Analysis of hand-crafted and learned feature extraction methods for real-time facial expression recognition
Jesús Olivares-Mercado, Karina Toscano-Medina, Gabriel Sánchez-Pérez, José Portillo-Portillo, Hector Manuel Perez-Meana, Gibran Benítez-García · 2019
This paper presents an analysis of hand-crafted and learned feature extraction methods for real-time facial expression recognition (FER). Our analysis focuses on methods capable of running on mobile devices, including traditional algorithms such as Gabor transform, HOG, LBP, as well as two compact CNN models, named Mobilenet V1 and V2. Additionally, we test the performance of MOTIF, a highly efficient texture feature extractor algorithm. Furthermore, we analyze the contribution of the mouth and front-eyes regions for recognizing the seven basic facial expressions. Experimental results are evaluated on two publicly available datasets. KDEF database which was captured under controlled conditions and RAF database which represents more naturalistic expressions captured in-the-wild. Under the same experimental conditions, MOTIF presents the fastest performance by sacrificing accuracy, while Mobilenet V2 presents the highest results with considerable speed and model size.