scholarly journals Facial Expression Recognition Based on Local Features and Monogenic Binary Coding

Informatica ◽  
2019 ◽  
Vol 43 (1) ◽  
Author(s):  
Zhangbao Chen
Keyword(s):  
Facial Expression ◽  
Facial Expression Recognition ◽  
Local Features ◽  
Expression Recognition ◽  
Binary Coding

Facial Expression Recognition Based on Monogenic Binary Coding

2014 ◽  
Vol 511-512 ◽  
pp. 437-440
Author(s):  
Xiao Xiao Xia ◽  
Zi Lu Ying ◽  
Wen Jin Chu
Keyword(s):  
Facial Expression ◽  
Facial Expression Recognition ◽  
Local Variation ◽  
Expression Recognition ◽  
Multi Scale ◽  
Linear Discrimination ◽  
Binary Coding ◽  
Japanese Female ◽  
Feature Based ◽  
Better Than

A new method based on Monogenic Binary Coding (MBC) is proposed for facial expression feature extraction and representation. Firstly, monogenic signal analysis is used to extract multi-scale magnitude, orientation and phase components. Secondly, Monogenic Binary Coding (MBC) is used to encode the monogenic local variation and intensity in local regions of each extracted component in each scale and local histograms are built. Then Blocked Fisher Linear Discrimination (BFLD) is used to reduce the dimensionality of histogram features and to enhance discrimination. Finally the three complementary components are fused for more effective facial expression recognition (FER). Experiment results on Japanese female expression database (JAFFE) show that the performance of the fusion method is even better than state-of-the-art local feature based FER methods such as Local Binary Pattern (LBP)+Sparse Representation (SRC), Local Phase Quantization (LPQ)+SRC ,etc.

Facial Expression Recognition Based on Fusion of Local Features and Deep Belief Network

2018 ◽  
Vol 55 (1) ◽  
pp. 011002 ◽  
Author(s):  
王琳琳 Wang Linlin ◽  
刘敬浩 Liu Jinghao ◽  
付晓梅 Fu Xiaomei
Keyword(s):  
Facial Expression ◽  
Facial Expression Recognition ◽  
Local Features ◽  
Deep Belief Network ◽  
Expression Recognition ◽  
Belief Network
Sign in / Sign up

Export Citation Format

Share Document