Revolutionizing Face Recognition : An Improved MobileNetV2 System
In this paper, we present an impressive face recognition model, which represents a robust improvement over the original MobileNetv2. Our model introduces the Receptive Field Block (RFB) to prevent any loss of facial feature information, expands the perceptual field, and implementing multi-scale feat...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Ministry of Education, china and Northeastern University, china.
2023
|
Subjects: | |
Online Access: | http://ir.unimas.my/id/eprint/43783/3/Revolutionizing.pdf http://ir.unimas.my/id/eprint/43783/ https://www.kzyjc.org/search-article |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Universiti Malaysia Sarawak |
Language: | English |
id |
my.unimas.ir.43783 |
---|---|
record_format |
eprints |
spelling |
my.unimas.ir.437832024-01-16T00:46:23Z http://ir.unimas.my/id/eprint/43783/ Revolutionizing Face Recognition : An Improved MobileNetV2 System Chi, Jing Zhang, Haopeng Chin, Kim On Chai, Soo See QA76 Computer software In this paper, we present an impressive face recognition model, which represents a robust improvement over the original MobileNetv2. Our model introduces the Receptive Field Block (RFB) to prevent any loss of facial feature information, expands the perceptual field, and implementing multi-scale feature fusion to enhance the model's feature extraction capability. Moreover, we have incorporated Coordinate Attention (CA) into the RFB to enhance recognition accuracy within the lightweight network. The proposed model is named CA_RFB_MobileNetv2. Our experimental results from eight public datasets demonstrate that the recognition accuracy rate of the proposed CA_RFB_MobileNetv2 model is either greater than or equal to that of MobileNetv2. In one of the eight datasets, the recognition accuracy of CA_RFB_MobileNetv2 was slightly reduced by 0.18% compared to FaceNet. However, it offers a significant advantage, a 2.3 times reduction in processing time per image and an 8.8 times decrease in the number of parameters used. Finally, our proposed model was used in a face recognition system, achieving an impressive accuracy of 97.5% with a low false acceptance rate of 2% when tested on 200 randomly selected face images from the Labeled Faces in the Wild dataset. Ministry of Education, china and Northeastern University, china. 2023 Article PeerReviewed text en http://ir.unimas.my/id/eprint/43783/3/Revolutionizing.pdf Chi, Jing and Zhang, Haopeng and Chin, Kim On and Chai, Soo See (2023) Revolutionizing Face Recognition : An Improved MobileNetV2 System. Kongzhi yu Juece/Control and Decision (KZYJC). pp. 45-59. ISSN 1001-0920 https://www.kzyjc.org/search-article |
institution |
Universiti Malaysia Sarawak |
building |
Centre for Academic Information Services (CAIS) |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Malaysia Sarawak |
content_source |
UNIMAS Institutional Repository |
url_provider |
http://ir.unimas.my/ |
language |
English |
topic |
QA76 Computer software |
spellingShingle |
QA76 Computer software Chi, Jing Zhang, Haopeng Chin, Kim On Chai, Soo See Revolutionizing Face Recognition : An Improved MobileNetV2 System |
description |
In this paper, we present an impressive face recognition model, which represents a robust improvement over the original MobileNetv2. Our model introduces the Receptive Field Block (RFB) to prevent any loss of facial feature information, expands the perceptual field, and implementing multi-scale feature fusion to enhance the model's feature extraction capability. Moreover, we have incorporated Coordinate Attention (CA) into the RFB to enhance recognition accuracy within the lightweight network. The proposed model is named CA_RFB_MobileNetv2. Our experimental results from eight public datasets demonstrate that the recognition accuracy rate of the proposed CA_RFB_MobileNetv2 model is either greater than or equal to that of MobileNetv2. In one of the eight datasets, the recognition accuracy of CA_RFB_MobileNetv2 was slightly reduced by 0.18% compared to FaceNet. However, it offers a significant advantage, a 2.3 times reduction in processing time per image and an 8.8 times decrease in the number of parameters used. Finally, our proposed model was used in a face recognition system, achieving an impressive accuracy of 97.5% with a low false acceptance rate of 2% when tested on 200 randomly selected face images from the Labeled Faces in the Wild dataset. |
format |
Article |
author |
Chi, Jing Zhang, Haopeng Chin, Kim On Chai, Soo See |
author_facet |
Chi, Jing Zhang, Haopeng Chin, Kim On Chai, Soo See |
author_sort |
Chi, Jing |
title |
Revolutionizing Face Recognition : An Improved MobileNetV2 System |
title_short |
Revolutionizing Face Recognition : An Improved MobileNetV2 System |
title_full |
Revolutionizing Face Recognition : An Improved MobileNetV2 System |
title_fullStr |
Revolutionizing Face Recognition : An Improved MobileNetV2 System |
title_full_unstemmed |
Revolutionizing Face Recognition : An Improved MobileNetV2 System |
title_sort |
revolutionizing face recognition : an improved mobilenetv2 system |
publisher |
Ministry of Education, china and Northeastern University, china. |
publishDate |
2023 |
url |
http://ir.unimas.my/id/eprint/43783/3/Revolutionizing.pdf http://ir.unimas.my/id/eprint/43783/ https://www.kzyjc.org/search-article |
_version_ |
1789430352746381312 |