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

Commodity purity detection method and display cabinet

A detection method and a technology of purity, which is applied in the field of commodity purity detection based on image processing and display cabinets, can solve the problem of low accuracy of weight judgment, improve detection accuracy, realize unmanned management, and reduce the amount of calculation Effect

Active Publication Date: 2018-09-28
QINGDAO HAIER SMART TECH R & D CO LTD +1
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the technical problem that the purity detection of existing commodity display cabinets is based on low weight judgment accuracy, the present invention proposes a commodity purity detection method, which can solve the above problems

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 purity detection method and display cabinet
  • Commodity purity detection method and display cabinet
  • Commodity purity detection method and display cabinet

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] Embodiment 1, this embodiment proposes a kind of commodity purity detection method, such as figure 1 , figure 2 shown, including the following steps:

[0046] Steps to train the product detector offline include:

[0047] Collect images of standard commodities, mark the location areas of standard commodities in the image, extract the HOG features of each location area, and train the AdaBoost commodity detector;

[0048] Under normal circumstances, the products displayed have a specific shape. For example, beverages are usually bottled or canned. This kind of product has obvious outline features in the image. This step manually collects a large number of bottle-shaped objects offline. There are no less than 20 types of objects, and each picture contains only one bottle-shaped object, and the area of ​​the bottle-shaped object accounts for more than 90% of the entire picture area. By extracting the HOG feature of the picture, and then inputting it into the AdaBoost cas...

Embodiment 2

[0086] This embodiment proposes a commodity display cabinet, such as image 3 Shown, comprise cabinet body 11, cabinet door 12, cabinet body 11 is provided with clapboard 13 and divides the cabinet body into several storage spaces, and the top plate of each storage space is respectively provided with image acquisition device 14, uses To collect the image located in the space below it, the image acquisition device 14 is connected to the main control board (not shown in the figure), and the main control board sends the image to the server through the wireless network to detect the purity of the product. According to the first embodiment The commodity purity detection method described in the test is used for detection, which will not be repeated here. The image acquisition device 14 can be realized by using a wide-angle lens, and of course it can also be realized by using other cameras with image acquisition functions.

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 a commodity purity detection method, which comprises the following steps of training a commodity detector offline and detecting and identifying a target commodity. The step ofdetecting and identifying the target commodity comprises the following steps that: (1) collecting the image of a target commodity in a display cabinet, wherein the image is an original image; (2) extracting the edge of the original image to obtain an edge map; (3) carrying out edge detection on the edge map to obtain n candidate areas; (4) adopting a commodity detector to independently carry out refined detection on each candidate area to obtain m selected areas; (5) obtaining a corresponding subimage of the selected area in the original image, and regulating the sizes of all subimages to be consistent to obtain standard subimages; and (6) inputting the standard subimages into a convolutional neural network, and outputting a brand to which the commodity in the standard subimages belongs. By use of the commodity purity detection method, a smart algorithm and an image processing technology are used for realizing the unmanned management of refrigerator purity monitoring, detection accuracy is improved, and meanwhile, manpower cost is saved.

Description

technical field [0001] The invention relates to the technical field of commodity purity detection, in particular to a commodity purity detection method based on image processing and a display cabinet. Background technique [0002] Existing shopping malls and commodity display cabinets for displaying commodities in supermarkets are often placed with commodities of multiple brands. When users choose, they often hesitate and do not know which brand of commodities to buy. In fact, this kind of product display cabinet is not allowed to display products of multiple brands, because this kind of product display cabinet is given to shopping malls and supermarkets by brand owners (for example, Coca-Cola Company) for free, and it should only be able to display Put the brand's products. However, due to the large number of shopping malls and supermarkets and the cost of personnel, it is difficult for brand owners to achieve real-time on-site supervision to ensure the purity of the produ...

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): G06K9/46G06K9/62G06N3/04G06N3/08A47F11/00
CPCA47F11/00G06N3/08G06V10/44G06N3/045G06F18/24
Inventor 刘兵高洪波俞国新刘彦甲李玉强
Owner QINGDAO HAIER SMART TECH R & D CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com