Commodity identification management method and device, server and readable storage medium

A commodity and category technology, applied in the field of commodity identification management methods, devices, servers and readable storage media, can solve the problems of low accuracy of commodity category and model identification

Active Publication Date: 2020-10-02
创新奇智(北京)科技有限公司
View PDF10 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] This application provides a product identification management method, device, server and readable

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
  • Commodity identification management method and device, server and readable storage medium
  • Commodity identification management method and device, server and readable storage medium
  • Commodity identification management method and device, server and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. It should be noted that terms such as "first" and "second" are only used for distinguishing descriptions, and should not be understood as indicating or implying relative importance.

[0052] The applicant found that, in the field of image recognition, in the process of refined identification and classification of products, if the products do not have obvious distinguishing features on the packaging, and the models and specifications of the products are different, the current image recognition processing methods usually cannot Refinedly identify the model and specification of the product. For example, for the same brand and the same series of canned milk powder, if there is only a difference in the weight of the milk powder, and the packaging pattern and color are the same, the existing image recogniti...

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 provides a commodity identification management method and device, a server and a readable storage medium. The method comprises the following steps: inputting an acquired first image intoa trained deep learning detection model to obtain a detection result of the first image, including commodity category and position information of a target commodity; inputting the first image and thedetection result into a trained fine classification model; performing feature extraction on the first image and the detection result through a feature extractor to obtain target semantic features; performing convolution processing on the target semantic features through a convolutional neural network; inputting the target semantic features after convolution processing into the classifier, obtaining the recognition result of the first image output by the classifier, wherein the recognition result comprises the commodity category and model information of the target commodity, the commodity category and model recognition accuracy and reliability can be improved, and the commodity recognition precision is improved.

Description

technical field [0001] The present invention relates to the technical field of computer image processing, in particular to a commodity identification management method, device, server and readable storage medium. Background technique [0002] With the development of artificial intelligence technology, in the process of using images to classify and identify products, it is currently possible to use the obvious differences in product packaging, such as the difference in shape and structure between products, the difference in packaging patterns, and the differences in pattern colors. Perform identification checks. If the product does not have obvious distinguishable features on the package, the current image recognition method cannot accurately identify the product category and model. Contents of the invention [0003] The present application provides a product identification management method, device, server and readable storage medium, which can improve the problem of low ...

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
IPC IPC(8): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/20G06V10/462G06N3/045G06F18/217G06F18/24
Inventor 秦永强敖川
Owner 创新奇智(北京)科技有限公司
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