Commodity classification method and device, electronic equipment and storage medium

A classification method and commodity technology, applied in the field of image processing, can solve the problem of inaccurate commodity identification and achieve the effect of improving accuracy

Pending Publication Date: 2020-09-01
创新奇智(西安)科技有限公司
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the embodiments of the present application is to provide a product classification method, device, electronic equipment and storage medium to solve the problem of inaccurate product identification using classification models in the prior art

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 classification method and device, electronic equipment and storage medium
  • Commodity classification method and device, electronic equipment and storage medium
  • Commodity classification method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] 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.

[0028] Prior to this application, the category recognition of goods on the shelf was done by classifying fisheye images with a pre-built and trained classification model. Because the shape of the goods in the fisheye image will be distorted, the distribution of goods in each aisle is not a linearly separable state. In addition, there are various types of goods placed on different aisles, so the existing classification model is not accurate. Product classification in fisheye images is not accurate enough.

[0029] In order to solve the above technical problems, the embodiment of the present application provides a product classification method, which uses the detection model to identify the product category in the fisheye image, and then corrects the category of some of the products to obtain the fina...

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 classification method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a to-be-corrected fisheye image, wherein theto-be-corrected fisheye image comprises at least one goods channel and a detection box corresponding to each commodity in each goods channel; dividing the commodity in the to-be-corrected fisheye image into commodity channels to obtain commodities corresponding to the commodity channels; obtaining category information of to-be-corrected commodities in the commodity channel; wherein the category information comprises confidence of at least one category corresponding to the to-be-corrected commodity output by the detection model; and correcting the category of the to-be-corrected commodity according to the confidence coefficient of the at least one category corresponding to the to-be-corrected commodity and the category of the commodity except the to-be-corrected commodity in the corresponding commodity channel. According to the embodiment of the invention, the commodity channel division is carried out on the commodity, the to-be-corrected commodity is obtained according to the confidence coefficient of the commodity category, and then the to-be-corrected image is corrected by utilizing the confidence coefficient of the category corresponding to the to-be-corrected commodity and other commodity categories in the commodity channel, so that the category of the commodity is accurately obtained.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular, to a commodity classification method, device, electronic equipment and storage medium. Background technique [0002] The fisheye image is an image collected by a fisheye lens. In order to maximize the photographic viewing angle of the lens, the diameter of the front lens of this photographic lens is very short and protrudes toward the front of the lens in a parabolic shape, which is quite similar to the eyes of a fish. , hence the name of the fisheye lens. [0003] Based on the advantages of wide photographic angle of view, fisheye lenses are widely used in shopping malls, supermarkets and other places. Taking a supermarket as an example, the products on a row of shelves are generally of the same type, and products of the same brand will be put together, and images of the products on the shelves can be collected through a fisheye lens. In order to facilitate th...

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): G06K9/32G06K9/62
CPCG06V10/242G06F18/241Y02T10/40
Inventor 柯政远
Owner 创新奇智(西安)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