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

A product appearance anti-counterfeiting method based on CNN image recognition

An image recognition and product technology, applied in the field of anti-counterfeiting, can solve the problems of unsalable products, consumers' inability to grasp, and purchase of counterfeit products, etc., and achieve the effect of reducing the possibility of buying fake products, high light and dark detail ability, and high image pixels

Active Publication Date: 2021-05-25
四川中新华搜信息技术有限公司
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] 1. Consumers have no channels to obtain these identification means
[0008] 2. There are many types of commodities, and each commodity has different identification methods. For 1,000 kinds of commodities, 1,000 identification methods must be mastered, and consumers cannot master so many skills.
[0009] 3. Products are constantly updated and iterated, identification methods are updated, and consumer information is not updated in time
[0010] There are also some special products that are in different states before leaving the factory and after leaving the factory. For example, jujube honey is in a viscous state before leaving the factory. After leaving the factory, it may become crystallized due to the temperature relationship, and the appearance of the product will change. Even if the appearance identification is consistent, Due to the lack of awareness of jujube nectar, consumers are unwilling to buy such products, resulting in unsalable crystallized jujube nectar. In addition, the smell of genuine jujube nectar is quite special. Unscrupulous merchants can take advantage of the loopholes and make them more popular among consumers. Counterfeit products with a pleasant fragrance, because consumers lack awareness of such special products, they are prone to unsalable products or the possibility of buying counterfeit products

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
  • A product appearance anti-counterfeiting method based on CNN image recognition
  • A product appearance anti-counterfeiting method based on CNN image recognition
  • A product appearance anti-counterfeiting method based on CNN image recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] see Figure 1-5 , a kind of product appearance anti-counterfeiting method based on the image recognition of CNN, comprises the following steps:

[0062] (1) Commodity information collection: The manufacturer conducts all-round video collection or photo collection of physical commodities, and places them in different environments to record several copies respectively, and mark them as authentic.

[0063] You can also find some counterfeit samples of this product in the market for video collection or photo collection, and mark them as: fake products, and selectively collect them according to the actual needs of the manufacturer. After the collection is completed, upload the videos and photos to the system;

[0064] see Figure 4 , in the step (1), a photographing mechanism is used to collect commodity image information. The photographing mechanism includes a photographing platform 1, a driving motor 3, a storage pallet 5 and a CCD camera 8. The photographing platform 1 p...

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 method for anti-counterfeiting of commodity appearance based on CNN image recognition, which belongs to the field of anti-counterfeiting technology. A method for anti-counterfeiting of commodity appearance based on CNN image recognition can realize the collection of commodity appearance in the form of photos or videos through a shooting mechanism. The information is stored in the system, the collected pictures or videos are selected, and the size of all pictures is adjusted to a uniform size through the picture processing algorithm, and the training is carried out based on the CNN model. After the training is completed, the model test is performed to improve the accuracy of the test pictures, and finally deployed To the cloud server, consumers can take photos of the goods and upload them to the cloud server for identification and comparison before purchasing the goods, which can significantly improve the recognition rate of the goods, and the ability to identify the authenticity of the goods can almost reach the human identification standard, providing consumers with a A powerful tool for quickly identifying genuine and fake products, greatly reducing the possibility of consumers buying fake products.

Description

technical field [0001] The present invention relates to the technical field of anti-counterfeiting, and more specifically, relates to a method for anti-counterfeiting of commodity appearance based on CNN image recognition. Background technique [0002] At present, the appearance anti-counterfeiting methods of commodities are mostly divided into two categories: 1, printing anti-counterfeiting; 2, image generation and recognition algorithm anti-counterfeiting. [0003] 1. The printing anti-counterfeiting method mainly uses special materials and monopoly printing technology to print commodity trademarks and special picture icons on the outer packaging of commodities. This kind of anti-counterfeiting method can basically prevent counterfeiters from imitating and copying, but the biggest problem lies in the computer system. Without effective identification ability, consumers themselves also lack the ability to identify such anti-counterfeiting printing technology, so this type of...

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): G06K9/62G06K9/00G06K9/20G06K17/00
Inventor 李银刘超
Owner 四川中新华搜信息技术有限公司
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