Image classification method, device, terminal device, and readable storage medium

A classification method and image technology, applied in the field of image processing, can solve problems such as inaccurate image classification and unreasonable classification of images, and achieve the effects of optimizing recognition ability, strong usability and practicability, and improving performance

Inactive Publication Date: 2019-02-22
SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
View PDF7 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the embodiment of the present invention provides an image classification method, device, terminal equipment and readable storage medium to solve the problems in the prior art but for images of unknown categories outside the training set of known image categories Reasonable classification cannot be performed, and there is a problem of inaccurate image classification

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 classification method, device, terminal device, and readable storage medium
  • Image classification method, device, terminal device, and readable storage medium
  • Image classification method, device, terminal device, and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0162] See Figure 7 , Is a schematic diagram of an image classification device provided by an embodiment of the present invention. For ease of description, only parts related to the embodiment of the present invention are shown.

[0163] The image classification device includes:

[0164] The first model obtaining unit 71 is configured to train the deep convolutional neural network through known category images to obtain a network training model;

[0165] The second model acquisition unit 72 is configured to separately establish a probability distribution model for each type of sample in the known type image according to the network training model;

[0166] The correction unit 73 is configured to correct the activation value of the known category image according to the probability distribution model;

[0167] The activation value obtaining unit 74 is configured to obtain the activation value of the unknown category image according to the activation value of the known category image data...

Embodiment 3

[0177] Figure 8 It is a schematic diagram of a terminal device provided by an embodiment of the present invention. Such as Figure 8 As shown, the terminal device 8 of this embodiment includes a processor 80, a memory 81, and a computer program 82 that is stored in the memory 81 and can run on the processor 80. When the processor 80 executes the computer program 82, the steps in the foregoing embodiments of the graph classification method are implemented, for example figure 1 Steps 101 to 105 are shown. Alternatively, when the processor 80 executes the computer program 82, the functions of the modules / units in the foregoing device embodiments are implemented, for example Figure 7 The functions of modules 71 to 75 are shown.

[0178] Exemplarily, the computer program 82 may be divided into one or more modules / units, and the one or more modules / units are stored in the memory 81 and executed by the processor 80 to complete this invention. The one or more modules / units may be a s...

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 is applicable to the technical field of image processing, and provides an image classification method, a device, a terminal device and a readable storage medium. The method comprises thefollowing steps: training a depth convolution neural network through a known class image to obtain a network training model; establishing a probability distribution model for each class of samples inthe known class image according to the network training model; correcting an activation value of the known class image according to the probability distribution model; obtaining an activation value of an unknown class image according to the activation value of the known class image data. The images are classified according to an activation value of the known category image and an activation valueof the unknown category image. The invention can reasonably and accurately classify the images other than the training set category in the known category images in practical application.

Description

Technical field [0001] The present invention belongs to the technical field of image processing, and in particular relates to an image classification method, device, terminal equipment and readable storage medium. Background technique [0002] Image classification can extract, process and analyze the feature data of the image through the computer, identify different targets and objects, and classify the image according to different characteristics. [0003] At present, when performing image classification, based on deep neural network algorithms, a trained image classification model is used to classify known image data. The trained image classification model is based on the training image data in the same category space. And test image data; or based on the activation value of a certain type of correctly classified image sample to determine the unknown image category; however, it cannot be reasonable for the unknown image category outside the training set of the known image categor...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/214
Inventor 乔宇庄培钦王亚立
Owner SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
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