Micro expression recognition method based on multi-feature multi-task dictionary sparse migration learning
A transfer learning and recognition method technology, applied in the field of modal recognition and machine learning, can solve the problems of incomplete sample label information, small number of micro-expression databases, unsatisfactory results, etc., and achieve the effect of improving recognition performance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0066] Example 1
[0067] A micro-expression recognition method based on sparse migration learning of multi-feature and multi-task macro expression dictionary, such as figure 1 Shown, including training phase, testing phase;
[0068] A. The training phase includes the following steps:
[0069] (1) Divide each picture in the micro-expression domain into several blocks; examples of sample pictures in the macro-expression domain are as figure 2 As shown; examples of sample pictures in the micro expression domain are as image 3 Shown
[0070] (2) Extract the most representative features of the macro expression domain and the micro expression domain; for the macro expression domain, the most representative feature extracted is the LBP feature; the LBP feature is the most representative texture feature of the macro expression domain; In order to fully reflect the characteristics of the dynamic sequence of micro-expression, for each segment in the micro-expression domain, the most represe...
Example Embodiment
[0079] Example 2
[0080] According to the micro-expression recognition method based on the sparse migration learning of the multi-feature multi-task macro-expression dictionary described in Embodiment 1, the difference is that:
[0081] The step (2), extracting the most representative features from the macro expression domain and the micro expression domain, includes:
[0082] a. Perform feature extraction on the macro expression domain and the micro expression domain. For the macro expression domain, the extracted features n x Refers to the number of samples in the macro expression domain; Refers to n in the macro expression domain x LBP features extracted from samples, R refers to the size of matrix X; m x Refers to the feature dimension of the macro expression domain;
[0083] For the micro-expression domain, since the micro-expression has extracted four different sets of features, the extracted features n y Refers to the number of samples in the micro expression domain;
[0084]...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2023 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap