object’s recognitions from desktop environments to the mobile world. The aim of this paper to reveal the efficiency and accuracy of the existing open-source facial recognition algorithms in real-life settings. We use the following popular open-source algorithms for efficiency evaluations: Eigenfaces, Fisherfaces, Local Binary Pattern Histogram, the deep convolutional neural network algorithm, and OpenFace. The evaluations of the test cases indicate that among the compared facial recognition algorithms the OpenFace algorithm has the highest accuracy to identify faces. The findings of this study help the practitioner on their decision of the algorithm selections and the academician on how to improve the accuracy of the current algorithms even further.</p>

REVIEW OF FACE RECOGNITION ALGORITHMS

2021 ◽  
Vol 140 (4) ◽  
pp. 209-243
Author(s):  
MICHAŁ BUKOWSKI
Keyword(s):  
Face Recognition ◽  
Hybrid Methods ◽  
Facial Recognition ◽  
Technical Problem ◽  
Three Dimensional ◽  
Facial Features ◽  
Automatic Assessment ◽  
Recognition Algorithms ◽  
Effi Ciency ◽  
Practical Effect

Information technology of the 20th and 21st centuries “opened the way” to the automatic assessment of anthropometric facial features, facial gestures and other characteristic behaviours. Recognition is a very complex technical problem with a signifi cant practical effect. There are dedicated applications for this purpose. The article presents face recognition algorithms for 2D images, for three-dimensional spaces, and methods using neural networks. Linear and nonlinear, local and global, and hybrid methods of facial recognition are presented. The study understands the strengths and weaknesses of the laws governing the use of face recognition technology and, if possible, analyses their effi ciency. The methodological review has been created in connection with the idea of the author’s own fast algorithms and facial recognition.

scholarly journals Age-based facial recognition using convoluted neural network deep learning algorithm

2020 ◽  
Vol 9 (3) ◽  
pp. 424
Author(s):  
Julius Yong Wu Jien ◽  
Aslina Baharum ◽  
Shaliza Hayati A. Wahab ◽  
Nordin Saad ◽  
Muhammad Omar ◽  
...  
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Learning Algorithm ◽  
Facial Recognition ◽  
Well Being ◽  
Deep Learning Algorithm ◽  
Business Applications ◽  
Image Dataset ◽  
The Face ◽  
The Individual

Face recognition is the use of biometric innovations that can see or validate a person by seeing and investigating designs depending on the shape of the individual. Face recognition is used largely for the purpose of well-being, despite the fact that passion for different areas of use is growing. Overall, face recognition innovations are worth considering because they have the potential for broad legal jurisdiction and different business applications. It is widely used in many spaces. How it works is a product of facial recognition processing facial geometry. The hole between the ear and the good way from the front to the jaw are the main variables. This code distinguishes the highlight of the face that is important for your facial separation and creates your facial expression. Therefore, this study gives an overview of age detection using a different combination of machine learning and image processing methods on the image dataset.

scholarly journals Multimodal Hierarchical Face Recognition using Information from 2.5D Images

2018 ◽  
Vol 2 (2) ◽  
pp. 39-54 ◽  
Author(s):  
João C. Monteiro ◽  
Tiago Freitas ◽  
Jaime S. Cardoso
Keyword(s):  
Face Recognition ◽  
Facial Recognition ◽  
Real Life ◽  
Human Cognition ◽  
Depth Information ◽  
Discriminative Power ◽  
Hierarchical Framework ◽  
Rgb Images

Facial recognition under uncontrolled acquisition environments faces major challenges that limit the deployment of real-life systems. The use of 2.5D information can be used to improve discriminative power of such systems in conditions where RGB information alone would fail. In this paper we propose a multimodal extension of a previous work, based on SIFT descriptors of RGB images, integrated with LBP information obtained from depth scans, modeled by an hierarchical framework motivated by principles of human cognition. The framework was tested on EURECOM dataset and proved that the inclusion of depth information improved significantly the results in all the tested conditions, compared to independent unimodal approaches.

Application of 3D face recognition in the access control system

Robotica ◽  
2021 ◽  
pp. 1-19
Author(s):  
Quoc Dien Le ◽  
Tran Thanh Cong Vu ◽  
Tuong Quan Vo
Keyword(s):  
Control System ◽  
Face Recognition ◽  
Access Control ◽  
Facial Recognition ◽  
Recognition Algorithm ◽  
User Cooperation ◽  
Web Based ◽  
Access Control System ◽  
Recognition Systems ◽  
And Storage

Abstract Over the years, face recognition has been the research topic that has attracted many researchers around the world. One of the most significant applications of face recognition is the access control system. The access control system allows authorized persons to enter or exit certain or restricted areas. As a result, it will increase the security situation without over-investment in staff security. The access information can be the identification, time, and location, etc. It can be used to carry out human resource management tasks such as attendance and inspection of employees in a more fair and transparent manner. Although face recognition has been widely used in access control systems because of its better accuracy and convenience without requiring too much user cooperation, the 2D-based face recognition systems also retain many limitations due to the variations in pose and illumination. By analyzing facial geometries, 3D facial recognition systems can theoretically overcome the disadvantages of prior 2D methods and improve robustness in different working conditions. In this paper, we propose the 3D facial recognition algorithm for use in an access control system. The proposed algorithm includes the preprocessing, feature extraction, and classification stages. The application of the proposed access control system is the automatic sliding door, the controller of the system, the web-based monitoring, control, and storage of data.

scholarly journals Sistemas de reconocimiento facial, como herramienta para la búsqueda de personas

2017 ◽  
Vol 1 (8) ◽  
Author(s):  
Alex Gregorio Mendoza Arteaga ◽  
Gregorio Isoldo Mendoza Cedeño ◽  
Enrique Javier Macías Arias ◽  
Sandy Raúl Chun Molina
Keyword(s):  
Face Recognition ◽  
Key Words ◽  
Video Surveillance ◽  
Facial Recognition ◽  
Surveillance Systems ◽  
Biometric Recognition ◽  
Recognition Algorithms ◽  
Methods And Techniques ◽  
Automatic Systems ◽  
The Ideal

En el presente artículo se analiza la factibilidad de la implementación de algoritmos de reconocimiento facial integrados a los sistemas de video vigilancia de un territorio, para la localización de personas y como herramienta de búsqueda de individuos prófugos de la justicia convirtiéndose en un aporte importante a las investigaciones policiales y judiciales. Para alcanzar este objetivo, se estudian aristas sobre el reconocimiento biométrico y se considera el reconocimiento facial como el proceso ideal para la propuesta y discusión del artículo, en consecuencia, se investiga las etapas, métodos y técnicas más comunes y de mayor eficacia en los sistemas automáticos de reconocimiento de rostros para identificación de personas mediante imágenes y videos. Por consiguiente, se concluye que la implementación de un sistema automático de reconocimiento faciales interconectado a uno o varios sistemas de video vigilancia facilitara la búsqueda de individuos dentro del territorio donde se lo aplique.   Palabras claves: Biométrico, algoritmos, sistemas automáticos, tecnologías    Sistema de reconocimiento Facial    Systems of facial recognition, like tool for people's quest  Abstract In this article the feasibility of implementing facial recognition algorithms integrated video surveillance systems in a territory, to locate people tool analyzes and as individuals search for fugitives from justice becoming an important contribution to the police and judicial investigations. To achieve this goal, edges on biometric recognition are studied and considered facial recognition as the ideal for the proposal and discussion of Article process, therefore the steps, methods and techniques more common and more effective is investigated on the automatic face recognition to identify people through images and videos. Therefore, it is concluded that the implementation of a system of interconnected automatic facial recognition of one or several video surveillance systems facilitate finding individuals within the territory where it is applied.  Key words: Biometric, algorithms, automatic systems, technologies  

scholarly journals MFCosface: A Masked-Face Recognition Algorithm Based on Large Margin Cosine Loss

2021 ◽  
Vol 11 (16) ◽  
pp. 7310
Author(s):  
Hongxia Deng ◽  
Zijian Feng ◽  
Guanyu Qian ◽  
Xindong Lv ◽  
Haifang Li ◽  
...  
Keyword(s):  
Face Recognition ◽  
Facial Recognition ◽  
Positional Information ◽  
Recognition Algorithm ◽  
Face Image ◽  
Convolutional Network ◽  
Public Places ◽  
Large Margin ◽  
The Face ◽  
Key Features

The world today is being hit by COVID-19. As opposed to fingerprints and ID cards, facial recognition technology can effectively prevent the spread of viruses in public places because it does not require contact with specific sensors. However, people also need to wear masks when entering public places, and masks will greatly affect the accuracy of facial recognition. Accurately performing facial recognition while people wear masks is a great challenge. In order to solve the problem of low facial recognition accuracy with mask wearers during the COVID-19 epidemic, we propose a masked-face recognition algorithm based on large margin cosine loss (MFCosface). Due to insufficient masked-face data for training, we designed a masked-face image generation algorithm based on the detection of the detection of key facial features. The face is detected and aligned through a multi-task cascaded convolutional network; and then we detect the key features of the face and select the mask template for coverage according to the positional information of the key features. Finally, we generate the corresponding masked-face image. Through analysis of the masked-face images, we found that triplet loss is not applicable to our datasets, because the results of online triplet selection contain fewer mask changes, making it difficult for the model to learn the relationship between mask occlusion and feature mapping. We use a large margin cosine loss as the loss function for training, which can map all the feature samples in a feature space with a smaller intra-class distance and a larger inter-class distance. In order to make the model pay more attention to the area that is not covered by the mask, we designed an Att-inception module that combines the Inception-Resnet module and the convolutional block attention module, which increases the weight of any unoccluded area in the feature map, thereby enlarging the unoccluded area’s contribution to the identification process. Experiments on several masked-face datasets have proved that our algorithm greatly improves the accuracy of masked-face recognition, and can accurately perform facial recognition with masked subjects.

Sign in / Sign up

Export Citation Format

Share Document