Explainability of the Implications of Supervised and Unsupervised Face Image Quality Estimations Through Activation Map Variation Analyses in Face Recognition Models.
Biying FuNaser DamerPublished in: CoRR (2021)
Keyphrases
- image quality
- face recognition
- face images
- unsupervised learning
- human faces
- face identification
- image data
- supervised learning
- feature selection
- method for face recognition
- unsupervised methods
- quality assessment
- recognition rate
- facial expressions
- learning algorithm
- visual quality
- linear discriminant analysis
- discriminant analysis
- facial images
- face databases
- bit rate
- supervised classification
- supervised methods
- supervised training