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

Image classification method, device and storage medium

An image and classification model technology, applied in the field of artificial intelligence, can solve problems such as poor model scalability

Active Publication Date: 2021-09-14
上海小零网络科技有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present disclosure provide a method, device, and storage medium for image classification, to at least solve the problem that the trained neural network model in the prior art can only identify categories during the training process, and when a new category appears Sometimes it is necessary to re-label the data for model training, so the technical problem of poor model scalability

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0021] According to this embodiment, a method for image classification is 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 the steps shown in the flow chart Although a logical order is shown, in some cases the steps shown or described may be performed in an order different from that shown or described herein.

[0022] The method embodiments provided in this embodiment can be executed in a server or similar computing devices. figure 1 A hardware structural block diagram of a computing device for implementing a method for image classification is shown. like figure 1 As shown, the computing device may include one or more processors (processors may include but not limited to processing devices such as microprocessors MCUs or programmable logic devices FPGAs), memory for storing data, and memory for communication functions transmissi...

Embodiment 2

[0067] Figure 5 An image classification apparatus 500 according to this embodiment is shown, and the apparatus 500 corresponds to the method according to the first aspect of Embodiment 1. refer to Figure 5 As shown, the device 500 includes: a feature extraction module 510, which is used to obtain the image feature vector of the image to be classified; a calculation module 520, which is used to calculate the image feature vector using a pre-trained image classification model, and determine that the image to be classified corresponds to The probability value of each classification category, where the classification category includes known classification categories and unknown classification categories. The image classification model is trained based on the classification category and category attribute set. The category attribute set contains multiple categories that are associated with the classification category. attribute; and a category determining module 530, configured ...

Embodiment 3

[0079] Image 6 An image classification apparatus 600 according to this embodiment is shown, and the apparatus 600 corresponds to the method according to the first aspect of Embodiment 1. refer to Image 6 As shown, the device 600 includes: a processor 610; and a memory 620, connected to the processor 610, used to provide the processor 610 with instructions for processing the following processing steps: obtain the image feature vector of the image to be classified; use the pre-trained image The classification model calculates the image feature vector to determine the probability value of the image to be classified corresponding to each classification category, where the classification category includes known classification categories and unknown classification categories, and the image classification model is trained based on the classification category and category attribute set , the category attribute set contains a plurality of category attributes associated with the clas...

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 application discloses an image classification method, device and storage medium. Wherein, the method includes: obtaining the image feature vector of the image to be classified; using the pre-trained image classification model to calculate the image feature vector, and determining the probability value corresponding to each classification category of the image to be classified, wherein the classification category includes known classification Category and unknown classification category, the image classification model is trained based on the classification category and category attribute set, the category attribute set contains multiple category attributes associated with the classification category; and the image to be classified belongs to the unknown classification category according to the probability value In the case of , the image to be classified is clustered, and the category attribute corresponding to the unknown classification category is determined from the category attribute set.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, in particular to an image classification method, device and storage medium. Background technique [0002] Image classification is to distinguish different types of images according to the semantic information of images. It is an important basic problem in computer vision and the basis of other high-level visual tasks such as image detection, image segmentation, object tracking, and behavior analysis. In the existing technology, neural networks can be used to classify images. However, traditional deep neural network classification systems require a large amount of labeled data for training. The trained network can only identify images related to labeled training data in practical applications. , when a new category that needs to be classified appears, it cannot be identified and classified. Only by re-labeling the data and then re-training the model can the emerging cate...

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): G06K9/62G06K9/46G06N3/04G06N3/08
CPCG06N3/08G06V10/40G06V10/56G06N3/048G06N3/045G06F18/24
Inventor 胡军张玥
Owner 上海小零网络科技有限公司
Features
  • Generate Ideas
  • 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