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

Image recognition method and system

An image recognition and image technology, applied in the computer field, can solve the problems of not making full use of complementary information and related information, and unable to guarantee the similarity of sample nodes, so as to achieve the effect of ensuring similarity and maintaining complementary and related information

Pending Publication Date: 2020-03-20
BEIJING JINGDONG SHANGKE INFORMATION TECH CO LTD +1
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method of constructing a hypergraph ignores the differences of different modal features, cannot guarantee the similarity of sample nodes in the same hyperedge, and does not make full use of the complementary information and related information between different modal features

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 recognition method and system
  • Image recognition method and system
  • Image recognition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The present invention is described below based on examples, but the present invention is not limited to these examples. In the following detailed description of the invention, some specific details are set forth in detail. The present invention can be fully understood by those skilled in the art without the description of these detailed parts. In order to avoid obscuring the essence of the present invention, well-known methods, procedures, and flow charts are not described in detail. Additionally, the drawings are not necessarily drawn to scale.

[0030] In image recognition technology, a hypergraph set by vertices Hyperedge set ε={e 1 ,e 2 ,...,e d} and hyperedge weight vector w. The weight of the corresponding hyperedge for e ∈ ε is denoted as w(e), whose value is set to 1 by default. hypergraph can be sized from The indicator matrix H represents:

[0031]

[0032] for nodes Based on the indicator matrix H, the node The degree of is defined as:...

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 embodiment of the invention provides an image recognition method and a system, and relates to the technical field of computers. The method comprises the following steps: extracting image featuresof multiple modes from an image training sample; constructing a plurality of hypergraphs according to the image features of the plurality of modes; performing joint learning on the plurality of hypergraphs; and carrying out image classification according to the local optimal solution obtained by joint learning. According to the image recognition method provided by the embodiment of the invention,in the process of constructing the hypergraphs, joint learning is carried out on the plurality of hypergraphs; and image classification is performed according to the local optimal solution obtained byjoint learning. The similarity between samples is measured without using a long feature vector formed by splicing all different modal feature vectors of one sample, and the similarity of sample nodesin the same hyperedge is ensured, so that complementary information and related information between image features of different modals are maintained to the maximum extent.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to an image recognition method and system. Background technique [0002] In real life, people's multiple senses are composed of vision, hearing, touch and smell. There are many ways that people perceive the world, such as the objects they see, the sounds they hear, the textures they feel, and the tastes they smell. The invariant features that describe things are called modal features. In computer vision and multimedia analysis, multiple modal features are often used to characterize the same object from different angles. For example, to characterize a natural scene image well, it is common to extract a set of visual features representing its color, texture, or shape, etc. How to fully mine the complementary information and related information of these different modal features to improve the performance of image recognition has become a hot and difficult issue in the field of com...

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): G06K9/46G06K9/62G06F17/14
CPCG06F17/14G06V10/50G06V10/464G06V10/56G06F18/214
Inventor 祖辰
Owner BEIJING JINGDONG SHANGKE INFORMATION 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