Voice emotion and facial expression bimodal recognition system

A facial expression, recognition system technology, applied in character and pattern recognition, acquisition/recognition of facial features, computer parts and other directions, can solve the problems of long analysis time and poor efficiency, and achieve enhanced performance, rapid analysis and screening. Effect

Pending Publication Date: 2020-01-21
湖南检信智能科技有限公司
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] 3Patient diagnosis is based on the determination of the current test item based on the level of mental state. Through blood extraction, the test analysis includes whether the positive item is included, the analysis time is long, and the efficiency is poor.

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
  • Voice emotion and facial expression bimodal recognition system
  • Voice emotion and facial expression bimodal recognition system
  • Voice emotion and facial expression bimodal recognition system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] In this embodiment, the dual-mode emotion recognition system of voice emotion and facial expression mainly includes four parts: input of emotion data and its preprocessing, extraction of emotion features, emotion recognition, and feature fusion.

[0042]First of all, the input of emotion data needs to select and establish the emotion database used (we choose the data set used for the Emotion Recognition In The WildChallenge (EmotiW) series of emotion recognition challenges), which has data annotations of seven common expressions .

[0043] First of all, the input of the first step emotion data needs to select and establish the emotion database used (we choose the dataset used for the Emotion Recognition In The WildChallenge (EmotiW) series of emotion recognition challenges), which has seven common expressions data labeling.

[0044] The second step is to select an appropriate preprocessing method according to the data characteristics of different databases and the char...

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 voice emotion and facial expression bimodal recognition system. The system comprises an emotion data input and preprocessing module, an emotion feature extraction module anda feature fusion emotion recognition module. The emotion data input and preprocessing module is used for selecting and establishing a used emotion database and selecting a preprocessing method according to data characteristics of different databases and characteristics of different modal data; the emotion feature extraction module is used for extracting expression features and voice features, andthe expression features comprise LBP features. The difference between different modal characteristics and different characteristic types is considered under the condition of keeping the integrity of overall information, the fusion performance of the characteristic layers is enhanced, and on the basis of establishing big data, a neural network model and the like, a training database is establishedthrough data acquisition and annotation, so that the condition of a mental patient can be quickly analyzed and screened.

Description

technical field [0001] The invention relates to the technical field of psychoanalysis, and more specifically, to a dual-mode recognition system for voice emotion and facial expression. Background technique [0002] At present, mental illness is a common disease that plagues our human psychological and emotional experience, especially in the era of rapid economic development and fast-paced people's life in our country. The working people are busy with daily business. Regarding the issue of support for the elderly, different environments have different social problems that lead to different mental illness hazards. Due to the current high pressure in people's lives, people of different ages have different practical problems, which nourishes the occurrence of mental diseases. For example, a child with autism, working with depression due to different social environments, schizophrenia (1 mental disorder caused by epilepsy, 2 schizophrenia, 3 paranoid schizophrenia, 4 catatonic s...

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): G06K9/00G06K9/62G16H50/20
CPCG16H50/20G06V40/174G06F18/253G06F18/214
Inventor 不公告发明人
Owner 湖南检信智能科技有限公司
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