Abstract
The recognition of human emotions from facial expression images is one of the most important topics in the machine vision and image processing fields. However, recognition becomes difficult when dealing with non-frontal faces. To alleviate the influence of poses, we propose an encoder-decoder generative adversarial network that can learn pose-invariant and expression-discriminative representations. Specifically, we assume that a facial image can be divided into an expressive component, an identity component, a head pose component and a remaining component. The encoder encodes each component into a feature representation space and the decoder recovers the original image from these encoded features. A classification loss on the components and an l 1 pixel-wise loss are applied to guarantee the rebuilt image quality and produce more constrained visual representations. Quantitative and qualitative evaluations on two multi-pose datasets demonstrate that the proposed algorithm performs favorably compared to state-of-the-art methods.
Highlights
The image-based analysis of human behavior has become a very popular topic in affective computing and cognitive science
We present an facial expression recognition (FER) approach based on generative adversarial network (GAN)
The main contributions of our work are summarized as follows: 1. We propose a novel FER framework for non-frontal facial images
Summary
The image-based analysis of human behavior has become a very popular topic in affective computing and cognitive science. Facial expression is one of the most powerful signals for human beings to convey their emotional intentions and states. Mehrabian and Ferris [1] showed that among all emotion expression contributory factors, facial expressions contribute 55% to the message effect, while 7% and 38% are attributed to the verbal and vocal parts, respectively. Facial expression recognition (FER) has attracted significant research attention because of its usefulness in many applications, such as digital entertainment, custom services, emotion robots, and human-computer interfaces (HCIs) [2]. It is a difficult task to build a robust FER system given challenging factors such as pose variations, unconstrained facial expressions, and uncontrolled circumstances (wild settings). One is to analyze and classify a given facial image into one or more
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have