Light intelligent adjusting system and method based on expression model identification
A technology of expression recognition and intelligent adjustment, applied in the field of pattern recognition
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0127] The first step is to establish an expression model database. First, establish an expression model database with expression model data of calm expressions, happy expressions (taking smiles as an example), sad expressions, and angry expressions.
[0128] The emoticon model library must be specific to the user. A photo of 4 expressions of a specific person is required. Using the same user as the previous one, you need to take pictures of happy expressions, sad expressions and anger, such as Figure 7 , Figure 8 , Picture 9 Shown. Then according to the above steps, the four kinds of expression data are processed in sequence, and the process of processing the expression model data is the same as that of image processing during expression recognition. After the model data is standardized, the distance information between the corresponding points shown in Table 1 is calculated and stored in the expression model library. At this time, there are 4 expression models in the expre...
Embodiment 2
[0141] Still selecting the same person, the model library uses the model library built in Example 1, and another picture is used for testing, such as Picture 11 As shown, the following settlement data are available:
[0142] Test the similarity value of facial features of face and calm expression: Left eyebrow: R lb =8.23%; right eyebrow: R rb = 4.84%; left eye: R le = 81.17%; right eye: R re = 70.46%; mouth: R m =8.24%; the comprehensive similarity between the test face and the calm expression calculated by formula (15): R=37.22%
[0143] Test the similarity value of the facial features of the face and the happy expression: Left eyebrow: R lb =9.12%; right eyebrow: R rb = 20.65%; left eye: R le = 63.05%; right eye: R re =77.5%; mouth: R m =6.46%; the comprehensive similarity between the test face and the calm expression calculated by formula (15): R=38.25%
[0144] Test the similarity value of facial features of human face and sad expression: Left eyebrow: R lb = 28.16%; right eyebr...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com