Skip to main content
Have a personal or library account? Click to login
Exploring the Potential of A-ResNet in Person-Independent Face Recognition and Classification Cover

Exploring the Potential of A-ResNet in Person-Independent Face Recognition and Classification

Open Access
|Aug 2023

Figures & Tables

Figure 1.

MTCNN's architecture: (a) P-Net (b) R-Net and (c) O-Net

Figure 2.

Examples of corrupt data from MTCNN

Figure 3.

FaceNet's high level model structure

Figure 4.

Inception-ResNet

Figure 5.

Six-final layers

Figure 6.

A-ResNet Architecture

Figure 7.

RMS tracking loss in TensorboradX

Figure 8.

Adam tracking loss in TensorboradX

Figure 9.

System fully utilised to identify (a) faces and (b) face masks

Results for ResNet

MetricsValue
Accuracy0.7884615384615384
Time38s

Accuracy achieved

StudyAccuracy (%)
Zhou et al. [1]99.50%
Iqbal et al. [2]96.40%
Balaban [3]99.63%
Sun et al. [4]67%

Results for A-ResNet

MetricsValue
Accuracy0.9169230769230769
Time50s

Records of combination for A-ResNet

EpochsBatch sizeTrue PositiveTrain FPS
246470151.9
2412881170.4
3212885254.4
3225676209.8
6425676194.3

Records of combination for ResNet

EpochsBatch sizeTrue PositiveTrain FPS
101620426.4
241625421.7
243240278.6
246474151.2
326470160.7
2412879148.9
3212876232.4
2425669182.5
3225676192.8
6425675154.3

Recognition rate based on LFW database

Recognition at 45 pxCorrect TimesWrong TimesCorrect Image AccuracyIncorrect Image Accuracy
Front facing871783.65%16.35%
Facing 30’ Right891585.57%14.43%
Facing 30’ Left911387.50%12.5%
Language: English
Page range: 12 - 19
Published on: Aug 16, 2023
In partnership with: Paradigm Publishing Services
Publication frequency: 4 issues per year

© 2023 Ahmed Mahdi Obaid, Aws Saad Shawkat, Nazar Salih Abdulhussein, published by Xi’an Technological University
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.