This paper presents a software based on an innovative Convolutional Neural Network model to recognize the six Ekman's universal emotions from the photos of human faces captured in the wild. The CNN was trained using three different datasets already labeled and merged after making them homogeneous. A comparison among different types of CNN architectures using the Keras framework for Python language is proposed and the evaluation results are presented.
Evaluation of Deep Convolutional Neural Network architectures for Emotion Recognition in the Wild
Giraldi Luca
2019-01-01
Abstract
This paper presents a software based on an innovative Convolutional Neural Network model to recognize the six Ekman's universal emotions from the photos of human faces captured in the wild. The CNN was trained using three different datasets already labeled and merged after making them homogeneous. A comparison among different types of CNN architectures using the Keras framework for Python language is proposed and the evaluation results are presented.
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
2019_Evaluation of Deep Convolutional Neural Network Architectures for emotion recognition in the Wild.pdf
Accesso riservato
Descrizione: Paper
Tipo di file:
PDF EDITORIALE
Dimensione
777.09 kB
Formato
Adobe PDF
|
777.09 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
