A Lightweight Face Recognition Model based on MobileFaceNet for Limited Computation Environment

Xiao, Jianyu; Jiang, Guang; Liu, Huanhua

doi:10.4108/eai.28-2-2022.173547

Cited by 3 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…s is the step stride [ 10 ]. It is worth noting that MobileFaceNet has been tested and employed in different face-recognition applications, such as in [ 42 , 43 , 44 ].…”

Section: Face Recognition In Real-timementioning

confidence: 99%

Analysis of Real-Time Face-Verification Methods for Surveillance Applications

et al. 2023

View full text Add to dashboard Cite

In the last decade, face-recognition and -verification methods based on deep learning have increasingly used deeper and more complex architectures to obtain state-of-the-art (SOTA) accuracy. Hence, these architectures are limited to powerful devices that can handle heavy computational resources. Conversely, lightweight and efficient methods have recently been proposed to achieve real-time performance on limited devices and embedded systems. However, real-time face-verification methods struggle with problems usually solved by their heavy counterparts—for example, illumination changes, occlusions, face rotation, and distance to the subject. These challenges are strongly related to surveillance applications that deal with low-resolution face images under unconstrained conditions. Therefore, this paper compares three SOTA real-time face-verification methods for coping with specific problems in surveillance applications. To this end, we created an evaluation subset from two available datasets consisting of 3000 face images presenting face rotation and low-resolution problems. We defined five groups of face rotation with five levels of resolutions that can appear in common surveillance scenarios. With our evaluation subset, we methodically evaluated the face-verification accuracy of MobileFaceNet, EfficientNet-B0, and GhostNet. Furthermore, we also evaluated them with conventional datasets, such as Cross-Pose LFW and QMUL-SurvFace. When examining the experimental results of the three mentioned datasets, we found that EfficientNet-B0 could deal with both surveillance problems, but MobileFaceNet was better at handling extreme face rotation over 80 degrees.

show abstract

“…s is the step stride [ 10 ]. It is worth noting that MobileFaceNet has been tested and employed in different face-recognition applications, such as in [ 42 , 43 , 44 ].…”

Section: Face Recognition In Real-timementioning

confidence: 99%

Analysis of Real-Time Face-Verification Methods for Surveillance Applications

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Dimana Mobile FaceNet ini mencapai performa mencapai kecepatan yang sangat baik dengan akurasi yang sangat tinggi dengan model hanya 4,0 MB. Akurasi yang diperoleh sangat mirip dengan model lain yang lebih berat seperti FaceNet [3].…”

Section: Dalam Implementasi Tensorflow Lite Berbasis Mobile Android M...unclassified

Rancang Bangun Aplikasi Kehadiran Siswa Menggunakan Pengenalan Wajah Berbasis Android Dengan Metode Machine Learning

Iskandar¹,

Abdurahman²,

Nursanto³

2022

JSAI

View full text Add to dashboard Cite

Pemanfaatan teknologi komputer Saat berkembang sangat pesat dalam hal pengontrolan kedisiplinan siswa selain dalam rangka mengenalkan penerapan teknologi digital pada siswa tentunya juga menjadi ajang promosi bagi sekolah bersangkutan terkait pemanfaatan teknologi komputer berbasis mobile, kondisi sistem kehadiran siswa selama ini masih dilakukan secara manual oleh guru pada daftar hadir siswa, dimana dalam pelaksanaannya membutuhkan waktu dan kadangkala terjadi kesalahan tulis serta membutuhkan waktu relatif lama. Dalam pengelolaan sistem kehadiran siswa dibutuhkan sistem yang flexibel, tepat guna dan aman terhadap perubahan kebutuhan manajemen sekolah. Machine Learning merupakan suatu metode pembelajaran pada mesin supaya mesin dapat meniru cara kerja otak manusia sehingga dapat memahami dan mengklasifikasikan suatu objek tertentu, dimana hal ini objek yang ditangkap dalam bentuk citra. Dalam penelitian ini dirancang sistem kehadiran siswa berbasis mobile android dengan menggunakan metode machine learning dimana sistem kehadiran dengan menggunakan pengenalan wajah menggunakan metode K-Nearest Neighbor dengan library Python 3.8, TensorFlow Lite dan sistem database sqlite. Dari implementasi dan trial sistem dari sisi kecepatan dan keakuratan sudah memadai untuk dapat digunakan pada satu institusi kelas atau sekolah. Kestabilan server face_api juga cukup memadai selama testing dapat berjalan tanpa gangguan lebih dari 7x24 jam

show abstract

ConvFaceNeXt: Lightweight Networks for Face Recognition

2022

View full text Add to dashboard Cite

The current lightweight face recognition models need improvement in terms of floating point operations (FLOPs), parameters, and model size. Motivated by ConvNeXt and MobileFaceNet, a family of lightweight face recognition models known as ConvFaceNeXt is introduced to overcome the shortcomings listed above. ConvFaceNeXt has three main parts, which are the stem, bottleneck, and embedding partitions. Unlike ConvNeXt, which applies the revamped inverted bottleneck dubbed the ConvNeXt block in a large ResNet-50 model, the ConvFaceNeXt family is designed as lightweight models. The enhanced ConvNeXt (ECN) block is proposed as the main building block for ConvFaceNeXt. The ECN block contributes significantly to lowering the FLOP count. In addition to the typical downsampling approach using convolution with a kernel size of three, a patchify strategy utilizing a kernel size of two is also implemented as an alternative for the ConvFaceNeXt family. The purpose of adopting the patchify strategy is to reduce the computational complexity further. Moreover, blocks with the same output dimension in the bottleneck partition are added together for better feature correlation. Based on the experimental results, the proposed ConvFaceNeXt model achieves competitive or even better results when compared with previous lightweight face recognition models, on top of a significantly lower FLOP count, parameters, and model size.

show abstract

A Lightweight Face Recognition Model based on MobileFaceNet for Limited Computation Environment

Cited by 3 publications

References 22 publications

Analysis of Real-Time Face-Verification Methods for Surveillance Applications

Analysis of Real-Time Face-Verification Methods for Surveillance Applications

Rancang Bangun Aplikasi Kehadiran Siswa Menggunakan Pengenalan Wajah Berbasis Android Dengan Metode Machine Learning

ConvFaceNeXt: Lightweight Networks for Face Recognition

Contact Info

Product

Resources

About