CN114494921A - Goods shelf commodity identification method and system - Google Patents
Goods shelf commodity identification method and system Download PDFInfo
- Publication number
- CN114494921A CN114494921A CN202210088489.7A CN202210088489A CN114494921A CN 114494921 A CN114494921 A CN 114494921A CN 202210088489 A CN202210088489 A CN 202210088489A CN 114494921 A CN114494921 A CN 114494921A
- Authority
- CN
- China
- Prior art keywords
- commodity
- price
- price tag
- target
- similarity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for identifying goods on a shelf, wherein the method comprises the following steps: acquiring a shelf image, wherein the content of the shelf image comprises a plurality of commodities and a plurality of price tags on a shelf; acquiring a plurality of price tags closest to the target commodity according to the shelf image; and determining the price tag corresponding to the target commodity from the plurality of price tags according to the distance between each price tag in the plurality of price tags and the target commodity and the characteristic similarity between the commodity corresponding to each price tag and the target commodity. According to the comprehensive judgment of the distance and the similarity of the characteristic values, the method can reduce the characteristic retrieval range of the commodities, improve the identification precision of the commodities, reduce the time requirement on a commodity characteristic retrieval algorithm, and improve the difficult situation that the similarity of adjacent commodities is high and difficult to identify.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a system for identifying shelf commodities.
Background
With the development of artificial intelligence technology, intelligent retail is also rapidly developing. In order to realize a shopping mode with higher efficiency, better service and better experience, technologies such as the Internet, the Internet of things, big data, artificial intelligence and the like are comprehensively applied to intelligent retail, the existing business stores and convenience stores are enabled or upgraded, the business stores and the convenience stores are managed in a digital and intelligent mode, meanwhile, the relation among commodities, users and payment is optimized, the big data is formed, and the digitization is further promoted.
The digital shelf is an important link in intelligent new retail business, and the intelligent management requirements of the digital shelf are met by the requirements of arrangement intelligent detection, intelligent commodity identification, intelligent shortage alarm, display supervision optimization and the like. The commodity identification is an important link in intelligent shelf management, is a precondition for application in aspects of shelf arrangement analysis, automatic settlement and the like, and is a core technical point for solving offline digitization, so that the commodity identification precision is of great importance. However, there is a great difficulty in realizing high-precision commodity identification, mainly due to the variety of commodities, multi-view difference and environmental light influence, and a massive data support and precise retrieval technology are required, which is a very great obstacle to the real commercial landing of the technology, and cannot enable intelligent retail to form a large-scale effect.
In order to realize high-precision commodity identification, the most effective technical means at present is to expand a commodity feature library, take mass data as support, and acquire and store image data of a certain commodity for a long time. Namely, a large amount of commodity data are manually collected, a large number of commodity types and commodity multi-angle characteristic information are covered as much as possible, and even respective long-tail data are accumulated in the long term, so that a complete commodity characteristic database is finally built. On the basis of the characteristic database, pure commodity identification supported by massive commodity data is realized by utilizing an image retrieval algorithm (similar to searching a graph by a graph) mature in the prior art.
However, the commodities in the world are various and have huge complexity, and the acquisition and accumulation of the multi-angle characteristic information of a single commodity is time-consuming, needs a lot of manpower for investment, and has huge cost. In addition, the pure visual commodity identification method has very poor robustness when the conditions such as reflection, local shielding, shadow, chromatic aberration, high inter-class similarity and the like occur, so that the hardware cost is improved, the algorithm efficiency is reduced, the algorithm identification precision is not high, the generalization capability is difficult to improve, and the scale effect is difficult to form.
Disclosure of Invention
The invention provides a method and a system for identifying goods on a shelf, which aim to overcome the defects of low identification precision and low efficiency in the prior art.
The invention provides a goods shelf identification method, which comprises the following steps:
acquiring a shelf image, wherein the content of the shelf image comprises a plurality of commodities and a plurality of price tags on a shelf;
acquiring a plurality of price tags closest to the target commodity according to the shelf image;
and determining the price tag corresponding to the target commodity from the plurality of price tags according to the distance between each price tag in the plurality of price tags and the target commodity and the characteristic similarity between the commodity corresponding to each price tag and the target commodity.
The invention also provides a system for identifying goods on a shelf, which comprises:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a shelf image, and the content of the shelf image comprises a plurality of commodities and a plurality of price tags on a shelf;
the acquisition module is used for acquiring a plurality of price tags which are closest to the target commodity according to the shelf image;
and the determining module is used for determining the price tag corresponding to the target commodity from the plurality of price tags according to the distance between each price tag in the plurality of price tags and the target commodity and the characteristic similarity between the commodity corresponding to each price tag and the target commodity.
According to the embodiment of the invention, the commodity feature retrieval range can be reduced, the commodity identification precision is improved, the time requirement on a commodity feature retrieval algorithm is reduced, and the difficult situation that the similarity of adjacent commodities is high and difficult to identify is improved according to the comprehensive judgment of the distance and the similarity of the feature values.
Drawings
Fig. 1 is a flowchart of a method for identifying a shelf product according to an embodiment of the present invention;
FIG. 2 is a schematic view of an identification scenario of a shelf product according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an identification system for shelf products according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a method for identifying shelf commodities, which comprises the following steps as shown in figure 1:
Wherein the content of the shelf image comprises a plurality of goods and a plurality of price tags on the shelf.
And 102, acquiring a plurality of price tags closest to the target commodity according to the shelf image.
In this embodiment, after the shelf image is collected, each price tag and each commodity on the shelf can be detected and identified according to the shelf image; and (4) digging out each commodity small picture from the shelf image, and extracting the characteristics of each commodity small picture.
Specifically, the matching score of each price tag may be calculated according to the distance between each price tag of the plurality of price tags and the target product and the feature similarity between the product corresponding to each price tag and the target product; and determining the price tag with the highest matching score as the price tag corresponding to the target commodity.
In this embodiment, the matching score of each price tag may be calculated by using the following formula:
Score＝a*(k-dis)+b*similarity
wherein, Score is a matching Score, dis is a distance between the target commodity and the price tag, similarity is a similarity between a characteristic value of the commodity corresponding to the price tag and a characteristic value of the target commodity, and a, b and k are weight coefficients used for adjusting the weight of the distance and the similarity influenced in Score;
it should be noted that the characteristic value of the commodity corresponding to each price tag specifically includes: and the commodity characteristic value with the maximum similarity to the characteristic value of the target commodity in the commodity characteristic value set corresponding to the code bound with the price tag. The commodity feature value set corresponding to the price label binding code may include a plurality of commodity feature values, and the price label binding code may be an ean (European article number) code.
In addition, after a plurality of price tags closest to the target commodity are obtained according to the shelf image, whether commodity characteristic values corresponding to codes bound with the price tags are recorded in a commodity characteristic database or not can be judged; if the commodity characteristic database does not record the commodity characteristic values corresponding to the codes bound with the price tags, determining the price tag corresponding to the target commodity from the price tags according to the distance between each price tag in the price tags and the target commodity; and if the commodity characteristic value corresponding to the code bound with the plurality of price tags is recorded in the commodity characteristic database, determining the price tag corresponding to the target commodity from the plurality of price tags according to the distance between each price tag in the plurality of price tags and the target commodity and the characteristic similarity between the commodity corresponding to each price tag and the target commodity.
According to the embodiment of the invention, the commodity feature retrieval range can be reduced, the commodity identification precision is improved, the time requirement on a commodity feature retrieval algorithm is reduced, and the difficult situation that the similarity of adjacent commodities is high and difficult to identify is improved according to the comprehensive judgment of the distance and the similarity of the feature values.
The embodiment of the invention can be applied to scenes comprising image acquisition equipment, a cloud server and edge end equipment or independent server equipment, wherein the image acquisition equipment can be a camera which can be fixed on a goods shelf or installed in a suspended ceiling. The edge terminal equipment or the independent server equipment can be used for deploying price tag detection, price tag identification, commodity detection and commodity feature extraction algorithms, and the cloud server can be used for deploying identification matching algorithms.
Based on the above scenario, the embodiment of the present invention provides a specific implementation process of a shelf commodity identification method, including the following steps: initializing a feature library of the whole category of commodities; a camera collects shelf images; calling a price tag detection and identification algorithm to detect and identify each price tag on the shelf; calling a commodity detection algorithm to detect each commodity on the goods shelf and extracting a small picture of each commodity; calling a feature extraction algorithm to extract the features of each commodity small graph; entering a fusion commodity identification flow, and circularly identifying each commodity; each commodity finds a plurality of price tags which are closest to the commodity, and the distance dis between each commodity and each price tag is calculated; checking whether characteristic values of EAN codes bound with a plurality of closest price tags are recorded in an initialized commodity characteristic library or not, and matching according to the distance between the commodity and the price tags only if the characteristic values of the EAN codes do not exist; and if the characteristic value of the EAN code exists, fusing the distance and the characteristic similarity for matching judgment.
The specific formula for calculating the matching score is as follows:
Score＝a*(k-dis)+b*similarity
wherein, a, b and k are weight coefficients used for adjusting the weight of the influence of the distance and the similarity in the score; dis is the distance between the commodity and the price tag, and similarity is the value with the maximum similarity in the commodity characteristic value set corresponding to the EAN code bound with the price tag and the characteristic value of the target commodity.
As shown in fig. 2, after calculating the scores between the target product and the latest several price tags, the price tag corresponding to the largest score can be determined as the final result of product identification, i.e., the EAN code and the product name of the target product are bound to the matching price tag.
According to the embodiment of the invention, the price tag position information, the price tag EAN information, the commodity position information and the commodity characteristic information on the goods shelf are fused, the matching score is comprehensively calculated, the actual matching identification of the commodity is carried out according to the maximum value of the score, so that the pure commodity identification is abandoned, the identification calculation method with the fusion of the price tag position and the characteristic similarity is completed, the difficulties of high similarity, light reflection, shadow, color difference and the like which cannot be dealt with by the pure commodity identification method can be eliminated, and the commodity identification precision on the goods shelf is greatly improved; according to comprehensive judgment of the distance and the similarity of the characteristic values, the retrieval range in the retrieval technology is reduced to the retrieval target of two to three EAN codes, the time requirement of a commodity characteristic retrieval algorithm is reduced, high-precision commodity identification on a goods shelf or similar scenes can be realized under the condition of a small amount of commodity characteristic data or even no characteristic data, the accumulation investment of the characteristic data is reduced, the complexity of the algorithm is also reduced, the algorithm can realize multi-scene popularization and deployment, and the practical commercial value is very high; when the visual features cannot be accurately judged, the matching identification can be performed by matching nearby or increasing the weight according to the information of the nearest price tag, so that the robustness of the algorithm is improved.
As shown in fig. 3, a schematic structural diagram of an identification system for shelf goods according to an embodiment of the present invention includes:
an acquisition module 310 is configured to acquire a shelf image, where the content of the shelf image includes a plurality of items and a plurality of price tags on a shelf.
The obtaining module 320 is configured to obtain, according to the shelf image, a plurality of price tags closest to the target product.
A determining module 330, configured to determine a price tag corresponding to the target product from the multiple price tags according to a distance between each of the multiple price tags and the target product and a feature similarity between a product corresponding to each price tag and the target product.
Wherein, the determining module 330 includes:
the calculation sub-module is used for calculating the matching score of each price tag according to the distance between each price tag in the price tags and the target commodity and the characteristic similarity between the commodity corresponding to each price tag and the target commodity;
and the determining submodule is used for determining the price tag with the highest matching score as the price tag corresponding to the target commodity.
Specifically, the calculating sub-module is specifically configured to calculate the matching score of each price tag by using the following formula:
Score＝a*(k-dis)+b*similarity
wherein, Score is a matching Score, dis is a distance between the target commodity and the price tag, similarity is a similarity between a characteristic value of the commodity corresponding to the price tag and a characteristic value of the target commodity, and a, b and k are weight coefficients used for adjusting the weight of the distance and the similarity influenced in Score;
the characteristic value of the commodity corresponding to each price tag specifically comprises the following steps: and the commodity characteristic value with the maximum similarity to the characteristic value of the target commodity in the commodity characteristic value set corresponding to the code bound with the price tag.
In addition, the system described above further includes:
the identification module is used for detecting and identifying each price tag and each commodity on the goods shelf according to the goods shelf image;
and the extraction module is used for picking out each commodity small image from the shelf image and extracting the characteristics of each commodity small image.
The judging module is used for judging whether commodity characteristic values corresponding to the codes bound with the price tags are recorded in the commodity characteristic database;
correspondingly, the determining module 330 is specifically configured to determine, if no commodity feature value corresponding to the code bound to the multiple price tags is recorded in the commodity feature database, a price tag corresponding to the target commodity from the multiple price tags according to a distance between each of the multiple price tags and the target commodity; if the commodity characteristic value corresponding to the code bound with the multiple price tags is recorded in the commodity characteristic database, the price tag corresponding to the target commodity is determined from the multiple price tags according to the distance between each price tag in the multiple price tags and the target commodity and the characteristic similarity between the commodity corresponding to each price tag and the target commodity.
According to the embodiment of the invention, the commodity feature retrieval range can be reduced, the commodity identification precision is improved, the time requirement on a commodity feature retrieval algorithm is reduced, and the difficult situation that the similarity of adjacent commodities is high and difficult to identify is improved according to the comprehensive judgment of the distance and the similarity of the feature values.
The steps of a method described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method for identifying a shelf product, comprising the steps of:
acquiring a shelf image, wherein the content of the shelf image comprises a plurality of commodities and a plurality of price tags on a shelf;
acquiring a plurality of price tags closest to the target commodity according to the shelf image;
and determining the price tag corresponding to the target commodity from the plurality of price tags according to the distance between each price tag in the plurality of price tags and the target commodity and the characteristic similarity between the commodity corresponding to each price tag and the target commodity.
2. The method as claimed in claim 1, wherein the determining the price tag corresponding to the target product from the plurality of price tags according to the distance between each price tag of the plurality of price tags and the target product and the feature similarity between the product corresponding to each price tag and the target product specifically comprises:
calculating the matching score of each price tag according to the distance between each price tag in the price tags and the target commodity and the characteristic similarity between the commodity corresponding to each price tag and the target commodity;
and determining the price tag with the highest matching score as the price tag corresponding to the target commodity.
3. The method as claimed in claim 2, wherein the calculating the matching score of each price tag according to the distance between each price tag of the plurality of price tags and the target product and the feature similarity between the product corresponding to each price tag and the target product specifically comprises:
the matching score for each price tag is calculated using the following formula:
Score＝a*(k-dis)+b*similarity
wherein, Score is a matching Score, dis is a distance between the target commodity and the price tag, similarity is a similarity between a characteristic value of the commodity corresponding to the price tag and a characteristic value of the target commodity, and a, b and k are weight coefficients used for adjusting the weight of the distance and the similarity influenced in Score;
the characteristic value of the commodity corresponding to each price tag specifically comprises the following steps: and the commodity characteristic value with the maximum similarity to the characteristic value of the target commodity in the commodity characteristic value set corresponding to the code bound with the price tag.
4. The method of claim 1, wherein after the capturing of the shelf image, further comprising:
detecting and identifying each price tag and each commodity on the goods shelf according to the goods shelf image;
and (4) digging out each commodity small picture from the shelf image, and extracting the characteristics of each commodity small picture.
5. The method of claim 1, wherein after obtaining a plurality of price tags closest to the target product based on the shelf image, further comprising:
judging whether commodity characteristic values corresponding to the codes bound with the price tags are recorded in a commodity characteristic database;
if the commodity characteristic database does not record the commodity characteristic values corresponding to the codes bound with the price tags, determining the price tag corresponding to the target commodity from the price tags according to the distance between each price tag in the price tags and the target commodity;
the determining, according to the distance between each price tag of the plurality of price tags and the target product and the feature similarity between the product corresponding to each price tag and the target product, the price tag corresponding to the target product from the plurality of price tags specifically includes:
and if the commodity characteristic value corresponding to the code bound with the plurality of price tags is recorded in the commodity characteristic database, determining the price tag corresponding to the target commodity from the plurality of price tags according to the distance between each price tag in the plurality of price tags and the target commodity and the characteristic similarity between the commodity corresponding to each price tag and the target commodity.
6. A system for identifying a shelf item, comprising:
the system comprises an acquisition module, a storage rack display module and a display module, wherein the acquisition module is used for acquiring a storage rack image, and the content of the storage rack image comprises a plurality of commodities and a plurality of price tags on a storage rack;
the acquisition module is used for acquiring a plurality of price tags which are closest to the target commodity according to the shelf image;
and the determining module is used for determining the price tag corresponding to the target commodity from the plurality of price tags according to the distance between each price tag in the plurality of price tags and the target commodity and the characteristic similarity between the commodity corresponding to each price tag and the target commodity.
7. The system of claim 6, wherein the determination module comprises:
the calculation sub-module is used for calculating the matching score of each price tag according to the distance between each price tag in the price tags and the target commodity and the characteristic similarity between the commodity corresponding to each price tag and the target commodity;
and the determining submodule is used for determining the price tag with the highest matching score as the price tag corresponding to the target commodity.
8. The system of claim 7,
the calculating submodule is specifically configured to calculate the matching score of each price tag by using the following formula:
Score＝a*(k-dis)+b*similarity
wherein, Score is a matching Score, dis is a distance between the target commodity and the price tag, similarity is a similarity between a characteristic value of the commodity corresponding to the price tag and a characteristic value of the target commodity, and a, b and k are weight coefficients used for adjusting the weight of the distance and the similarity influenced in Score;
the characteristic value of the commodity corresponding to each price tag specifically comprises the following steps: and the commodity characteristic value with the maximum similarity to the characteristic value of the target commodity in the commodity characteristic value set corresponding to the code bound with the price tag.
9. The system of claim 6, further comprising:
the identification module is used for detecting and identifying each price tag and each commodity on the goods shelf according to the goods shelf image;
and the extraction module is used for picking out each commodity small image from the shelf image and extracting the characteristics of each commodity small image.
10. The system of claim 6, further comprising:
the judging module is used for judging whether commodity characteristic values corresponding to the codes bound with the price tags are recorded in the commodity characteristic database;
the determining module is specifically configured to determine, if no commodity feature value corresponding to the code bound to the multiple price tags is recorded in the commodity feature database, a price tag corresponding to the target commodity from the multiple price tags according to a distance between each of the multiple price tags and the target commodity; and if the commodity characteristic value corresponding to the code bound with the plurality of price tags is recorded in the commodity characteristic database, determining the price tag corresponding to the target commodity from the plurality of price tags according to the distance between each price tag in the plurality of price tags and the target commodity and the characteristic similarity between the commodity corresponding to each price tag and the target commodity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210088489.7A CN114494921A (en) | 2022-01-25 | 2022-01-25 | Goods shelf commodity identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210088489.7A CN114494921A (en) | 2022-01-25 | 2022-01-25 | Goods shelf commodity identification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114494921A true CN114494921A (en) | 2022-05-13 |
Family
ID=81474924
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210088489.7A Pending CN114494921A (en) | 2022-01-25 | 2022-01-25 | Goods shelf commodity identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114494921A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116828595A (en) * | 2023-08-24 | 2023-09-29 | 汉朔科技股份有限公司 | Positioning method of electronic price tag, computer equipment and storage medium |
-
2022
- 2022-01-25 CN CN202210088489.7A patent/CN114494921A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116828595A (en) * | 2023-08-24 | 2023-09-29 | 汉朔科技股份有限公司 | Positioning method of electronic price tag, computer equipment and storage medium |
| CN116828595B (en) * | 2023-08-24 | 2024-01-02 | 汉朔科技股份有限公司 | Positioning method of electronic price tag, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111415461B (en) | Article identification method and system and electronic equipment | |
| CN108491799B (en) | Intelligent sales counter commodity management method and system based on image recognition | |
| CN101268478B (en) | Method and apparatus for detecting suspicious activity using video analysis | |
| US8855361B2 (en) | Scene activity analysis using statistical and semantic features learnt from object trajectory data | |
| US20150262116A1 (en) | Machine vision technology for shelf inventory management | |
| CN102063616A (en) | Automatic identification system and method for commodities based on image feature matching | |
| CN102982332A (en) | Retail terminal goods shelf image intelligent analyzing system based on cloud processing method | |
| CN111680654B (en) | Personnel information acquisition method, device and equipment based on article picking and placing event | |
| CN114494921A (en) | Goods shelf commodity identification method and system | |
| US11748787B2 (en) | Analysis method and system for the item on the supermarket shelf | |
| CN115797910A (en) | Long-tail target identification method, computer-readable storage medium and vehicle | |
| CN115063084A (en) | Inventory checking method and system for cigarette retail merchants | |
| CN110705620A (en) | Display image detection method and device based on copying recognition and storage medium | |
| CN112329521A (en) | Multi-target tracking video shop-patrol method based on deep learning | |
| Steiger et al. | Automatic detection of transmission towers | |
| CN113361405B (en) | Asian image recognition method and system based on yolo v3 | |
| CN110287203B (en) | Updating method and updating device for vending machine and vending machine | |
| CN116109992A (en) | Goods shelf commodity identification method and system | |
| CN111738184B (en) | Commodity picking and placing identification method, device, system and equipment | |
| CN114358870A (en) | Chain store and store passenger flow volume acquisition and analysis system | |
| CN114445725A (en) | Method and device for detecting fresh goods | |
| CN113160414A (en) | Automatic identification method and device for remaining amount of goods, electronic equipment and computer readable medium | |
| Morán et al. | Towards a Robust Solution for the Supermarket Shelf Audit Problem. | |
| KR102533239B1 (en) | Image library system and counterfeit detection method for artificial intelligence-based counterfeit product detection | |
| CN116563622A (en) | Commodity identification method, device, equipment and readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |