Character relationship visual analysis method based on social photos

A technology of character relationship and analysis method, applied in the field of computer graphics, can solve the problems of low accuracy and intuition, and achieve the effect of objective data and accurate relationship acquisition

Pending Publication Date: 2020-08-07
ZHEJIANG UNIV OF TECH
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention aims to overcome the shortcomings of the existing methods for analyzing the relationship between people in social photos, and provides a method for analyzing the relationship between people in social photos using computer technology. The information in the database builds the social relationship between the characters in the photo, and then displays it in a visual way of the node chain

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
  • Character relationship visual analysis method based on social photos
  • Character relationship visual analysis method based on social photos

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] With reference to the drawings, the present invention will be further explained:

[0016] The visual analysis method of person relationship based on social photos includes the following steps:

[0017] Step 1. Use a Convolutional Neural Network (CNN) face detection model to detect the face area to be recognized in the photo.

[0018] Step 2. Use the face recognition model of the deep residual network (ResNet) to obtain 128-dimensional face feature data, and match the obtained face feature data with the feature template stored in the database, and compare the threshold to obtain the matched result.

[0019] Step 3. Obtain the relational data of the identified object from the database, and construct a social relational network.

[0020] Step 4. Visualize the social network through force-guided layout.

[0021] In the step 1, the Convolutional Neural Network (CNN) face detection model is provided by the third-party face detection Dlib library, and the face area to be recognized in t...

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 character relationship visual analysis method based on social photos. A convolutional neural network (CNN) face detection model is used for detecting a to-be-recognized facearea in the photo; 128-dimensional face feature data is obtainedby using a face recognition model of a deep residual network (ResNet), the obtained face feature data is matchedwith a feature templatestored in a database, and a matched result is obtainedby comparing threshold values; relationship data of the identification object is obtainedfrom a database, and a social relationship network is constructed; and finally, the social relation network is displayed in a force guidance layout visualization mode. According to the invention, the human face in the social photo can be recognized, and thesocial relation network among the figures in the photo is constructed and displayed through a visualization method.

Description

Technical field [0001] The present invention relates to the field of computer graphics, in particular to a method for analyzing the relationship between people in social photos using computer technology, which can recognize faces in social photos, construct a social relationship network between people in photos, and display them through a visualization method. Background technique [0002] With the popularization of digital photography equipment such as digital cameras and smartphones, taking photos has become an indispensable part of social activities such as friend gatherings, event celebrations, academic reports, and weddings, which are called "social photos". The relationship between members participating in social activities is implied in social photos. Even if two people who don’t know each other appear in the same photo, there must be some connection between them, or they have common friends, or they have common hobbies, or they have common research directions, etc. . Ex...

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): G06F16/9536G06Q50/00G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06F16/9536G06Q50/01G06N3/08G06V40/172G06N3/045G06F18/241
Inventor 黄可妤陈樟樟陈佳舟秦绪佳汪雨薇
Owner ZHEJIANG UNIV OF TECH
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