Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for image automatic text annotation based on generative adversarial networks

An automatic text and image technology, applied in special data processing applications, instruments, electrical digital data processing, etc., to achieve the effect of convenient retrieval

Inactive Publication Date: 2017-11-07
SUZHOU UNIV OF SCI & TECH
View PDF1 Cites 48 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Looking at the existing generative confrontation network methods, most of them are aimed at a single data domain

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
  • Method for image automatic text annotation based on generative adversarial networks
  • Method for image automatic text annotation based on generative adversarial networks
  • Method for image automatic text annotation based on generative adversarial networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0040] This embodiment introduces a generative confrontation network on the basis of the traditional CNN-RNN method, and proposes an algorithm for automatic sentence labeling of images based on the generative confrontation network, which overcomes the problems in the traditional automatic sentence labeling of images.

[0041] Among them, refer to figure 1 As shown, the traditional GAN ​​structure consists of a generator G and a discriminator D. Among them, the gen...

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 method for image automatic text annotation based on generative adversarial networks, which comprises the steps of generating false statements by a generator, rebuilding a discriminator at the same time, and inputting the generated statements and real statements into the discriminator to train until the discriminator cannot discriminate the real statements and the generated statements. The method disclosed by the invention changes a problem that sentences are rigid and inflexible in CNN-RNN image automatic statement annotation, and enables the generated sentences to be more accurate, more natural and more diversified. The generated statements can face more complex scenes in reality and more conform to language expression means annotation images of the human, thereby having more extensive applications in practice.

Description

technical field [0001] The invention relates to the field of image sentence tagging, in particular to an image automatic text tagging method based on a generative confrontation network. Background technique [0002] In recent years, the problem of automatic sentence annotation on images has been extensively studied. Since not only the target recognition problem of the image itself is involved, but also the natural language processing problem is involved, the current main related methods can be summarized into the following three types: [0003] Semantic template filling method: This method obtains the specific target in the image, puts the category text representing the target into a fixed natural language generation template, and automatically generates sentences. Some methods use the results of object recognition to compose a simple sentence with three fixed semantic elements. Some methods also put the identified relationship between targets into the same template to for...

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): G06K9/62G06F17/30
CPCG06F16/583G06F18/214
Inventor 胡伏原吕凡沈军宇孙钰李林燕李宏
Owner SUZHOU UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com