TY - GEN
T1 - Image-based Kinship Verification Using Dual VGG-Face Classifie
AU - Rachmadi, Reza Fuad
AU - Ketut Eddy Purnama, I.
AU - Nugroho, Supeno Mardi Susiki
AU - Suprapto, Yoyon Kusnendar
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/1/27
Y1 - 2021/1/27
N2 - In this paper, we investigated dual VGG-Face convolutional neural network classifier for image-based kinship verification problems. The proposed classifier is formed by paralleling convolutional layers of VGG CNN architecture and combined it with several fully-connected layers. Although the VGG CNN architecture is consists of huge parameters, the number of parameters in the classifier will be reduced by more than 80% by removing the fully-connected layers of the original classifier. We use the multi-task loss function for the training process to ensure that the features learned by the classifier are also can be used for family classification. Experiments on the FIW kinship verification dataset show that dual VGG-Face CNN classifiers can achieve an average accuracy of 64.71% on a single classifier and 65.49% on ensemble configuration. Based on our experiments, the lowest accuracy is produced for second-generation kinship (grandchild-grandparent) which have a low number of examples on FIW kinship.
AB - In this paper, we investigated dual VGG-Face convolutional neural network classifier for image-based kinship verification problems. The proposed classifier is formed by paralleling convolutional layers of VGG CNN architecture and combined it with several fully-connected layers. Although the VGG CNN architecture is consists of huge parameters, the number of parameters in the classifier will be reduced by more than 80% by removing the fully-connected layers of the original classifier. We use the multi-task loss function for the training process to ensure that the features learned by the classifier are also can be used for family classification. Experiments on the FIW kinship verification dataset show that dual VGG-Face CNN classifiers can achieve an average accuracy of 64.71% on a single classifier and 65.49% on ensemble configuration. Based on our experiments, the lowest accuracy is produced for second-generation kinship (grandchild-grandparent) which have a low number of examples on FIW kinship.
KW - convolutional neural network
KW - dual VGG-Face
KW - image-based kinship verification
UR - http://www.scopus.com/inward/record.url?scp=85102173576&partnerID=8YFLogxK
U2 - 10.1109/IoTaIS50849.2021.9359720
DO - 10.1109/IoTaIS50849.2021.9359720
M3 - Conference contribution
AN - SCOPUS:85102173576
T3 - IoTaIS 2020 - Proceedings: 2020 IEEE International Conference on Internet of Things and Intelligence Systems
SP - 123
EP - 128
BT - IoTaIS 2020 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Conference on Internet of Things and Intelligence Systems, IoTaIS 2020
Y2 - 27 January 2021 through 28 January 2021
ER -