Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Expression variation recognizing method for tensor-based active appearance models

A technology of active appearance model and recognition method, applied in the field of facial expression recognition, which can solve problems such as difficulty in fitting

Inactive Publication Date: 2017-05-31
SHENZHEN WEITESHI TECH
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, fitting AAMs to 2D facial images is difficult, especially for faces that exhibit a wide range of appearance variations

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Expression variation recognizing method for tensor-based active appearance models
  • Expression variation recognizing method for tensor-based active appearance models
  • Expression variation recognizing method for tensor-based active appearance models

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present invention will be further described in detail below in conjunction with the drawings and specific embodiments.

[0067] figure 1 It is a system framework diagram of an expression change recognition method based on a tensor active appearance model of the present invention. It mainly includes tensor-based active appearance model (T-AAM) and unified tensor-based active appearance model (UT-AAM).

[0068] Tensor-based active appearance model (T-AAM) includes active appearance model (AAM) and tensor-based AAM (T-AAM).

[0069] The Active Appearance Model (AAM) has two parametric models based on Principal Component Analysis (PCA), namely the shape and texture models; given a new facial image I, the AAM can use a fitting algorithm to reconstruct and build a model based on the shape and texture informat...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides an expression variation recognizing method for tensor-based active appearance models. The tensor-based active appearance models mainly comprise a tensor-based active appearance model (T-AAM) and a unified tensor-based active appearance model (UT-AAM). The method comprises the following steps: giving a new facial image, reestablishing the active appearance model (AAM) by using a fitting algorithm and carrying out modeling according to the shape and the texture information of the face; constructing a tensor-based shape and texture model through the tensor-based AAM (T-AAM) by using multi-linear subspace analysis; and providing the unified tensor-based active appearance model (UT-AAM) so as to realize unification. The invention provides an effective and accurate model fitting algorithm based on cascade regression for UT-AAM fitting. The detection performance is improved. Influence of postures, expressions, illumination, occlusion and the like is reduced; and the accuracy of recognition is improved.

Description

technical field [0001] The invention relates to the field of expression recognition, in particular to an expression change recognition method based on a tensor active appearance model. Background technique [0002] Facial expression recognition is an important research direction in the field of artificial intelligence, which can automatically recognize human expressions and then analyze human emotions. Expression recognition can be applied in the field of security. In public places, such as airports, subway stations, etc., monitoring equipment such as cameras can be installed to automatically analyze people's expressions and movements. Through these analyzes, people's psychology can be further judged, so as to judge suspicious people. thereby deterring his crimes. Expression change recognition can also be applied to the analysis of customer satisfaction and children's points of interest, and customer feedback can be obtained by recording the expression changes of characters...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/48
CPCG06V40/168G06V10/473G06V10/46
Inventor 夏春秋
Owner SHENZHEN WEITESHI TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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