Supercharge Your Innovation With Domain-Expert AI Agents!

Image recognition method and device, and residual network model construction method

A network model and image recognition technology, applied in the field of image recognition, can solve problems such as poor model recognition effect, and achieve the effect of solving poor recognition effect and accurate and effective recognition results

Pending Publication Date: 2022-04-12
ALIBABA GRP HLDG LTD
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present application provides an image recognition method and device, and a method for constructing a residual network model, so as to at least solve the technical problem in the related art that the training model recognition effect is not good due to insufficient training data

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 device, and residual network model construction method
  • Image recognition method and device, and residual network model construction method
  • Image recognition method and device, and residual network model construction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] According to the embodiment of the present application, a method embodiment of an image recognition method is also provided. It should be noted that the steps shown in the flow chart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and , although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that shown or described herein.

[0027] The method embodiment provided in Embodiment 1 of the present application may be executed in a mobile terminal, a computer terminal, or a similar computing device. figure 1 A hardware structural block diagram of a computer terminal (or mobile device) for realizing the image recognition method is shown. Such as figure 1 As shown, the computer terminal 10 (or mobile device 10) may include one or more (shown by 102a, 102b, ..., 102n in the figure) processor 102 (the processor 102 may include bu...

Embodiment 2

[0063] According to an embodiment of the present application, a device for implementing the above image recognition method is also provided, such as Figure 4 As shown, the device includes:

[0064] An acquisition module 40, configured to acquire feature information of the image to be identified;

[0065] The analysis module 42 is configured to input feature information into the residual network model for analysis to obtain analysis results, wherein each residual block in the residual network model includes a plurality of branches, wherein the specified branch in the plurality of branches Include at least a selective convolution kernel;

[0066] Optionally, there are multiple specified branches, and the selective convolution kernels in the multiple specified branches are the same.

[0067] The determination module 44 is configured to determine the image type of the image to be recognized according to the analysis result.

[0068] Through the above modules, the salient featu...

Embodiment 3

[0078] The embodiment of the present application provides a method for constructing a residual network model, such as Figure 5 As shown, the method includes:

[0079] Step S502, for the residual block in the residual network model, replace the designated convolution kernel in the first branch of the residual block with a selective convolution kernel, wherein the first branch is the jump in the residual network model except The branch other than the connecting branch, the jumping branch is the branch directly connected to the input end and the output end of the residual block;

[0080] Step S504, setting the same second branch as the first branch with selective convolution kernel in the residual block to obtain the target residual block;

[0081] Step S506, determine and construct a residual network model based on the target residual block. Optionally, there are multiple target residual blocks, for example, 4, 5, 6... and so on.

[0082] In some embodiments, when the specif...

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 an image recognition method and device and a construction method of a residual network model. The method comprises the following steps: acquiring feature information of a to-be-recognized image; the feature information is input into a residual network model for analysis, an analysis result is obtained, each residual block in the residual network model comprises a plurality of branches, and a specified branch in the plurality of branches at least comprises a selective convolution kernel; and determining the image type of the to-be-identified image according to the analysis result. The technical problem that the training model recognition effect is poor due to insufficient training data in the prior art is solved.

Description

technical field [0001] The present application relates to the field of image recognition, in particular, to an image recognition method and device, and a method for constructing a residual network model. Background technique [0002] With the development of artificial intelligence technology, the application of neural network models is becoming more and more extensive. Since neural network models often require massive training data as the basis, however, in practical applications, subject to various restrictions, often It will face the problem of insufficient training data, so that it is impossible to train a sufficiently accurate and effective model. [0003] For the above problems, no effective solution has been proposed yet. Contents of the invention [0004] Embodiments of the present application provide an image recognition method and device, and a method for constructing a residual network model, so as to at least solve the technical problem in the related art that ...

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): G06V10/764G06V10/774G06V10/82G06K9/62G06N3/04G06N3/08
Inventor 孙鹏飞
Owner ALIBABA GRP HLDG LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com