Global ETD Search

1	Adaptace neuronových sítí pro identifikaci osob / Model Adaptation in Person Identification Stratil, Jan January 2019 (has links) This thesis deals with facial recognition using convolutional neural networks and with their current problems, which are pose, lighting and expression variance. It summarizes existing approaches, architectures and most recent loss functions. Further it deals with methods for rotating faces using GAN networks. In this thesis 3 neural networks are designed and trained for facial recognition. The best of them achieves 99.38% accuracy on LFW dataset and 88.08% accuracy on CPLFW dataset. Next face rotation network PCGAN is designed, which can be used for face frontalization or data augmentation purposes. This network is evaluated on Multi-PIE dataset and using the face frontalization it increases identification accuracy.
2	Feature extraction on faces : from landmark localization to depth estimation Honari, Sina 12 1900 (has links) No description available. Neural networks Deep learning Convolutional networks Supervised learning Unsupervised learning Semi-supervised learning Coarse-to-fine architectures Landmark localization Depth estimation Face rotation Face replacement Réseaux neuronaux Apprentissage profond Réseaux neuronaux de convolution Apprentissage supervisé Apprentissage non-supervisé Apprentissage semi-supervisé Architectures grossières à fines Localisation de points clés Estimation de la profondeur Rotation de visage Échange de visage

Search results

Adaptace neuronových sítí pro identifikaci osob / Model Adaptation in Person Identification

Feature extraction on faces : from landmark localization to depth estimation