Matches in SemOpenAlex for { <https://semopenalex.org/work/W2929482630> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2929482630 abstract "In this paper we develop a Quality Assessment approach for face recognition based on deep learning. The method consists of a Convolutional Neural Network, FaceQnet, that is used to predict the suitability of a specific input image for face recognition purposes. The training of FaceQnet is done using the VGGFace2 database. We employ the BioLab-ICAO framework for labeling the VGGFace2 images with quality information related to their ICAO compliance level. The groundtruth quality labels are obtained using FaceNet to generate comparison scores. We employ the groundtruth data to fine-tune a ResNet-based CNN, making it capable of returning a numerical quality measure for each input image. Finally, we verify if the FaceQnet scores are suitable to predict the expected performance when employing a specific image for face recognition with a COTS face recognition system. Several conclusions can be drawn from this work, most notably: 1) we managed to employ an existing ICAO compliance framework and a pretrained CNN to automatically label data with quality information, 2) we trained FaceQnet for quality estimation by fine-tuning a pre-trained face recognition network (ResNet-50), and 3) we have shown that the predictions from FaceQnet are highly correlated with the face recognition accuracy of a state-of-the-art commercial system not used during development. FaceQnet is publicly available in GitHub." @default.
- W2929482630 created "2019-04-11" @default.
- W2929482630 creator A5014609627 @default.
- W2929482630 creator A5019135461 @default.
- W2929482630 creator A5038880089 @default.
- W2929482630 creator A5056531316 @default.
- W2929482630 creator A5068081385 @default.
- W2929482630 date "2019-04-03" @default.
- W2929482630 modified "2023-09-27" @default.
- W2929482630 title "FaceQnet: Quality Assessment for Face Recognition based on Deep Learning" @default.
- W2929482630 cites W1506836750 @default.
- W2929482630 cites W1988558213 @default.
- W2929482630 cites W2024804726 @default.
- W2929482630 cites W2071266191 @default.
- W2929482630 cites W2144942180 @default.
- W2929482630 cites W2163865841 @default.
- W2929482630 cites W2180240608 @default.
- W2929482630 cites W2194775991 @default.
- W2929482630 cites W2548780814 @default.
- W2929482630 cites W2776637495 @default.
- W2929482630 cites W2793964976 @default.
- W2929482630 cites W2871667416 @default.
- W2929482630 cites W2963839617 @default.
- W2929482630 cites W3101998545 @default.
- W2929482630 cites W3142692140 @default.
- W2929482630 hasPublicationYear "2019" @default.
- W2929482630 type Work @default.
- W2929482630 sameAs 2929482630 @default.
- W2929482630 citedByCount "4" @default.
- W2929482630 countsByYear W29294826302020 @default.
- W2929482630 countsByYear W29294826302021 @default.
- W2929482630 crossrefType "posted-content" @default.
- W2929482630 hasAuthorship W2929482630A5014609627 @default.
- W2929482630 hasAuthorship W2929482630A5019135461 @default.
- W2929482630 hasAuthorship W2929482630A5038880089 @default.
- W2929482630 hasAuthorship W2929482630A5056531316 @default.
- W2929482630 hasAuthorship W2929482630A5068081385 @default.
- W2929482630 hasConcept C108583219 @default.
- W2929482630 hasConcept C111472728 @default.
- W2929482630 hasConcept C115961682 @default.
- W2929482630 hasConcept C119857082 @default.
- W2929482630 hasConcept C138885662 @default.
- W2929482630 hasConcept C144024400 @default.
- W2929482630 hasConcept C153180895 @default.
- W2929482630 hasConcept C154945302 @default.
- W2929482630 hasConcept C2779304628 @default.
- W2929482630 hasConcept C2779530757 @default.
- W2929482630 hasConcept C31510193 @default.
- W2929482630 hasConcept C31972630 @default.
- W2929482630 hasConcept C36289849 @default.
- W2929482630 hasConcept C41008148 @default.
- W2929482630 hasConcept C50644808 @default.
- W2929482630 hasConcept C55020928 @default.
- W2929482630 hasConcept C81363708 @default.
- W2929482630 hasConceptScore W2929482630C108583219 @default.
- W2929482630 hasConceptScore W2929482630C111472728 @default.
- W2929482630 hasConceptScore W2929482630C115961682 @default.
- W2929482630 hasConceptScore W2929482630C119857082 @default.
- W2929482630 hasConceptScore W2929482630C138885662 @default.
- W2929482630 hasConceptScore W2929482630C144024400 @default.
- W2929482630 hasConceptScore W2929482630C153180895 @default.
- W2929482630 hasConceptScore W2929482630C154945302 @default.
- W2929482630 hasConceptScore W2929482630C2779304628 @default.
- W2929482630 hasConceptScore W2929482630C2779530757 @default.
- W2929482630 hasConceptScore W2929482630C31510193 @default.
- W2929482630 hasConceptScore W2929482630C31972630 @default.
- W2929482630 hasConceptScore W2929482630C36289849 @default.
- W2929482630 hasConceptScore W2929482630C41008148 @default.
- W2929482630 hasConceptScore W2929482630C50644808 @default.
- W2929482630 hasConceptScore W2929482630C55020928 @default.
- W2929482630 hasConceptScore W2929482630C81363708 @default.
- W2929482630 hasLocation W29294826301 @default.
- W2929482630 hasOpenAccess W2929482630 @default.
- W2929482630 hasPrimaryLocation W29294826301 @default.
- W2929482630 hasRelatedWork W1937026393 @default.
- W2929482630 hasRelatedWork W1991777678 @default.
- W2929482630 hasRelatedWork W2022456440 @default.
- W2929482630 hasRelatedWork W2062212345 @default.
- W2929482630 hasRelatedWork W2149705965 @default.
- W2929482630 hasRelatedWork W2175082661 @default.
- W2929482630 hasRelatedWork W2234866176 @default.
- W2929482630 hasRelatedWork W2793964976 @default.
- W2929482630 hasRelatedWork W2903975231 @default.
- W2929482630 hasRelatedWork W2922433978 @default.
- W2929482630 hasRelatedWork W2963839617 @default.
- W2929482630 hasRelatedWork W3006276840 @default.
- W2929482630 hasRelatedWork W3035460915 @default.
- W2929482630 hasRelatedWork W3080221988 @default.
- W2929482630 hasRelatedWork W3135042526 @default.
- W2929482630 hasRelatedWork W3147297818 @default.
- W2929482630 hasRelatedWork W3169662560 @default.
- W2929482630 hasRelatedWork W3171989036 @default.
- W2929482630 hasRelatedWork W3211201073 @default.
- W2929482630 hasRelatedWork W1499713072 @default.
- W2929482630 isParatext "false" @default.
- W2929482630 isRetracted "false" @default.
- W2929482630 magId "2929482630" @default.
- W2929482630 workType "article" @default.