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

Image semantic recognition method, system, device and medium based on multiple models

A semantic recognition, multi-model technology, applied in character and pattern recognition, natural language data processing, instruments, etc., can solve problems such as uneven recognition results, lack of uniform standards for image semantic recognition algorithms, and affecting the accuracy of semantic recognition. achieve the effect of improving the accuracy

Active Publication Date: 2020-09-04
SHANGHAI CLOUDWALK HUILIN ARTIFICIAL INTELLIGENCE TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the shortcomings of the prior art described above, the purpose of the present invention is to provide a multi-model-based image semantic recognition method, system, device and medium, which is used to solve the lack of a unified standard for the existing image semantic recognition algorithm, which causes recognition problems for the same application scene. The results are uneven, which affects the accuracy of semantic recognition

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
  • Image semantic recognition method, system, device and medium based on multiple models
  • Image semantic recognition method, system, device and medium based on multiple models
  • Image semantic recognition method, system, device and medium based on multiple models

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] Embodiments of the present invention are described below through specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific implementation modes, and various modifications or changes can be made to the details in this specification based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, in the case of no conflict, the following embodiments and features in the embodiments can be combined with each other.

[0068] It should be noted that the diagrams provided in the following embodiments are only schematically illustrating the basic ideas of the present invention, and only the components related to the present invention are shown in the diagrams rather than the number, shape and shape of the compo...

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 present invention provides a method, system, device and medium for image semantic recognition based on multiple models. The method includes: acquiring an image, and using multiple image semantic recognition models to process the image respectively to obtain various recognition results related to semantic recognition; The recognition results are similarly paired, and the sequence in the recognition results is rearranged to arrange the most similar recognition results in the same order position; according to the similarity between the root nodes and the similarity between the child nodes in the various recognition results, calculate each kind of recognition results. The comprehensive confidence of each root node and each child node in the image semantic recognition model; according to the comprehensive confidence of the root node and child nodes, select an adaptive semantic description as the recognition result of the image. The present invention obtains multiple recognition results by using multiple image semantic recognition models, uses the comprehensive confidence of the root node and child nodes in the recognition results to select semantic description as the recognition result, and improves the accuracy of image semantic recognition.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a multi-model-based image semantic recognition method, system, device and medium. Background technique [0002] With the development of artificial intelligence technology, more and more image processing tasks can be done through artificial intelligence. As a means of artificial intelligence, neural network has been fully applied in the field of computer image recognition. For example, identifying different people in images, or automatically identifying different objects on the road in unmanned driving, these constitute the specific content of image semantic recognition, and convert them into natural voice descriptions to meet image search and other scenarios Applications. [0003] However, the open source software development kits and commercial application services involved in the existing image semantic recognition algorithms are all based on deep learning neur...

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 Patents(China)
IPC IPC(8): G06K9/62G06F40/253
CPCG06F18/22G06F18/241
Inventor 周曦姚志强吴媛吴大为
Owner SHANGHAI CLOUDWALK HUILIN ARTIFICIAL INTELLIGENCE TECH CO LTD
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