Face Recognition Applications Research Articles

Diagnosis of Facial Recognition Using Deep Transfer Learning

Abstract: The connection among the face and infection that has been investigated a shockingly prolonged stretch of time back, which prompts the event. The objective is to explore the chance seeing contaminations by utilizing an unstructured 2D face pictures with critical figuring out frameworks. this paper, we recommend using huge exchange obtaining from feature assertion to play out the PC helped facial confirmation on different infections. In the tests, we play out the PC maintained facial considering on single (betathalassemia) and different sicknesses (beta-thalassemia, hyperthyroidism, Down syndrome, and leprosy) a genuinely little dataset General ahead of everyone else exactness by basic trade in view of facial confirmation shows up at much than 90%, beating the two clinicians and normal AI structures in the starters. In obliging, collecting a tangle of unambiguous face photos is confused, unnecessary, and tedious, and powers moral snags by prudence of the treatment of individual data. Accordingly, the face educational files finding related Investigations are classified and for the most part insignificant separating and the ones of other AI application locale. The headway of critical exchange applications of face recognition in learning with a small dataset could give an irrelevant expense and simple way for jumble screening and disclosure

New Local Binary Pattern Feature Extractor with Adaptive Threshold for Face Recognition Applications

This paper represents a feature extraction method constructed on the local binary pattern (LBP) structure. The proposed method introduces a new adaptive thresholding function to the LBP method replacing the fixed thresholding at zero. The introduced function is a Gaussian Distribution Function (GDF) variation. The proposed technique uses the global and local information of the image and image blocks to perform the adaptation. The adaptive function adds to the on-hand im-age’s features by preserving the information of the amplitude of the pixel difference rather than just considering the sign of the pixel difference in the process of LBP coding. This feature improves the accuracy of the face recognition system by providing additional information. The proposed method demonstrates a higher recognition rate than other presented techniques (%97.75). The proposed method was also tested with different types of noise to demonstrate its effectiveness in the presence of various levels of noise. The Extended Yale B dataset was used for the testing along with Support Vector Machine (SVM) as classifier.

The sensitive nature of facial recognition: Tensions between the Swedish police and regulatory authorities1

Emerging technologies with artificial intelligence (AI) and machine learning are laying the foundation for surveillance capabilities of a magnitude never seen before. This article focuses on facial recognition, now rapidly introduced in many police authorities around the world, with expectations of enhanced security but also subject to concerns related to privacy. The article examined a recent case where the Swedish police used the controversial facial recognition application Clearview AI, which led to a supervisory investigation that deemed the police’s use of the technology illegitimate. Following research question guided the study: How do the trade-offs between privacy and security unfold in the police use of facial recognition technology? The study was designed as a qualitative document analysis of the institutional dialogue between the police and two regulatory authorities, theoretically we draw on technological affordance and legitimacy. The results show how the police’s use of facial recognition gives rise to various tensions that force the police as well as policy makers to rethink and further articulate the meaning of privacy. By identifying these tensions, the article contributes with insights into various controversial legitimacy issues that may arise in the area of rules in connection with the availability and use of facial recognition.

Boosting Face Presentation Attack Detection in Multi-Spectral Videos Through Score Fusion of Wavelet Partition Images.

Presentation attack detection (PAD) algorithms have become an integral requirement for the secure usage of face recognition systems. As face recognition algorithms and applications increase from constrained to unconstrained environments and in multispectral scenarios, presentation attack detection algorithms must also increase their scope and effectiveness. It is important to realize that the PAD algorithms are not only effective for one environment or condition but rather be generalizable to a multitude of variabilities that are presented to a face recognition algorithm. With this motivation, as the first contribution, the article presents a unified PAD algorithm for different kinds of attacks such as printed photos, a replay of video, 3D masks, silicone masks, and wax faces. The proposed algorithm utilizes a combination of wavelet decomposed raw input images from sensor and face region data to detect whether the input image is bonafide or attacked. The second contribution of the article is the collection of a large presentation attack database in the NIR spectrum, containing images from individuals of two ethnicities. The database contains 500 print attack videos which comprise approximately 1,00,000 frames collectively in the NIR spectrum. Extensive evaluation of the algorithm on NIR images as well as visible spectrum images obtained from existing benchmark databases shows that the proposed algorithm yields state-of-the-art results and surpassed several complex and state-of-the-art algorithms. For instance, on benchmark datasets, namely CASIA-FASD, Replay-Attack, and MSU-MFSD, the proposed algorithm achieves a maximum error of 0.92% which is significantly lower than state-of-the-art attack detection algorithms.

Application of an Artificial Intelligence System Recognition Based on the Deep Neural Network Algorithm.

With the development of artificial intelligence and computer technology, the deep neural network algorithm is applied to the intelligentization of various fields of production and life. However, from the current application status, the application of artificial intelligence technology has many shortcomings. Based on this, this paper starts with the deep neural network algorithm, takes face recognition as the research tool, and deeply studies how to use the deep neural network algorithm to demonstrate the application of intelligent face recognition in complex environments. A face recognition neural network algorithm is proposed, and the accuracy of the algorithm is checked by testing. The results show that the average accuracy of a single sample in the LFW dataset is 99.17%, and the efficiency of using a single sample is close to that of many smelting models, which can be applied to various intelligent recognition scenarios.

Fusion Methods for Face Presentation Attack Detection.

Face presentation attacks (PA) are a serious threat to face recognition (FR) applications. These attacks are easy to execute and difficult to detect. An attack can be carried out simply by presenting a video, photo, or mask to the camera. The literature shows that both modern, pre-trained, deep learning-based methods, and traditional hand-crafted, feature-engineered methods have been effective in detecting PAs. However, the question remains as to whether features learned in existing, deep neural networks sufficiently encompass traditional, low-level features in order to achieve optimal performance on PA detection tasks. In this paper, we present a simple feature-fusion method that integrates features extracted by using pre-trained, deep learning models with more traditional colour and texture features. Extensive experiments clearly show the benefit of enriching the feature space to improve detection rates by using three common public datasets, namely CASIA, Replay Attack, and SiW. This work opens future research to improve face presentation attack detection by exploring new characterizing features and fusion strategies.

The Importance of Hyperparameter Optimisation for Facial Recognition Applications

This paper explores the importance of using optimisation techniques when tuning a machine learning model. The hyperparameters that need to be determined for the Artificial Neural Network (ANN) to work most efficiently are supposed to find a value that achieves the highest recognition accuracy in a face recognition application. First, the model was trained with manual optimisation of the parameters. The highest recognition accuracy that could be achieved was 96.6% with a specific set of parameters used in the ANN. However, the error rate was at 30%, which was not optimal. After utilising Grid Search as the first automated tuning method for hyperparameters, the recognition accuracy rose to 96.9% and the error rate could be minimised to be less than 1%. Applying Random Search, a recognition accuracy of 98.1% could be achieved with the same error rate. Adding further optimisation to the results from Random Search resulted in receiving an accuracy of 98.2%. Hence, the accuracy of the facial recognition application could be increased by 1.6% by applying automated optimisation methods. Furthermore, this paper will also deal with common issues in face recognition and focus on potential solutions.

Speckle-Based Optical Cryptosystem and its Application for Human Face Recognition via Deep Learning.

Face recognition has become ubiquitous for authentication or security purposes. Meanwhile, there are increasing concerns about the privacy of face images, which are sensitive biometric data and should be protected. Software‐based cryptosystems are widely adopted to encrypt face images, but the security level is limited by insufficient digital secret key length or computing power. Hardware‐based optical cryptosystems can generate enormously longer secret keys and enable encryption at light speed, but most reported optical methods, such as double random phase encryption, are less compatible with other systems due to system complexity. In this study, a plain yet highly efficient speckle‐based optical cryptosystem is proposed and implemented. A scattering ground glass is exploited to generate physical secret keys of 17.2 gigabit length and encrypt face images via seemingly random optical speckles at light speed. Face images can then be decrypted from random speckles by a well‐trained decryption neural network, such that face recognition can be realized with up to 98% accuracy. Furthermore, attack analyses are carried out to show the cryptosystem's security. Due to its high security, fast speed, and low cost, the speckle‐based optical cryptosystem is suitable for practical applications and can inspire other high‐security cryptosystems.

Application of High-Resolution Face Recognition and EDF Image Reconstruction in English Classroom Teaching

This study examines classroom monitoring in order to increase the effectiveness of English classroom instruction. This article uses high-resolution algorithms and EDF image reconstruction technology in the English classroom education system to improve the high resolution of students’ faces. This work presents a fast pixel capture function to enhance the rapid video capture function. The stack velocity picking of the speed spectrum is the most important aspect of velocity analysis. To create successful changes to the algorithm, this method often employs optimization algorithms as a way of stack velocity choosing speed. Finally, based on algorithm improvements, this study builds the system structure and develops simulation tests to validate system performance. The English classroom teaching system created in this work can properly determine the real-time status of students by facial recognition and has excellent user satisfaction, indicating that it may effectively increase the teaching impact, according to experimental research.

Development of Deep Learning Applications for Face Recognition in Online Media to Determine Student Presence

Presensi masih dilakukan dengan cara manual yaitu dengan cara pemateri meminta semua mahasiswa yang hadir untuk mengaktifkan kamera pada device masing-masing agar wajah mahasiswa terlihat dan mencatat nama mahasiswa tersebut untuk dilaporkan hadir. Untuk mempermudah presensi, maka pengenalan wajah adalah cara yang tepat untuk mengatasi masalah tersebut. Mahasiswa cukup mengaktifkan kamera dan program akan meng-capture window dari aplikasi Zoom setiap sekian menit dan merubah view partisipan menjadi gallery agar masing-masing mahasiswa yang sudah hadir dapat melakukan presensi otomatis. Tahapan awal untuk melakukan pengenalan wajah adalah pendeteksian wajah dan mengekstraksi fitur wajah mahasiswa. Fitur tersebut akan dibandingkan dengan dataset wajah mahasiswa agar metode yang digunakan dapat mengenali siapa mahasiswa yang terdeteksi. Metode yang digunakan pada penelitian ini adalah Convolutional Neural Network (CNN) untuk ekstraksi fitur dan pengenalan wajah. Ide utama di balik CNN adalah proses konvolusinya, dimana sebuah gambar diekstraksi untuk setiap fitur untuk menghasilkan banyak pola yang lebih mudah diidentifikasi. Strategi ini dapat meningkatkan efisiensi dengan penerapan fungsi pembelajaran citra. Diharapkan dengan menggunakan metode pengenalan wajah ini, proses pendeteksi kehadiran mahasiswa dapat diimplementasikan. Hasil penelitian ini dengan melakukan presensi pada 6 kelas mahasiswa Politeknik Negeri Malang jurusan Teknik Informatika dan Manajemen Informatika menghasilkan waktu presensi rata-rata per kelas adalah 4,466 detik dan akurasi pengenalan wajah adalah 77,27%

Application Research of Face Recognition Algorithm based on MATLAB

Face recognition is a biometric recognition technology based on human facial features. Its application is generally to collect relevant face images through the camera, extract the video stream containing the face, or monitor the face in real time. This paper will take matlab simulation software as the research platform to study the effect of different face recognition algorithms in practical application. The main research method is to establish the corresponding face recognition application simulation interface on MATLAB, carry out simulation verification through different face recognition algorithms, compare and analyze the simulation results, and summarize the advantages and disadvantages of face recognition in the process of practical application,it provides a certain reference for the follow-up application of face recognition in real life.

Real-Time Object Detection Using Deep Learning

Abstract: The computer vision field known as real-time acquisition is large, dynamic, and complex. Local image process refers to the acquisition of one object in an image, while Objects refers to the acquisition of multiple objects in an image. In digital photos and videos, this sees semantic class objects. Tracking features, video surveilance, pedestrian detection, census, self-driving cars, face recognition, sports tracking, and many other applications used to find real-time object. Convolution Neural Networks is an in-depth study tool for OpenCV (Opensource Computer Vision), a set of basic computer-assisted programming tasks. Computer visualization, in-depth study, and convolutional neural networks are some of the words used in this paper..

Face Shape Classification Based on Bilinear Network with Attention Mechanism

Face shape is an important information in face recognition, personalized recommendation and other applications. For example, rough face shape filtering before face recognition can effectively improve the recognition accuracy and speed. At the same time, an effective face shape classification can be used to construct a recommendation system for hairstyles and glasses. Therefore, this paper proposes a new face shape classification algorithm. Firstly, the M-RetinaFace network is proposed to align face image. Secondly, by combing the attention mechanism with the EfficientNet bilinear network, the AB-CNN network is proposed to extract feature. Finally, a bilinear pooling layer is used to classify face shape. Experiments on public data sets show that, compared with existing algorithms, the algorithm proposed in this paper is get state-of-the-art results and significantly improves the accuracy of face shape classification.

Face recognition based on Siamese convolutional neural network using Kivy framework

Human face recognition is a vital biometric sign that has remained owing to its many levels of applications in society. This study is complex for free faces globally because human faces may vary significantly due to lighting, emotion, and facial stance. This study developed a mobile application for face recognition and implemented one of the convolutional neural network (CNN) architectures, namely the Siamese CNN for face recognition. Siamese CNN can learn the similarity between two object representations. Siamese CNN is one of the most common techniques for one-shot learning tasks. Our participation in this study determined the efficiency of the Siamese CNN architecture with the enormous quantity of face data employed. The findings demonstrated that the suggested strategy is both practical and accurate. The method with augmentation produces the best results with a total data set of 9000 face images, a buffer size of 10000, and epochs of 5, producing the minimum loss of 0.002, recall of 0.996, the precision of 0.999, and F1-score of 0.672. The proposed method gets the best accuracy of 98% with test data. The Siamese CNN model is successfully implemented in Python, and a user interface and executables are built using the Kivy framework.

Face Recognition System for Control Access to Restrictive Domain

Recent progress in computer vision applied to facial analysis has led to state-of-the-art face detection and facial feature extraction models. A cautious implementation of these models into face recognition pipelines can enable achieving superior performances and popularized daily applications of face recognition in a variety of domains. However, modern face recognition system is a multi-steps process including face detection, feature extraction and classification model. Developing a high-performance face recognition application generalizing on local data set remains challenging. In this paper, we present Deep learning based face recognition system employing MTCNN for face detection and FaceNet for feature extraction. We compare KNN and SVM classification models trained on the facial features extracted from prepared labeled faces. Both models demonstrated almost 100% accuracy on static test faces. Moreover, as face pose get more pronounced, far above 30°, both SVM and KNN models demonstrate efficient recognition rate of 95.95% and 96.67% respectively. Real-time evaluation shows less than 1% deviation from the static performances with both classifiers on less 30° tilted images.

Face Security Authentication System Based on Deep Learning and Homomorphic Encryption

The development of deep learning technology has promoted the wide application of face recognition in many scenarios such as mobile payment and social media, but the security of user data is facing great challenges. To protect the privacy of users, face authentication cannot be operated in plaintext. To solve this problem, a face feature ciphertext authentication scheme based on homomorphic encryption is proposed. First, the face image feature extraction is completed based on a deep learning model. Second, the face features are packaged into ciphertext by using homomorphic encryption and batch processing technology, and the face feature ciphertext is saved in the database of the cloud server. Third, combined with automorphism mapping and Hamming distance, a face feature ciphertext recognition method is designed, which can complete face recognition in the case of ciphertext. Finally, the integrity and consistency of face feature ciphertext recognition results before and after decryption are guaranteed by the one-time MAC authentication method. The whole framework can finish identity recognition without decrypting face feature coding, and the homomorphic ciphertext of face feature coding is saved in the database, so there is no risk of face feature coding leakage. Experiments show that the system has met the requirements of real application scenarios.

Face Patterns Analysis and Recognition System Based on Quantum Neural Network QNN

The past few years have witnessed a huge increase in the application of facial recognition, detection, and analysis technology. However, face recognition systems remain the most popular among the general public. The facial recognition system can detect the presence of a face when exposed to one. The accuracy and fairness that can be derived from such systems necessitate their use, because humans, particularly security personnel can be tired and target the wrong person as a suspect. However, artificial intelligence systems that are properly trained are capable of efficiently identifying and classifying faces without errors. In this work, the use of Matlab language was employed in building a software system that is capable of recognizing and differentiating different face patterns. The proposed system is equipped with a camera that serves as the practical aspect of the software that captures different shots that are sent to the theoretical part of a special program that is designed to recognize faces by comparing them with a database stored within the program. The practical part of the work involved the use of Quantum Neural Network. In this work, the training dataset is made up of features vectors that were obtained from a well-known set of face images of different people. Here, Principle Component Analysis (PCA) was used for the extraction of feature vectors from images and then prepared for the next training step. The experimental results revealed that efficient face recognition can be achieved through the use of well-trained Quantum Network.

MEMBANDINGAN METODE JARINGAN SYARAF TIRUAN BACKPROPAGATION DAN LEARNING VECTOR QUANTIZATION DENGAN OPENCV PADA PENGENALAN WAJAH

Face recognition is an area that is still being researched and improved for various purposes such as attendance, population data collection, security systems and others. Two methods that are often used for face recognition applications are artificial intelligence methods, especially back-propagation neural networks (ANN) and learning vector quantization. Both of these techniques are directed learning techniques that are widely used to identify distinctive patterns, namely grouping patterns into groups of patterns, making them ideal for use in facial recognition applications. In this application, preprocessing of the input image includes the detection process of scaling, grayscale, edged with the sobel and threshold methods, carried out before the image is processed in ANN. Meanwhile, the ANN approach used to identify faces involves the Backpropagation method and the Learning Vector Quantization method. The findings of this analysis are a comparison of the backpropagation neural network method and quantization of the learning vectors of face recognition used to assess variations, limitations, strengths and optimal results of the two techniques for use in facial recognition systems.
 

CHEHRA: An Application for Forensic Face Sketch Construction and Recognition

In this modern age, the overall crime rate is increasing day-by-day and to cope up with this the law enforcement departments too should find ways that would speed up the overall process and help them in bringing one to justice. One such way can be using face recognition technology for identifying and verifying the criminal. The traditional approach here is to use the hand-drawn face sketches drawn by forensic sketch artist to identify the criminal, modernizing this would mean using the hand drawn sketch and then matching them with the law enforcement departments database to identify the criminal. We believe, there is a need for creating an application which would not just provide a set of individual features like eyes, ears, mouth, etc. to be selected to create a face sketch but also would help in finding the criminal much faster and efficiently.

Face Recognition based on Convoluted Neural Networks: Technical Review

Human beings recognize and classify objects with biological senses and brain that processes the input into meaningful information. Other than that humans have come to recognize each other in multiple ways one of which is visual recognition of faces. As a biological trait human faces are certainly a biometric such they are universal, distinctive, mostly permanent and collectable. With that a computerized face recognition system can constructed relying on visual information present on each face uniquely. Generally a face recognition system consists of two main phases, face detection phase where presence of a human face is verified on visual input and face recognition phase where detected face is processed for identification. One of the most sought after methods in field image processing for face recognition is CNN (Convoluted Neural Networks). CNNs have proved its effectiveness and accuracy in many CNN based face detection and face recognition systems. As such in this paper the architecture of CNN is presented. Then different techniques for face detection and face recognition based on CNNs are reviewed. In reviewed papers CNNs have repeatedly demonstrated effectiveness and accuracy on multiple benchmarks for face recognition application.