Enter your keyword

2-s2.0-85101545727

[vc_empty_space][vc_empty_space]

Improving the Capability of Real-Time Face Masked Recognition using Cosine Distance

Maharani D.A.a, MacHbub C.a, Rusmin P.H.a, Yulianti L.a

a Institut Teknologi Bandung, School of Electrical Engineering and Informatics, Bandung, Indonesia

[vc_row][vc_column][vc_row_inner][vc_column_inner][vc_separator css=”.vc_custom_1624529070653{padding-top: 30px !important;padding-bottom: 30px !important;}”][/vc_column_inner][/vc_row_inner][vc_row_inner layout=”boxed”][vc_column_inner width=”3/4″ css=”.vc_custom_1624695412187{border-right-width: 1px !important;border-right-color: #dddddd !important;border-right-style: solid !important;border-radius: 1px !important;}”][vc_empty_space][megatron_heading title=”Abstract” size=”size-sm” text_align=”text-left”][vc_column_text]© 2020 IEEE.During the pandemic, people around the world are expected to wear masks. So far, the ability to recognize the identity of a person who wears a mask is still a challenge. Face recognition is widely used in schools, hospitals, and companies as an attendance system, even as a criminal watchlist examination system. Thus, face recognition implementation is difficult to obtain the identity of people who are wearing masks, and moreover, computer systems might fail to detect the faces. This study used Haar-cascade Face detection and MobileNet while proposing the addition of the cosine distance method. This method compares the middle position of face detection results within the previous frame and the current. The proposed system can generate a person’s name and identification number while wearing a mask. The system is designed to utilize multi-threading by comparing the transfer learning methods of VGG16 and Triplet Loss FaceNet for face mask recognition with an accuracy rate of 100% and 82.20%. Real-time implementation speed resulted in 4 FPS and 22 FPS and successfully added cosine distance to generate a person’s ID number.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Accuracy rate,Attendance systems,Distance method,Examination system,Identification number,Multi-threading,Real-time implementations,Transfer learning methods[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Indexed keywords” size=”size-sm” text_align=”text-left”][vc_column_text]cosine distance,face mask recognition,FaceNet,MobileNet,multi-threading,real-time,VGG16[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Funding details” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”DOI” size=”size-sm” text_align=”text-left”][vc_column_text]https://doi.org/10.1109/ICIDM51048.2020.9339677[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/4″][vc_column_text]Widget Plumx[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row][vc_column][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][/vc_column][/vc_row]