Three-dimensional face expression recognition method based on SSF-IL-CNN

A SSF-IL-CNN, three-dimensional face technology, applied in the field of three-dimensional facial expression recognition, can solve the problems of multiple interference information, insignificant changes in facial expressions, and the sensitivity of expression changes needs to be enhanced, and achieves high recognition rate. High discriminative and discriminative ability, the effect of comprehensive feature learning

Active Publication Date: 2019-08-30
SOUTHEAST UNIV
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Second, the sensitivity of the loss function of the convolutional neural network to expression changes needs to be enhanced
However, since the changes in facial expres

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
  • Three-dimensional face expression recognition method based on SSF-IL-CNN
  • Three-dimensional face expression recognition method based on SSF-IL-CNN
  • Three-dimensional face expression recognition method based on SSF-IL-CNN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings:

[0035] The present invention is a three-dimensional facial expression recognition algorithm based on SSF-IL-CNN (Structure and Strength Filtered CNN based on Island Loss). Its purpose is to build a convolutional neural network suitable for three-dimensional facial expression samples to achieve efficient three-dimensional facial expression recognition. The implementation of this algorithm includes:

[0036] 1) First, build the structure of the SSF-IL-CNN model. Like other convolutional neural network (CNN) models, the SSF-IL-CNN model has modules such as convolutional layer, pooling layer, activation function, full link layer, and loss function. In particular, the SSF-IL-CNN model also has a feature fusion layer, so that the model can learn texture images and depth images corresponding to three-dimensional faces at the same time, and can...

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 discloses a three-dimensional face expression recognition method based on an SSF-IL-CNN. According to the method, firstly, a convolutional neural network structure is improved, a convolutional kernel is disassembled into the structure parameters and the strength parameters, and the two parameters are enabled to respectively undertake the initialization and updating tasks, so that theconvolutional neural network originally needing a large number of samples for training can be applied to a three-dimensional facial expression library with a small sample scale. Meanwhile, accordingto the method, an Island Loss function is adopted to construct a loss function in the convolutional neural network, the sensitivity and the distinction degree of the network to the facial expressionsare enhanced, and the expression recognition effect is improved.

Description

Technical field [0001] The invention relates to a three-dimensional facial expression recognition method based on SSF-IL-CNN, which belongs to the field of three-dimensional image recognition in computer vision. Background technique [0002] The three-dimensional facial expression recognition technology refers to the technology of facial expression recognition based on the three-dimensional data of the human face. This technology has huge application potential in the fields of human-computer interaction and psychology research. Compared with two-dimensional data, the three-dimensional data of a face is not affected by factors such as light, posture, angle, etc., and contains richer geometric information and topological features. Therefore, the research on facial expression recognition based on three-dimensional face data has gained more attention in recent years. Widespread concern. Faced with complex and diverse application scenarios, it will become more difficult to generate ...

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
IPC IPC(8): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V20/64G06V40/174G06N3/045Y02T10/40
Inventor 达飞鹏余璟
Owner SOUTHEAST UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap