Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385069944> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4385069944 endingPage "421" @default.
- W4385069944 startingPage "421" @default.
- W4385069944 abstract "This research proposes a single network model architecture for mask face recognition using the FaceNet training method. Three pre-trained convolutional neural networks of different sizes are combined, namely InceptionResNetV2, InceptionV3, and MobileNetV2. The models are augmented by connecting an otherwise fully connected network with a SoftMax output layer. We combine triplet loss and categorical cross-entropy loss to optimize the training process. In addition, the learning rate of the optimizer is dynamically updated using the cosine annealing mechanism, which improves the convergence of the model during training. Mask face recognition (MFR) experimental results on a custom MASK600 dataset show that proposed InceptionResNetV2 and InceptionV3 use only 20 training epochs, and MobileNetV2 uses only 50 training epochs, but to achieve more than 93% accuracy than the previous works of MFR with annealing. In addition to reaching a practical level, it saves time for training models and effectively reduces energy costs." @default.
- W4385069944 created "2023-07-23" @default.
- W4385069944 creator A5013470161 @default.
- W4385069944 creator A5052094039 @default.
- W4385069944 creator A5076042378 @default.
- W4385069944 creator A5087552792 @default.
- W4385069944 date "2023-07-21" @default.
- W4385069944 modified "2023-09-30" @default.
- W4385069944 title "Combining Classifiers for Deep Learning Mask Face Recognition" @default.
- W4385069944 cites W2739722733 @default.
- W4385069944 cites W2790299973 @default.
- W4385069944 cites W2963163009 @default.
- W4385069944 cites W2964350391 @default.
- W4385069944 cites W2981408674 @default.
- W4385069944 cites W3093217433 @default.
- W4385069944 cites W3096609285 @default.
- W4385069944 cites W3099206234 @default.
- W4385069944 cites W3112696837 @default.
- W4385069944 cites W3186860856 @default.
- W4385069944 cites W3191841357 @default.
- W4385069944 cites W3208637248 @default.
- W4385069944 cites W3217228024 @default.
- W4385069944 cites W4285506605 @default.
- W4385069944 cites W4293192750 @default.
- W4385069944 cites W4307955276 @default.
- W4385069944 cites W4313574384 @default.
- W4385069944 cites W4316660204 @default.
- W4385069944 cites W4319082318 @default.
- W4385069944 cites W4319595423 @default.
- W4385069944 cites W4321194974 @default.
- W4385069944 cites W4372341649 @default.
- W4385069944 cites W4378696923 @default.
- W4385069944 doi "https://doi.org/10.3390/info14070421" @default.
- W4385069944 hasPublicationYear "2023" @default.
- W4385069944 type Work @default.
- W4385069944 citedByCount "0" @default.
- W4385069944 crossrefType "journal-article" @default.
- W4385069944 hasAuthorship W4385069944A5013470161 @default.
- W4385069944 hasAuthorship W4385069944A5052094039 @default.
- W4385069944 hasAuthorship W4385069944A5076042378 @default.
- W4385069944 hasAuthorship W4385069944A5087552792 @default.
- W4385069944 hasBestOaLocation W43850699441 @default.
- W4385069944 hasConcept C108583219 @default.
- W4385069944 hasConcept C119857082 @default.
- W4385069944 hasConcept C153180895 @default.
- W4385069944 hasConcept C154945302 @default.
- W4385069944 hasConcept C167981619 @default.
- W4385069944 hasConcept C188441871 @default.
- W4385069944 hasConcept C31510193 @default.
- W4385069944 hasConcept C41008148 @default.
- W4385069944 hasConcept C50644808 @default.
- W4385069944 hasConcept C5274069 @default.
- W4385069944 hasConcept C81363708 @default.
- W4385069944 hasConceptScore W4385069944C108583219 @default.
- W4385069944 hasConceptScore W4385069944C119857082 @default.
- W4385069944 hasConceptScore W4385069944C153180895 @default.
- W4385069944 hasConceptScore W4385069944C154945302 @default.
- W4385069944 hasConceptScore W4385069944C167981619 @default.
- W4385069944 hasConceptScore W4385069944C188441871 @default.
- W4385069944 hasConceptScore W4385069944C31510193 @default.
- W4385069944 hasConceptScore W4385069944C41008148 @default.
- W4385069944 hasConceptScore W4385069944C50644808 @default.
- W4385069944 hasConceptScore W4385069944C5274069 @default.
- W4385069944 hasConceptScore W4385069944C81363708 @default.
- W4385069944 hasIssue "7" @default.
- W4385069944 hasLocation W43850699441 @default.
- W4385069944 hasOpenAccess W4385069944 @default.
- W4385069944 hasPrimaryLocation W43850699441 @default.
- W4385069944 hasRelatedWork W2610906757 @default.
- W4385069944 hasRelatedWork W2621864722 @default.
- W4385069944 hasRelatedWork W2758063741 @default.
- W4385069944 hasRelatedWork W2883041339 @default.
- W4385069944 hasRelatedWork W2977314777 @default.
- W4385069944 hasRelatedWork W3000978536 @default.
- W4385069944 hasRelatedWork W3156786002 @default.
- W4385069944 hasRelatedWork W3208883981 @default.
- W4385069944 hasRelatedWork W4366723329 @default.
- W4385069944 hasRelatedWork W4381487685 @default.
- W4385069944 hasVolume "14" @default.
- W4385069944 isParatext "false" @default.
- W4385069944 isRetracted "false" @default.
- W4385069944 workType "article" @default.