Matches in SemOpenAlex for { <https://semopenalex.org/work/W4316021154> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4316021154 abstract "When constructing a face recognition model, many face images for each person are required for the model to perform well. Face data augmentation is a popular technique to create variations of face poses via angular head movements, e.g., yaw, pitch, and roll. This study used convolutional neural networks, ResNet-50, MobileNetV3-Large, and SeResNet18 models to evaluate the impact of face data augmentation on the performance of the models. The training was performed using the FaceScrub dataset to evaluate the performance of the face data augmentation approach using a batch size of 20, a learning rate of 0.001, and 150 epochs. The results demonstrate that the SeResNet18 model obtained the highest accuracy (0.8719) with a loss of 1.5106. Before increasing the amount of face data through various poses, the accuracy of the SeResNet18 model was only 0.8108, with a loss of 1.5513. We also discovered that the original data combined with all angular head movements (yaw, pitch, and roll) produced the best result for all models." @default.
- W4316021154 created "2023-01-14" @default.
- W4316021154 creator A5015860477 @default.
- W4316021154 creator A5043900478 @default.
- W4316021154 creator A5050567658 @default.
- W4316021154 creator A5058879962 @default.
- W4316021154 creator A5069923818 @default.
- W4316021154 date "2022-12-08" @default.
- W4316021154 modified "2023-09-27" @default.
- W4316021154 title "Analysis of Face Data Augmentation in Various Poses for Face Recognition Model" @default.
- W4316021154 cites W122389516 @default.
- W4316021154 cites W2024922353 @default.
- W4316021154 cites W2025217965 @default.
- W4316021154 cites W2194775991 @default.
- W4316021154 cites W2763177262 @default.
- W4316021154 cites W2769905613 @default.
- W4316021154 cites W2797558164 @default.
- W4316021154 cites W2929968583 @default.
- W4316021154 cites W2937343562 @default.
- W4316021154 cites W2954996726 @default.
- W4316021154 cites W2997604048 @default.
- W4316021154 cites W3040887178 @default.
- W4316021154 cites W3099206234 @default.
- W4316021154 cites W3099319035 @default.
- W4316021154 cites W3217427959 @default.
- W4316021154 cites W4200120709 @default.
- W4316021154 doi "https://doi.org/10.1109/icic56845.2022.10006997" @default.
- W4316021154 hasPublicationYear "2022" @default.
- W4316021154 type Work @default.
- W4316021154 citedByCount "0" @default.
- W4316021154 crossrefType "proceedings-article" @default.
- W4316021154 hasAuthorship W4316021154A5015860477 @default.
- W4316021154 hasAuthorship W4316021154A5043900478 @default.
- W4316021154 hasAuthorship W4316021154A5050567658 @default.
- W4316021154 hasAuthorship W4316021154A5058879962 @default.
- W4316021154 hasAuthorship W4316021154A5069923818 @default.
- W4316021154 hasConcept C144024400 @default.
- W4316021154 hasConcept C153180895 @default.
- W4316021154 hasConcept C154945302 @default.
- W4316021154 hasConcept C2779304628 @default.
- W4316021154 hasConcept C28490314 @default.
- W4316021154 hasConcept C31510193 @default.
- W4316021154 hasConcept C31972630 @default.
- W4316021154 hasConcept C36289849 @default.
- W4316021154 hasConcept C41008148 @default.
- W4316021154 hasConcept C51632099 @default.
- W4316021154 hasConcept C67186912 @default.
- W4316021154 hasConcept C77088390 @default.
- W4316021154 hasConcept C81363708 @default.
- W4316021154 hasConceptScore W4316021154C144024400 @default.
- W4316021154 hasConceptScore W4316021154C153180895 @default.
- W4316021154 hasConceptScore W4316021154C154945302 @default.
- W4316021154 hasConceptScore W4316021154C2779304628 @default.
- W4316021154 hasConceptScore W4316021154C28490314 @default.
- W4316021154 hasConceptScore W4316021154C31510193 @default.
- W4316021154 hasConceptScore W4316021154C31972630 @default.
- W4316021154 hasConceptScore W4316021154C36289849 @default.
- W4316021154 hasConceptScore W4316021154C41008148 @default.
- W4316021154 hasConceptScore W4316021154C51632099 @default.
- W4316021154 hasConceptScore W4316021154C67186912 @default.
- W4316021154 hasConceptScore W4316021154C77088390 @default.
- W4316021154 hasConceptScore W4316021154C81363708 @default.
- W4316021154 hasLocation W43160211541 @default.
- W4316021154 hasOpenAccess W4316021154 @default.
- W4316021154 hasPrimaryLocation W43160211541 @default.
- W4316021154 hasRelatedWork W1548715306 @default.
- W4316021154 hasRelatedWork W1560697087 @default.
- W4316021154 hasRelatedWork W1989039360 @default.
- W4316021154 hasRelatedWork W2060029454 @default.
- W4316021154 hasRelatedWork W2136485282 @default.
- W4316021154 hasRelatedWork W2146295394 @default.
- W4316021154 hasRelatedWork W2521062615 @default.
- W4316021154 hasRelatedWork W2545171730 @default.
- W4316021154 hasRelatedWork W2908959303 @default.
- W4316021154 hasRelatedWork W2976316911 @default.
- W4316021154 isParatext "false" @default.
- W4316021154 isRetracted "false" @default.
- W4316021154 workType "article" @default.