Multi-information fusion picture auditing method and system

A multi-information fusion and image technology, applied in the field of multi-information fusion image review methods and systems, can solve the problems of uneven quality of uploaded images, low review efficiency, and impact on website quality, so as to reduce labor costs and improve review. The effect of efficiency and accuracy

Inactive Publication Date: 2019-10-22
FOCUS TECH
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Due to the huge amount of uploaded pictures on the e-commerce website platform every day, the quality of the uploaded pictures is uneven. At the same time, some pictures do not meet the requirements and rules of the website. There are illegal information in the pictures, such as infringement information, violent slogans, pornographic information, etc. Manual review, the labor cost is huge, the review efficiency is not high, and it is easy to affect the quality of the website

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
  • Multi-information fusion picture auditing method and system
  • Multi-information fusion picture auditing method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The present invention will be further described below in conjunction with accompanying drawing and exemplary embodiment:

[0024] Such as figure 1 As shown, a multi-information fusion image review method includes the following steps:

[0025] Step S1: Enter the picture uploaded by the seller to obtain the basic information of the picture.

[0026] Step S2: Input the picture into the infringement information review module for infringement information review, use the multi-layer neural network in the infringement information review module to detect whether there is any infringement information in the picture, if there is, record the infringement information and its location in the picture.

[0027] Step S3: Input the picture into the pornography-related information review module for pornography-related information review, use the multi-layer neural network in the pornography-related information review module to extract the feature information of the picture, and judge wh...

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 multi-information fusion picture auditing method and a multi-information fusion picture auditing system. The method is characterized by comprising the steps: 1, inputting a picture uploaded by a seller, and obtaining the basic information of the picture; 2, inputting the picture into an infringement information auditing module for infringement information auditing; 3, inputting the picture into a yellow-related information auditing module for yellow-related information auditing; and step 4, inputting the picture into a text information auditing module for text information auditing. According to the method, whether violation conditions such as infringement, yellowing and violent terrorism exist in the picture or not can be quickly and accurately identified. Meanwhile, the picture quality is given, and the manpower expenditure of picture auditing is greatly reduced. The auditing efficiency and accuracy are improved.

Description

technical field [0001] The invention relates to the field of automatic picture review, in particular to a picture review method and system for multi-information fusion. Background technique [0002] At present, sellers on the e-commerce website platform mainly use pictures and text to display their products, among which pictures are more intuitive and comprehensive, which are well recognized by buyers. Therefore, picture display has become one of the main display methods for product display. [0003] Due to the huge amount of uploaded pictures on the e-commerce website platform every day, the quality of the uploaded pictures is uneven. At the same time, some pictures do not meet the requirements and rules of the website. There are illegal information in the pictures, such as infringement information, violent slogans, pornographic information, etc. Manual review, the labor cost is huge, the review efficiency is not high, and it is easy to affect the quality of the website. ...

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): G06F16/958G06F16/55G06K9/32G06K9/62
CPCG06F16/958G06F16/55G06V20/635G06V30/10G06F18/241
Inventor 吕晨俞登艳张健房鹏展
Owner FOCUS 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