Title :
Analysis and compression of facial animation parameter set (FAPs)
Author :
Tao, Hai ; Chen, Homer ; Huang, Thomas
Author_Institution :
Beckman Inst. for Adv. Sci. & Technol., Illinois Univ., Urbana, IL, USA
Abstract :
In this paper, a new representation of FAPs based on principal component analysis is proposed. Based on this compact representation, a FAPs compression scheme is designed. A facial expression recognition algorithm using recurrent neural network is also investigated. The inputs to the network are the most significant components of this new data representation. Experimental results show that computational complexity is reduced and expressions can be correctly recognized even with changed sampling rate
Keywords :
computational complexity; computer animation; data compression; data structures; face recognition; image coding; recurrent neural nets; computational complexity; data representation; facial animation parameter set; facial expression recognition algorithm; principal component analysis; recurrent neural network; sampling rate; Computational complexity; Covariance matrix; Face recognition; Facial animation; Financial advantage program; Hidden Markov models; Image sampling; Principal component analysis; Recurrent neural networks; Rendering (computer graphics);
Conference_Titel :
Multimedia Signal Processing, 1997., IEEE First Workshop on
Conference_Location :
Princeton, NJ
Print_ISBN :
0-7803-3780-8
DOI :
10.1109/MMSP.1997.602643
