A New Face Recognition Method for Intelligent Security

Wang, Zhenzhou; Zhang, Xu; Yu, Pingping; Duan, Wenjie; Zhu, Dongjie; Cao, Ning

doi:10.3390/app10030852

Cited by 14 publications

(6 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, many researchers have demonstrated the reliability of their face recognition models in identifying peoples' identities. These models can be applied to a range of real-world scenarios, such as security checks and monitoring, gated access control, verification of proper face-mask usage, and identification of masked faces [6][7][8][9][10]. While executing these programs on high-performance-computing (HPC) devices poses no issue, they often encounter limited computational resources.…”

Section: Related Workmentioning

confidence: 99%

A lightweight deep learning model for real‐time face recognition

Deng

Chiang

Kang

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

Lightweight deep learning models for face recognition are becoming increasingly crucial for deployment on resource‐constrained devices such as embedded systems or mobile devices. This paper presents a highly efficient and compact deep learning (DL) model that achieves state‐of‐the‐art performance on various face recognition benchmarks. The developed DL model employs one‐ or few‐shot learning to obtain effective feature embeddings and draws inspiration from FaceNet with significant refinements to achieve a memory size of only 3.5 MB—about 30 times smaller than FaceNet—while maintaining high accuracy and real‐time performance. The study demonstrates the model's effectiveness through extensive experiments, which include testing on public datasets and the model's ability to recognize occluded faces in uncontrolled environments using grayscale input images. Compared to the state‐of‐the‐art lightweight models, the proposed model requires fewer FLOPs (0.06G), has a smaller number of parameters (1.2 M), and occupies a smaller model size (3.5 MB) while achieving a competitive level of recognition accuracy and real‐time performance. The results show that the model is well‐suited for deployment in embedded domains, including live entrance security checks, driver authorization, and in‐class attendance systems. The entire code of FN8 is available on GitHub.

show abstract

Section: Related Workmentioning

confidence: 99%

A lightweight deep learning model for real‐time face recognition

Deng

Chiang

Kang

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Built-in video cameras, particularly front-facing digital cameras, are now more common in mobile phones. Facial biometric authentication has become very popular compared to the optical fingerprint recognition component in cell phones, such as in the approach of [49,50]. The works related to e-wallets and their findings are shown in Table 1.…”

Section: Literature Reviewmentioning

confidence: 99%

Device Identity-Based User Authentication on Electronic Payment System for Secure E-Wallet Apps

Hassan

Shukur

2021

Electronics

View full text Add to dashboard Cite

E-wallets are a modern electronic payment system technology that easily recognize consumer interest, making our transactions very convenient and efficient. E-wallets are intended to substitute the existing physical wallet, which may tell others something about us as a person. That is why using a physical wallet is a unique, personal experience that cannot be duplicated. A solution would be to replace the physical wallet with an e-wallet on an existing mobile device. The personal nature of the e-wallet is that it should be installed on a unique device. One of the fundamental protections against any illegal access to e-wallet application is through authentication. In particular, the fundamental authentication category used in an existing e-wallet is based on knowledge (i.e., what you know), ownership (i.e., what you have), and biometric (i.e., what you are) authentication, which are sometimes prone to security threats such as account takeover, sim swapping, app cloning, or know your customer verification attacks. The design of an e-wallet authentication on mobile device solution must take into consideration the intensity of the security. To address this problem, this study proposes a design of e-wallet apps with an extension security element that focuses on the device identity in the existing user authentication mechanism. This study covers four fundamental categories of authentication: password, one time password, fingerprints, and international mobile equipment identifier. Using IMEI limits an e-wallet to be in one specific device in one time; this brings it into line with the nature of a physical wallet. In addition, it will be ready to handle the mentioned threats above, which will ultimately result in the far more reliable to use of e-wallet apps. The proposed authentication design has two phases, a registration phase and an authentication phase. The proposed method has been developed and implemented based on an Android Studio Firebase real-time database management and PayPal. In addition, the complete design has been evaluated using functional requirement testing to see how closely it meets functionality requirements. The results obtained from functional testing show that the functionalities of the proposed method meet the requirements, and one cannot use a same account on two devices; hence, it is secure from attacks. The result also shows that the proposed method has no errors. Moreover, it has been shown that our proposed method has better security parameters in terms of the existing method.

show abstract

“…Three-dimensional (3D) face recognition is another branch of face recognition techniques for overcoming issues arising from ambient light, background, and shooting angle. Supported by auxiliary 3D face images and 3D imaging technologies, more accurate results can be obtained [21][22][23][24]. However, the requirements of computational power and equipment increase heavily and become highly dominant.…”

Section: Related Workmentioning

confidence: 99%

Lightweight and Resource-Constrained Learning Network for Face Recognition with Performance Optimization

Deng

Chiang

2020

Sensors

View full text Add to dashboard Cite

Despite considerable progress in face recognition technology in recent years, deep learning (DL) and convolutional neural networks (CNN) have revealed commendable recognition effects with the advent of artificial intelligence and big data. FaceNet was presented in 2015 and is able to significantly improve the accuracy of face recognition, while also being powerfully built to counteract several common issues, such as occlusion, blur, illumination change, and different angles of head pose. However, not all hardware can sustain the heavy computing load in the execution of the FaceNet model. In applications in the security industry, lightweight and efficient face recognition are two key points for facilitating the deployment of DL and CNN models directly in field devices, due to their limited edge computing capability and low equipment cost. To this end, this paper provides a lightweight learning network improved from FaceNet, which is called FN13, to break through the hardware limitation of constrained computational resources. The proposed FN13 takes the advantage of center loss to reduce the variations of the between-class features and enlarge the difference of the within-class features, instead of the triplet loss by using FaceNet. The resulting model reduces the number of parameters and maintains a high degree of accuracy, only requiring few grayscale reference images per subject. The validity of FN13 is demonstrated by conducting experiments on the Labeled Faces in the Wild (LFW) dataset, as well as an analytical discussion regarding specific disguise problems.

show abstract

A New Face Recognition Method for Intelligent Security

Cited by 14 publications

References 30 publications

A lightweight deep learning model for real‐time face recognition

A lightweight deep learning model for real‐time face recognition

Device Identity-Based User Authentication on Electronic Payment System for Secure E-Wallet Apps

Lightweight and Resource-Constrained Learning Network for Face Recognition with Performance Optimization

Contact Info

Product

Resources

About