CN114120105A - Method, device, equipment and medium for identifying counterfeiting of store commodity display image - Google Patents
Method, device, equipment and medium for identifying counterfeiting of store commodity display image Download PDFInfo
- Publication number
- CN114120105A CN114120105A CN202111337421.XA CN202111337421A CN114120105A CN 114120105 A CN114120105 A CN 114120105A CN 202111337421 A CN202111337421 A CN 202111337421A CN 114120105 A CN114120105 A CN 114120105A
- Authority
- CN
- China
- Prior art keywords
- image
- store
- characteristic
- fusion
- display image
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method, a device, equipment and a medium for identifying counterfeiting of store commodity display images, wherein the method comprises the following steps: acquiring position information of a plurality of stores and a commodity display image corresponding to each store; grouping a plurality of stores according to the location information of the stores, and for each group, performing the following steps: carrying out feature extraction on the commodity display images of all shops in the group to obtain first image features; processing the SKU information of the commodity display image by utilizing a preset first self-encoder model to obtain a second image characteristic; performing fusion processing on the first image characteristic and the second image characteristic to obtain a fusion characteristic matrix; and calculating the similarity between every two eigenvectors of the fusion characteristic matrix, and identifying stores with fake commodity display images according to the calculated similarity result. The method not only combines the image characteristics to learn the apparent similarity, but also utilizes semantic annotation to learn and continue to merge, thereby improving the accuracy of image counterfeiting recognition.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method, a device, equipment and a medium for identifying counterfeiting of a store commodity display image.
Background
In the fast-moving goods industry, when the payment of the commodity display activity cost is checked, business personnel are often required to shoot and collect the commodity display condition of a store, and the background carries out activity cost checking according to the collected commodity display image information. However, some business persons may report the exhibition situation of the store additionally or report the exhibition situation falsely by using the image of the exhibition event in the nearby store instead of the store without exhibition event, so it is usually difficult to quickly determine whether the exhibition photo data of the huge store is false.
At present, manufacturers mainly perform fake identification by means of manual spot check by appointing supervisors to go to stores, but the method is high in cost and low in efficiency; on the other hand, the conventional image recognition technology can obtain a better judgment result for the recognition of the same picture, but the judgment accuracy rate is often lower for similar commodity display pictures.
Disclosure of Invention
In view of the above-mentioned problems, the present invention provides a method, an apparatus, a device, and a medium for identifying a store display image forgery, which can accurately and quickly identify a store having a product display image forgery from huge store display photograph data.
In a first aspect, the present invention provides a method for identifying counterfeiting of a store merchandise display image, comprising:
acquiring position information of a plurality of stores and a commodity display image corresponding to each store;
grouping a plurality of the stores according to the location information of the stores, and for each group, performing the following steps:
carrying out feature extraction on the commodity display images of all shops in the group to obtain first image features;
processing the SKU information of the commodity display image by utilizing a preset first self-encoder model to obtain a second image characteristic;
performing fusion processing on the first image characteristic and the second image characteristic to obtain a fusion characteristic matrix;
and calculating the similarity between every two eigenvectors of the fusion characteristic matrix, and identifying stores with fake commodity display images according to the calculated similarity result.
Optionally, the identifying of the store with the counterfeit product display image according to the calculated similarity result specifically includes:
judging whether the calculated similarity is greater than a preset threshold value or not;
and if the similarity greater than the preset threshold exists, determining the corresponding store with the commodity display image counterfeiting based on the index of the fusion feature matrix.
Optionally, the fusion processing is performed on the first image feature and the second image feature to obtain a fusion feature matrix, which specifically includes:
horizontally splicing the first image characteristic and the second image characteristic to obtain a spliced characteristic matrix;
and processing the splicing characteristic matrix by using a preset second self-encoder model to obtain a fusion characteristic matrix.
Optionally, ResNet101 is used as a skeleton network to perform image feature extraction on the product display images of each store in the group, so as to obtain a first image feature.
Optionally, the preset first self-encoder model specifically includes: the variabilities are self-coder models.
In a second aspect, the present invention provides a store merchandise display image counterfeiting recognition apparatus, comprising:
the system comprises an image acquisition module, a display module and a display module, wherein the image acquisition module is used for acquiring position information of a plurality of stores and a commodity display image corresponding to each store;
an image recognition module for grouping a plurality of said stores according to their location information, for each grouping, performing the steps of:
carrying out feature extraction on the commodity display images of all shops in the group to obtain first image features;
processing the SKU information of the commodity display image by utilizing a preset first self-encoder model to obtain a second image characteristic;
performing fusion processing on the first image characteristic and the second image characteristic to obtain a fusion characteristic matrix;
and calculating the similarity between every two eigenvectors of the fusion characteristic matrix, and identifying stores with fake commodity display images according to the calculated similarity result.
Optionally, the identifying of the store with the counterfeit product display image according to the calculated similarity result specifically includes:
judging whether the calculated similarity is greater than a preset threshold value or not;
and if the similarity greater than the preset threshold exists, determining the corresponding store with the commodity display image counterfeiting based on the index of the fusion feature matrix.
Optionally, the fusion processing is performed on the first image feature and the second image feature to obtain a fusion feature matrix, which specifically includes:
horizontally splicing the first image characteristic and the second image characteristic to obtain a spliced characteristic matrix;
and processing the splicing characteristic matrix by using a preset second self-encoder model to obtain a fusion characteristic matrix.
In a third aspect, an embodiment of the present invention further provides a computing device, where the computing device includes:
a communication interface for communicating with other devices;
a processor coupled with the communication interface, so that the communication device executes the store merchandise display image counterfeiting identification method according to the first aspect.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program, and when the computer program runs on a computer, the computer executes the store display image counterfeiting identification method according to the first aspect.
Compared with the prior art, the invention has the beneficial effects that:
the shop commodity display image counterfeiting identification method provided by the invention firstly groups a plurality of shops based on the geographical position information of the shops, and respectively acquires two heterogeneous characteristics, namely SKU identification content and image characteristic, of the image for the commodity display image obtained by visiting and photographing each shop in the group by a business representative so as to fuse the SKU identification content and the image characteristic, thereby realizing the similarity calculation based on the fusion characteristics and further obtaining the counterfeiting identification result. The SKU identification result is the annotation on display semantics, so that the learning of semantic annotation is utilized to fuse evidences after the apparent similarity is learned through image features, the accuracy of counterfeit identification of display images of similar commodities can be effectively improved, and the identification efficiency is higher compared with a manual sampling inspection mode.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a store merchandise display image counterfeiting identification method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a store merchandise display image counterfeiting identification device according to an embodiment of the present invention.
Detailed Description
The technical solution of the present invention will be further described in more detail with reference to the accompanying drawings and the detailed description. It is to be understood that the described embodiments are merely a few embodiments of the invention, and not all 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.
In the description of the present invention, it is to be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In the description of the present invention, it is to be noted that, unless otherwise explicitly specified or limited, the terms "connected" and "connected" are to be interpreted broadly, e.g., as being fixed or detachable or integrally connected; can be mechanically or electrically connected; may be directly connected or indirectly connected through an intermediate.
To those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood in conjunction with specific situations. In addition, in the description of the present invention, "a plurality" means two or more unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a method for identifying counterfeiting of a store merchandise display image, including the following steps:
s1: the position information of a plurality of stores and the corresponding commodity display image of each store are obtained.
For the fast-moving industry, it is often necessary to ensure that the terminal stores reach a certain coverage to increase the sales volume of the goods, and therefore, each fast-moving enterprise generally needs to manage a plurality of terminal stores simultaneously. In each terminal store operation visit, a business representative usually needs to go to a patrol store, take pictures of the commodity display conditions in the store and acquire the commodity display images of each store, so that enterprises can perform activity cost accounting according to the acquired images.
Therefore, in the first step of this embodiment, the location information of a plurality of stores is obtained, specifically including names of the stores, longitude and latitude information, and the like; and then, coding and grouping the stores based on the acquired latitude and longitude information of the stores by using a Geohash algorithm so as to avoid data comparison of the whole stores.
S2: grouping a plurality of the stores according to the location information of the stores, and for each group, performing the following steps:
s21: feature extraction is performed on the commodity display images of the stores in the group to obtain first image features.
It can be understood that, the representative usually selects a nearby store as a collection source of the display image counterfeiting, and therefore, the embodiment reduces invalid comparison operations by encoding and grouping a plurality of stores based on the location information of each store, thereby improving the counterfeiting identification efficiency.
Specifically, for a plurality of stores in each group, a product display image corresponding to each store in the group is acquired, and feature extraction is performed on the acquired image to obtain a first image feature.
In one embodiment, ResNet101 may be used as a skeleton network to perform image feature extraction on the merchandise display images of the stores in the group to obtain a first image feature, where the first image feature may specifically be a 2048-dimensional feature vector.
S22: and processing the SKU information of the commodity display image by utilizing a preset first self-encoder model to obtain a second image characteristic.
Specifically, for the acquired product display images of the stores in the group, the SKU identification result of the product display image may be obtained by an image identification method.
It can be understood that after the SKU identification is performed on each product display image, the SKU identification result of each product display image is flattened into an N-dimensional sparse feature according to the type and quantity of the SKUs.
In one embodiment, for the construction of the preset first self-encoder model, a sparse matrix of 5 ten thousand SKU recognition results may be randomly extracted as a training sample set to train the initial self-encoder model, and specifically, the preset first self-encoder model may be a Variational Auto-Encoders (VAE).
And after the SKU information of the target commodity display image is processed by utilizing a preset first self-encoder model, the obtained second image characteristic is specifically a low-dimensional dense expression characteristic vector of a SKU identification result sparse matrix.
S23: and carrying out fusion processing on the first image characteristic and the second image characteristic to obtain a fusion characteristic matrix.
In one embodiment, the first image feature and the second image feature may be spliced in the horizontal direction to obtain a spliced feature matrix, and then the spliced feature matrix is processed by using a preset second self-encoder model to obtain a fused feature matrix, where the fused feature matrix includes feature vectors of two heterogeneous features fused in a deeper layer.
Specifically, the preset second self-encoder model is a pre-trained self-encoder (Auto-Encoders, AE).
S24: and calculating the similarity between every two eigenvectors of the fusion characteristic matrix, and identifying stores with fake commodity display images according to the calculated similarity result.
After calculating the similarity between every two eigenvectors of the fusion characteristic matrix, firstly judging whether the obtained similarity is greater than a preset threshold value; if the similarity greater than the preset threshold exists, the store corresponding to the fusion feature matrix is a store with a fake commodity display image, namely the store is a terminal store which is suspected to have a fraudulent display expense putting behavior and needs to be tracked; therefore, the corresponding store with the merchandise display image counterfeiting can be determined based on the index of the fusion feature matrix.
Specifically, firstly, according to the calculated similarity result, grouping and storing all feature vectors with feature similarities larger than a preset threshold, wherein the grouping mode is as follows: and dividing the commodity display images belonging to the same GeoHash code into a repeated group, and further identifying stores with fake commodity display images.
It should be noted that each commodity display image is provided with a unique identification code id for identifying different commodity display images, and meanwhile, each commodity display image is also provided with a store code id for identifying the commodity display images belonging to different stores; each element in the feature matrix represents a feature value extracted from one commodity display image, and the subscript of the feature matrix corresponds to the unique identification code id of the image, so that the similar feature subscript in the feature matrix can be traced based on the similarity, and the corresponding commodity display image and the affiliated store can be traced.
In one embodiment, the similarity between the feature vectors of the fused feature matrix may be computed by the faiss framework. Correspondingly, the preset threshold may be set to 0.95, i.e.: and when the similarity is greater than 0.95, judging that the shop corresponding to the feature matrix possibly has the commodity display image counterfeiting behavior.
It is understood that the preset threshold may be determined according to the data set and the characteristic property, and the present invention is not limited thereto.
In one embodiment, based on the identification result of the store with the counterfeit product display image obtained in the above embodiment, a data service may be issued to provide the relevant applet with the store-in-doubt data so that the checker can perform offline check on the store-in-doubt; specifically, the checker can submit the proof of verification by taking a picture during the verification process.
The embodiment of the invention provides the shop commodity display image counterfeiting identification method based on heterogeneous feature fusion, so that the terminal shop with the commodity display image counterfeiting behavior can be rapidly screened from large-scale collected image data, and the aims of cost reduction and efficiency improvement can be achieved.
As shown in fig. 2, another embodiment of the present invention further provides an image fraud recognition apparatus for store merchandise display, which includes an image acquisition module 101 and an image recognition module 102.
The image acquisition module 101 is configured to acquire location information of a plurality of stores and a product display image corresponding to each store.
The image recognition module 102 is configured to group a plurality of stores according to the location information of the stores, and for each group, perform the following steps:
carrying out feature extraction on the commodity display images of all shops in the group to obtain first image features; processing the SKU information of the commodity display image by utilizing a preset first self-encoder model to obtain a second image characteristic; performing fusion processing on the first image characteristic and the second image characteristic to obtain a fusion characteristic matrix; and calculating the similarity between every two eigenvectors of the fusion characteristic matrix, and identifying stores with fake commodity display images according to the calculated similarity result.
Moreover, the information interaction and execution process between the store commodity display image counterfeiting identification device and the store commodity display image counterfeiting identification method embodiment provided by the invention are based on the same concept, and specific contents can be referred to the description in the method embodiment of the invention, and are not described herein again.
The above-described embodiments of the apparatus are merely illustrative, and the modules described as separate components may or may not be physically separate, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the units can be selected according to actual needs to achieve the purpose of the method of the embodiment.
In a third aspect, the present invention provides a data processing apparatus comprising a processor coupled to a memory, the memory storing a program, the program being executed by the processor to cause the data processing apparatus to perform the store merchandise display image fraud identification method of the first aspect.
In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the store merchandise display image counterfeiting recognition method according to the first aspect.
It will be understood by those skilled in the art that all or part of the processes of the methods of the above embodiments may be implemented by a computer program, which may be stored in a computer-readable storage medium, and may include the processes of the embodiments of the methods when executed. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The detailed description set forth above in connection with the appended drawings describes exemplary embodiments but does not represent all embodiments that may be practiced or fall within the scope of the claims. The term "exemplary" used throughout this specification means "serving as an example, instance, or illustration," and does not mean "preferred" or "advantageous" over other embodiments. The detailed description includes specific details for the purpose of providing an understanding of the described technology. However, the techniques may be practiced without these specific details. In some instances, well-known structures and devices are shown in block diagram form in order to avoid obscuring the concepts of the described embodiments.
The previous description of the present disclosure is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the examples and designs described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for identifying counterfeiting of an image of a store commodity display is characterized by comprising the following steps:
acquiring position information of a plurality of stores and a commodity display image corresponding to each store;
grouping a plurality of the stores according to the location information of the stores, and for each group, performing the following steps:
carrying out feature extraction on the commodity display images of all shops in the group to obtain first image features;
processing the SKU information of the commodity display image by utilizing a preset first self-encoder model to obtain a second image characteristic;
performing fusion processing on the first image characteristic and the second image characteristic to obtain a fusion characteristic matrix;
and calculating the similarity between every two eigenvectors of the fusion characteristic matrix, and identifying stores with fake commodity display images according to the calculated similarity result.
2. The store merchandise display image counterfeiting identification method according to claim 1, wherein the identifying of the store with the merchandise display image counterfeiting according to the calculated similarity result is specifically:
judging whether the calculated similarity is greater than a preset threshold value or not;
and if the similarity greater than the preset threshold exists, determining the corresponding store with the commodity display image counterfeiting based on the index of the fusion feature matrix.
3. The store merchandise display image counterfeiting identification method according to claim 1, wherein the fusion processing is performed on the first image feature and the second image feature to obtain a fusion feature matrix, and specifically comprises:
horizontally splicing the first image characteristic and the second image characteristic to obtain a spliced characteristic matrix;
and processing the splicing characteristic matrix by using a preset second self-encoder model to obtain a fusion characteristic matrix.
4. The method for identifying a counterfeit of a product display image of an store according to claim 1, wherein the first image feature is obtained by performing image feature extraction on the product display image of each store in the group using ResNet101 as a skeleton network.
5. The store merchandise display image counterfeiting identification method according to claim 1, wherein the preset first self-encoder model is specifically: the variabilities are self-coder models.
6. An apparatus for recognizing counterfeiting of an image on a display of an article in an store, comprising:
the system comprises an image acquisition module, a display module and a display module, wherein the image acquisition module is used for acquiring position information of a plurality of stores and a commodity display image corresponding to each store;
an image recognition module for grouping a plurality of said stores according to their location information, for each grouping, performing the steps of:
carrying out feature extraction on the commodity display images of all shops in the group to obtain first image features;
processing the SKU information of the commodity display image by utilizing a preset first self-encoder model to obtain a second image characteristic;
performing fusion processing on the first image characteristic and the second image characteristic to obtain a fusion characteristic matrix;
and calculating the similarity between every two eigenvectors of the fusion characteristic matrix, and identifying stores with fake commodity display images according to the calculated similarity result.
7. The store merchandise display image counterfeiting recognition device according to claim 6, wherein the recognition of the store with the merchandise display image counterfeiting according to the calculated similarity result is specifically:
judging whether the calculated similarity is greater than a preset threshold value or not;
and if the similarity greater than the preset threshold exists, determining the corresponding store with the commodity display image counterfeiting based on the index of the fusion feature matrix.
8. The store merchandise display image counterfeiting identification device according to claim 6, wherein the fusion processing is performed on the first image feature and the second image feature to obtain a fusion feature matrix, and specifically comprises:
horizontally splicing the first image characteristic and the second image characteristic to obtain a spliced characteristic matrix;
and processing the splicing characteristic matrix by using a preset second self-encoder model to obtain a fusion characteristic matrix.
9. A computing device, wherein the computing device comprises:
a communication interface for communicating with other devices;
a processor coupled with the communication interface, so that the communication device executes the store merchandise display image counterfeiting identification method according to any one of claims 1 to 5.
10. A computer-readable storage medium, characterized in that,
the computer-readable storage medium stores a computer program which, when run on a computer, causes the computer to execute the store merchandise display image fraud identification method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111337421.XA CN114120105A (en) | 2021-11-11 | 2021-11-11 | Method, device, equipment and medium for identifying counterfeiting of store commodity display image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111337421.XA CN114120105A (en) | 2021-11-11 | 2021-11-11 | Method, device, equipment and medium for identifying counterfeiting of store commodity display image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114120105A true CN114120105A (en) | 2022-03-01 |
Family
ID=80378620
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111337421.XA Pending CN114120105A (en) | 2021-11-11 | 2021-11-11 | Method, device, equipment and medium for identifying counterfeiting of store commodity display image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114120105A (en) |
-
2021
- 2021-11-11 CN CN202111337421.XA patent/CN114120105A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107690657B (en) | Trade company is found according to image | |
| JP6452186B2 (en) | Insurance compensation fraud prevention method, system, apparatus and readable recording medium based on coincidence of multiple photos | |
| CN110009364B (en) | Industry identification model determining method and device | |
| KR20190069457A (en) | IMAGE BASED VEHICLES LOSS EVALUATION METHOD, DEVICE AND SYSTEM, | |
| US9489582B2 (en) | Video anomaly detection based upon a sparsity model | |
| CN102831385A (en) | Device and method for target identification in multiple-camera monitoring network | |
| TW202009681A (en) | Sample labeling method and device, and damage category identification method and device | |
| CN111553355B (en) | Monitoring video-based method for detecting and notifying store outgoing business and managing store owner | |
| CN109766755A (en) | Face identification method and Related product | |
| CN112508109B (en) | Training method and device for image recognition model | |
| CN112613569A (en) | Image recognition method, and training method and device of image classification model | |
| CN112614102A (en) | Vehicle detection method, terminal and computer readable storage medium thereof | |
| CN111241873A (en) | Image reproduction detection method, training method of model thereof, payment method and payment device | |
| CN114550051A (en) | Vehicle loss detection method and device, computer equipment and storage medium | |
| CN115018513A (en) | Data inspection method, device, equipment and storage medium | |
| CN114255377A (en) | Differential commodity detection and classification method for intelligent container | |
| CN111401438B (en) | Image sorting method, device and system | |
| CN113486715A (en) | Image reproduction identification method, intelligent terminal and computer storage medium | |
| CN114120105A (en) | Method, device, equipment and medium for identifying counterfeiting of store commodity display image | |
| Sprague et al. | Integrating acceleration signal processing and image segmentation for condition assessment of asphalt roads | |
| CN115565097A (en) | Method and device for detecting compliance of personnel behaviors in transaction scene | |
| CN113160414A (en) | Automatic identification method and device for remaining amount of goods, electronic equipment and computer readable medium | |
| CN111105590A (en) | Alarm method and device | |
| CN116453194B (en) | Face attribute discriminating method and device | |
| CN118115230A (en) | Commodity information display, image identification method and electronic equipment |
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 |