Preference emotion automatic identification method and system

An automatic recognition and emotion technology, applied in character and pattern recognition, acquisition/recognition of facial features, image data processing, etc., can solve the problems of facial emotion analysis related to consumer preference degree and low accuracy of consumer preference emotion recognition, etc. To achieve the effect of improving the speed and convenience, and improving the recognition effect

Inactive Publication Date: 2020-01-21
UNIV OF SCI & TECH BEIJING
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The technical problem to be solved by the present invention is to provide a method and system for automatic recognition of preferences and emotions to solve the problems in the prior art that the recognition accuracy of consumers' preferences and emotions is low, and the analysis of facial emotions is not directly related to the degree of preference of consumers

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
  • Preference emotion automatic identification method and system
  • Preference emotion automatic identification method and system
  • Preference emotion automatic identification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] Such as figure 1 As shown, the preference emotion automatic recognition method provided by the embodiment of the present invention includes:

[0075] S101, acquiring the testee's facial expression videos under different flavor stimulations and the testee's sensory preference for flavors, and obtaining a direct mapping relationship between the flavor sensory preference and facial responses under stimulation;

[0076] S102, using the facial feature points to align the facial expression images in the facial expression video;

[0077] S103, divide the facial area in the aligned facial expression image into a plurality of regional blocks, extract dense optical flow for each regional block, and perform main direction optimization based on the extracted dense optical flow, and obtain the optical flow of each regional block main flow direction;

[0078] S104, according to the obtained main direction of the optical flow of each area block, determine the combination of area blo...

Embodiment 2

[0158]The present invention also provides a specific embodiment of an automatic preference emotion recognition system. Since the preference emotion automatic recognition system provided by the present invention corresponds to the specific implementation of the aforementioned method for preference emotion automatic recognition, the preference emotion automatic recognition system can perform the above-mentioned The purpose of the present invention is realized by the process steps in the specific implementation of the method. Therefore, the explanations in the specific implementation of the method for automatic recognition of preference emotion are also applicable to the specific implementation of the automatic recognition system for preference emotion provided by the present invention. In the present invention Details will not be described in the following specific implementation manners.

[0159] Such as Figure 7 As shown, the embodiment of the present invention also provides ...

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 a favorite emotion automatic identification method and system, which can improve the rapidness and convenience of sensory favorite degree measurement and improve the identification effect of favorite emotion. The method comprises the steps of acquiring facial expression videos of a testee under stimulation of different flavors and sensory preference of the testee to the flavors; aligning facial expression images in the facial expression video by utilizing the facial feature points; dividing a facial region in the aligned facial expression image into a plurality of regionblocks, extracting dense optical flow from each region block, and performing main direction optimization based on the extracted dense optical flow to obtain an optical flow main direction of each region block; determining a region block combination for emotion level classification according to the obtained optical flow main direction of each region block; and training a classifier for identifyingthe sensory preference degree according to the main direction of the optical flow in the determined regional block combination and the sensory preference degree of the testee to the flavor. The invention relates to the fields of sensory analysis, consumption behavior analysis and artificial intelligence.

Description

technical field [0001] The invention relates to the fields of sensory analysis, consumer behavior analysis and artificial intelligence, in particular to a method and system for automatic recognition of preferences and emotions. Background technique [0002] With the transformation of the economy and the formation of the global market, enterprises are paying more and more attention to the small batch and individual needs of consumers. The needs of consumers will guide the innovation of products and business models of enterprises, and enhance the market competitiveness of enterprises. The famous management expert Hammer once said that it is no longer the seller but the buyer who is the one and the same. It is the consumer who decides what he wants, when he wants it, how he wants it and how much he is willing to pay. It can be seen that only when the product meets the preferences and wishes of consumers can it get good returns. Market competition is not just product competitio...

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): G06K9/00G06K9/62G06T3/00G06T7/11
CPCG06T7/11G06T3/0006G06V40/171G06V40/174G06F18/214
Inventor 支瑞聪王晨阳
Owner UNIV OF SCI & TECH BEIJING
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