Figure - available from: International Journal of Advanced Robotic Systems
This content is subject to copyright.
Source publication
It is an interesting and challenging problem to synthesise vivid facial expression images. In this paper, we propose a facial expression synthesis system which imitates a reference facial expression image according to the difference between shape feature vectors of the neutral image and expression image. To improve the result, two stages of postpro...
Similar publications
The facial expression recognition in the real-world
environment is much more challenging than it in the laboratory
environment. We hope that the intra-class distance is relatively
small and the inter-class distance is relatively large in the feature
space. The solution of variations resulting from different
subjects, postures and other non-expressi...
Citations
... Yihjia Tsai et al. (2017) studied and designed a model in which facial expressions can be generated based on imitation. The difference between shape feature vectors of neutral image and expression image is used to imitate the facial expression. ...
Facial expressions are an important means of communication among human beings, as they convey different meanings in a variety of contexts. All human facial expressions, whether voluntary or involuntary, are formed as a result of movement of different facial muscles. Despite their variety and complexity, certain expressions are universally recognized as representing specific emotions - for instance, raised eyebrows in combination with an open mouth are associated with surprise, whereas a smiling face is generally interpreted as happy. Deep learning based implementations of expression synthesis have demonstrated their ability to preserve essential features of input images, which is desirable. However, one limitation of using deep learning networks is that their dependence on data distribution and the quality of images used for training purposes. The variation in performance can be studied by changing the optimizer and loss functions, and their effectiveness is analysed based on the quality of output images obtained.
Facial pose synthesis is applied to generatemuch required information for several applications, such as public security, facial cosmetology, etc. How to synthesize facial pose images from one image accurately without spatial information is still a challenging problem. In this chapter we propose a tensor-based subspace learning method (TSL) for synthesizing human multi-pose facial images from a single twodimensional image. In the proposed TSL method, two-dimensional multi-pose images in the database are previously organized into a tensor form and a tensor decomposition technique is applied to build projection subspaces. In synthesis processing, the input two-dimensional image is first projected into its corresponding projection subspace to get an identity vector and then the identity vector is used to generate other novel pose images. Our technique is applied onKAO-RitsumeikanMulti-AngleView, Illumination and Cosmetic Facial Database(MaVIC) and experimental results show the effectiveness of our proposed method for facial pose synthesis.
