Micro-Expression Recognition Algorithm Based on Information Entropy Feature
- PDF / 1,690,703 Bytes
- 11 Pages / 612.284 x 810.709 pts Page_size
- 68 Downloads / 228 Views
Micro-Expression Recognition Algorithm Based on Information Entropy Feature WU Jin ∗ (
),
MIN Yu (
),
Ê),
YANG Xiaodie (
MA Simin (
)
(School of Electronic Engineering, Xi’an University of Posts and Telecommunications, Xi’an 710121, China)
© Shanghai Jiao Tong University and Springer-Verlag GmbH Germany, part of Springer Nature 2020 Abstract: The intensity of the micro-expression is weak, although the directional low frequency components in the image are preserved by many algorithms, the extracted micro-expression feature information is not sufficient to accurately represent its sequences. In order to improve the accuracy of micro-expression recognition, first, each frame image is extracted from its sequences, and the image frame is pre-processed by using gray normalization, size normalization, and two-dimensional principal component analysis(2DPCA); then, the optical flow method is used to extract the motion characteristics of the reduced-dimensional image, the information entropy value of the optical flow characteristic image is calculated by the information entropy principle, and the information entropy value is analyzed to obtain the eigenvalue. Therefore, more micro-expression feature information is extracted, including more important information, which can further improve the accuracy of micro-expression classification and recognition; finally, the feature images are classified by using the support vector machine(SVM). The experimental results show that the micro-expression feature image obtained by the information entropy statistics can effectively improve the accuracy of micro-expression recognition. Key words: micro-expression recognition, two-dimensional principal component analysis (2DPCA), optical flow, information entropy statistics, support vector machine (SVM) CLC number: TP 391.4 Document code: A
0 Introduction Micro-expression is a subtle expression that the facial muscles exist in the subconscious mind in emotional states such as tension, happiness and sadness. It has the characteristics of short duration, weak amplitude and local motion asymmetry[1-2] . First, its subtle movements and short time are the huge challenges for the human eyes[3] . Second, the micro-expression uses an image sequence to represent an emotional tag[4] , the micro expression image sequence and gait sequence are regarded as the third-order tensor, and the optimal projection matrix is found. This paper attempts to optimize the difference between inter-class Laplace divergence and intra-class Laplace divergence. Multilinear principal component analysis (MPCA) is used as the pretreatment to find a suitable linear transformation in the original high-dimensional space for optimal matrix projection, and then K-nearest neighbor Received date: 2019-07-02 Foundation item: the National Natural Science Foundation of China (Nos. 61772417, 61634004, and 61602377), the Key R&D Program Projects in Shaanxi Province (No. 2017GY-060), and the Shaanxi Natural Science Basic Research Project (No. 2018JM4018) ∗E-mail: [email protected]
(KNN) i
Data Loading...
