CN109271935A - The matching method of article and electronic tag, apparatus and system - Google Patents
The matching method of article and electronic tag, apparatus and system Download PDFInfo
- Publication number
- CN109271935A CN109271935A CN201811084413.7A CN201811084413A CN109271935A CN 109271935 A CN109271935 A CN 109271935A CN 201811084413 A CN201811084413 A CN 201811084413A CN 109271935 A CN109271935 A CN 109271935A
- Authority
- CN
- China
- Prior art keywords
- article
- electronic tag
- identity
- image
- label
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device
Abstract
The present invention provides the matching methods of a kind of article and electronic tag, apparatus and system, are related to electronic label technology field, this method comprises: acquisition includes the target image of various article and multiple electronic tags；Detect the location information of each article and the location information of each electronic tag in target image；The identity of the Item Information of each article and each electronic tag in recognition target image；According to the location information and identity of the location information of each article and Item Information and each electronic tag, the pairing relationship between each article and each electronic tag is determined.The present invention can save human cost, effectively promote the matching efficiency of article and electronic tag.
Description
Technical field
The present invention relates to electronic label technology fields, more particularly, to the matching method of a kind of article and electronic tag, dress
It sets and system.
Background technique
In a variety of occasions such as retail shop, storehouse, library, require to put a variety of objects on supporter mostly
Product, while giving each article the corresponding label for attaching display Item Information on supporter；That is, need it is artificial in advance to article and
Label is matched.Such as, need related personnel that Item Information is printed upon on label first, then according to article position
The label is attached near such as article front and other items again, completes artificial pairing process.
However, related personnel also needs to be replaced frequently label, and marks due to the variation of laying for goods position or Item Information
The attaching and replacement of label fully rely on manpower completion, take time and effort, inefficiency.
Summary of the invention
In view of this, the purpose of the present invention is to provide the matching method of a kind of article and electronic tag, apparatus and system,
Human cost can be saved, the matching efficiency of article and electronic tag is effectively promoted.
To achieve the goals above, technical solution used in the embodiment of the present invention is as follows:
In a first aspect, the embodiment of the invention provides the matching method of a kind of article and electronic tag, the kind of the article
Class be it is multiple, the quantity of the electronic tag is multiple, and each electronic tag currently shows respective identity；It is more
The kind article and multiple electronic tags are arranged on supporter；The described method includes: obtaining comprising there are many described
The target image of article and multiple electronic tags；Detect the location information of each article and each institute in the target image
State the location information of electronic tag；Identify the Item Information of each article and each electronic tag in the target image
Identity；According to the location information of each article and Item Information and the location information and body of each electronic tag
Part mark, determines the pairing relationship between each article and each electronic tag.
Further, described according to the location information and Item Information of each article and the position of each electronic tag
The step of confidence ceases and identity, determines the pairing relationship between each article and each electronic tag, comprising: according to
The location information of the location information of each article and each electronic tag is determined according to preset location matches relationship
Electronic tag corresponding with each article；Wherein, the location matches relationship includes article and corresponding electronic tag
Positional relationship；The identity of the Item Information of each article electronic tag corresponding with each article is closed
Connection generates the pairing relationship between each article and each electronic tag.
Further, the method also includes: the label for obtaining each article shows information；Based on the pairing relationship,
The label of each article is shown that information is handed down to electronic tag corresponding with each article.Further, include in acquisition
Before the step of there are many target images of the article and multiple electronic tags, the method also includes: using random
The method of salary distribution issues identity to multiple electronic tags；Wherein, the identity includes number, character, identification code
One of or it is a variety of.
Further, the location information of each article and the position of each electronic tag in the detection target image
The step of confidence ceases, comprising: the target image is input in target detection model, passes through the target detection model inspection
Each article is obtained in the position of location information and each electronic tag in the target image in the target image
Confidence breath.
Further, the target detection model is two stages detection model.
Further, the Item Information of each article and the body of each electronic tag in the identification target image
The step of part mark, comprising: based on location information of each article in the target image, scratched from the target image
Take the images of items of each article；Location information based on each electronic tag in the target image, from the mesh
The label image of each electronic tag is taken in logo image；The article letter of each article is obtained from each images of items
It ceases, and obtains the identity of each electronic tag from each label image.
Further, the Item Information that each article is obtained from each images of items, and from each mark
The step of obtaining the identity of each electronic tag in label image, comprising: be input to the images of items of each article
In article identification model, the Item Information of each article is identified by the article identification model；By each electronic tag
Label image be input in tag recognition model, identified by the tag recognition model and to be shown on each electronic tag
Identity.
Further, the identity in a label image includes at least one component；The tag recognition
Model includes that marker element detection unit, marker element take unit, marker element recognition unit and marker element assembled unit；
The label image by each electronic tag is input in tag recognition model, is identified by the tag recognition model each
The step of identity shown on the electronic tag, comprising: be input to the label image of each electronic tag described
Marker element detection unit detects to obtain each of identity in each label image by the marker element detection unit
The position of component；Based on the position of each component in each label image, scratched by the marker element
Unit is taken to take the element image of each component；It is single that each element image is input to the marker element identification
Member identifies the component in each element image by the marker element recognition unit；Based on each label image
In each component position, combined by each component that the marker element assembled unit will identify that
Form the identity shown on each electronic tag.
Further, the label shows that information includes the pass of Item Title, item price, the associated date of article, article
Join one of identification code or a variety of.
Second aspect, the embodiment of the present invention also provide the contrast means of a kind of article and electronic tag, the kind of the article
Class be it is multiple, the quantity of the electronic tag is multiple, and each electronic tag currently shows respective identity；It is more
The kind article and multiple electronic tags are arranged on supporter；Described device includes: image collection module, for obtaining
It takes comprising there are many target images of the article and multiple electronic tags；Position detecting module, for detecting the mesh
The location information of the location information of each article and each electronic tag in logo image；Identification module, it is described for identification
The identity of the Item Information of each article and each electronic tag in target image；Matching module, for according to each
The location information and identity of the location information and Item Information of the article and each electronic tag, determine each institute
State the pairing relationship between article and each electronic tag.
The third aspect, the embodiment of the invention provides the pair system of a kind of article and electronic tag, the system comprises:
Image collecting device, processor and storage device；Described image acquisition device, for acquiring target image；The storage device
On be stored with computer program, the computer program is executed as described in any one of first aspect when being run by the processor
Method.
Fourth aspect, the embodiment of the invention provides be stored with computer journey on a kind of computer readable storage medium
The step of sequence, the computer program executes above-mentioned first aspect described in any item methods when being run by processor.
The embodiment of the invention provides the matching methods of a kind of article and electronic tag, apparatus and system, obtain packet first
Target image containing various article and multiple electronic tags on supporter；Then each article and each is detected in the target image
The location information of electronic tag, and identify the identity of the Item Information and each electronic tag of each article, and then can basis
Location information and the identity of the location information and Item Information and each electronic tag of each article determine each article and each
Pairing relationship between electronic tag.This mode provided in this embodiment, only need to by the image of acquisition can to article and
Electronic tag pairing, without manually matching in advance to article and label in advance, has preferably saved human cost, has improved article
With the matching efficiency of electronic tag.
Other feature and advantage of the embodiment of the present invention will illustrate in the following description, alternatively, Partial Feature and excellent
Point can deduce from specification or unambiguously determine, or the above-mentioned technology by implementing the embodiment of the present invention can obtain
Know.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 shows the structural schematic diagram of a kind of electronic equipment provided by the embodiment of the present invention；
Fig. 2 shows the matching method flow charts of a kind of article provided by the embodiment of the present invention and electronic tag；
Fig. 3 a shows a kind of positional diagram of article and electronic tag provided by the embodiment of the present invention；
Fig. 3 b shows the positional diagram of another kind article and electronic tag provided by the embodiment of the present invention；
Fig. 4 shows a kind of pairing schematic diagram of commodity and electronic tag provided by the embodiment of the present invention；
Fig. 5 shows a kind of structural block diagram of the contrast means of article and electronic tag provided by the embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with attached drawing to the present invention
Technical solution be clearly and completely described, it is clear that described embodiments are some of the embodiments of the present invention, rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, shall fall within the protection scope of the present invention.
The pairing process of article and label is needed mostly by manually realizing at present, it is contemplated that often will appear laying for goods
The case where shift in position or article self information change can put into more manpower replacement note, take time and effort and inefficiency,
To improve this problem, a kind of matching method, the apparatus and system of article and electronic tag provided in an embodiment of the present invention, the technology
It can be applied to the various fields for needing to correspond to attachment labels to article such as retail trade, storage sector, library, the technology
Corresponding software and or hardware realization can be used, describe in detail below to the embodiment of the present invention.
Embodiment one:
Firstly, referring to Fig.1 come describe for realizing the embodiment of the present invention a kind of article and electronic tag matching method,
The exemplary electronic device 100 of apparatus and system.
The structural schematic diagram of a kind of electronic equipment as shown in Figure 1, electronic equipment 100 include one or more processors
102, one or more storage devices 104, input unit 106, output device 108 and image collecting device 110, these components
It is interconnected by bindiny mechanism's (not shown) of bus system 112 and/or other forms.It should be noted that electronic equipment shown in FIG. 1
100 component and structure be it is illustrative, and not restrictive, as needed, the electronic equipment also can have other
Component and structure.
The processor 102 can use digital signal processor (DSP), field programmable gate array (FPGA), can compile
At least one of journey logic array (PLA) example, in hardware realizes that the processor 102 can be central processing unit
(CPU) or one or more of the processing unit of other forms with data-handling capacity and/or instruction execution capability
Combination, and can control other components in the electronic equipment 100 to execute desired function.
The storage device 104 may include one or more computer program products, and the computer program product can
To include various forms of computer readable storage mediums, such as volatile memory and/or nonvolatile memory.It is described easy
The property lost memory for example may include random access memory (RAM) and/or cache memory (cache) etc..It is described non-
Volatile memory for example may include read-only memory (ROM), hard disk, flash memory etc..In the computer readable storage medium
On can store one or more computer program instructions, processor 102 can run described program instruction, to realize hereafter institute
The client functionality (realized by processor) in the embodiment of the present invention stated and/or other desired functions.In the meter
Can also store various application programs and various data in calculation machine readable storage medium storing program for executing, for example, the application program use and/or
The various data etc. generated.
The input unit 106 can be the device that user is used to input instruction, and may include keyboard, mouse, wheat
One or more of gram wind and touch screen etc..
The output device 108 can export various information (for example, image or sound) to external (for example, user), and
It and may include one or more of display, loudspeaker etc..
Described image acquisition device 110 can shoot the desired image of user (such as photo, video etc.), and will be clapped
The image taken the photograph is stored in the storage device 104 for the use of other components.
Illustratively, for realizing the matching method of article according to an embodiment of the present invention and electronic tag, device and it is
The exemplary electronic device of system may be implemented as the intelligent terminals such as gateway, server, computer.
Embodiment two:
The matching method of a kind of article and electronic tag is present embodiments provided, it for ease of understanding, first can be to this method
A kind of application environment be described below: such as, this method can by previous embodiment provide electronic equipment execute, the electronic equipment
It can be gateway, be also possible to other equipment with data-handling capacity, such as host computer, local server, Cloud Server
Deng.The electronic equipment can independently be handled the information received, can also be connected with server, be carried out jointly to information
It determines processing, and processing result is uploaded to cloud.
It is mainly used in the matching method of article provided in this embodiment and electronic tag more on supporter to being arranged in
Kind of article and electronic tag matched namely the type of article be it is multiple, the quantity of electronic tag be it is multiple, herein with retail
It being illustrated for shop, the various article (namely commodity) in retail shop is all placed on supporter for consumer's selection,
It is also previously provided with electronic tag on the supporter, for showing the information such as Item Title, item price.Wherein, article and electricity
Subtab can be arranged in a one-to-one correspondence, and can also be arranged with many-one；Such as, an electronic tag is correspondingly arranged before every kind of article,
Or various article shares an electronic tag.
Specifically, each electronic tag currently shows respective identity during pairing.The identity can
To include one of number, character, identification code or multiple combinations, the identity difference of different electronic tags.Wherein, it identifies
Code can be the information codings such as bar code, two dimensional code, three-dimension code, and information can be presented according to predetermined manner in identification code, in this implementation
In example, different identification codes can characterize the identity of different electronic tags.When it is implemented, above-mentioned electronic equipment can be with
Each electronic tag on supporter is communicated to connect by wire/wireless mode, then issues identity to each electronic tag.One
In kind embodiment, corresponding identity can be fixedly installed with electron label can also adopt in another embodiment
Identity is issued to multiple electronic tags with the mode that is randomly assigned.Random electron label provided in this embodiment issues identity
The mode of mark, the identity of electronic tag are only intended to distinguish each electronic tag when matching to article and electronic tag,
Without needing the artificial fixation identity for recording electronic tag on an electronic device in advance in the related technology, thus it is randomly assigned
The mode of the identity of electronic tag is more convenient, can effectively reduce human cost in this link.
In one embodiment, reference can be made to the matching method flow chart of a kind of article shown in Fig. 2 and electronic tag, is somebody's turn to do
Method includes the following steps:
Step S202, acquisition include the target image of various article and multiple electronic tags.Wherein, the present embodiment is signified
Article can be the commodity in retail shop, storage article, books in library in warehouse etc. are not limited herein.
Multiple electronic tags have been subjected to the initialization process of distribution identity at this time, currently show respective identity,
String number etc..
When acquisition includes the target image of various article and multiple electronic tags, it can directly pass through the figure such as video camera
As the supporter that acquisition equipment face is placed with article and electronic tag acquires a whole photo.
Step S204 detects the location information of each article and the location information of each electronic tag in target image.It is specific and
Speech, can detecte the position of each article and each electronic tag in the target image, and the position that will test out is marked, all
Such as, position coordinates be can record, or directly mark includes the framework of article and includes electronic tag in the target image
Framework.In one embodiment, such as target detection model realization based on deep learning, the target detection can be used
Model is specially a kind of neural network model, can be obtained by training in advance, to realize to article in image and electronic tag
Detection.In practical application, target image can be input in a target detection model while detect article and electronics mark
Label, target image can also be separately input in two target detection models, using a target detection model inspection article,
Using another target detection model inspection electronic tag, specific detection mode be can according to need and flexible setting, herein not
It is repeated.
Step S206, the identity of the Item Information and each electronic tag of each article in recognition target image.Wherein, object
Product information can be the identification information of article, Brand, book name, the Item Information for article of storing in a warehouse etc.；Specifically may be used
It is realized using the Model of Target Recognition based on deep learning, Model of Target Recognition is equally a kind of to be obtained by training in advance
Neural network model.In practical application, can also using the Item Information for identifying article in Model of Target Recognition simultaneously and
A Model of Target Recognition identification Item Information, another target identification can also be respectively adopted in the identity of electronic tag
Model identifies the identity of electronic tag, and specific identification method can according to need and flexible setting, herein without repeating.
Step S208, according to the location information of each article and Item Information and the location information and body of each electronic tag
Part mark, determines the pairing relationship between each article and each electronic tag.
Such as, according to the location information of the location information of each article and each electronic tag, according to preset position
Electronic tag corresponding with each article is determined with relationship；Wherein, location matches relationship includes article and corresponding electronics mark
The positional relationship of label；The positional relationship depends primarily on the position of article and the electronic tag of its information to be shown on supporter,
For ease of understanding, the present embodiment simply illustrates two kinds of positional relationships as shown in Figure 3a and Figure 3b shows, and Fig. 3 a and Fig. 3 b only show
The article (that is, SKU) and electronic tag anticipated out on one layer of shelf of supporter；Wherein, Fig. 3 a indicates article and electronic tag
One-to-one positional relationship, Fig. 3 b indicate article and the many-to-one positional relationship of electronic tag, such as, same layer on supporter
The Item Information of various article on shelf is shown in an electronic tag jointly, for showing the electronic tag of Item Information
It can be set in the leftmost side, medial side or rightmost side etc., specifically can manually set.It is understood that Fig. 3 a and Fig. 3 b are only
Example in practical applications can also be by other positions relationship, herein without repeating.
It, can be by the Item Information of each article electricity corresponding with each article after the corresponding electronic tag of each article has been determined
The identity of subtab is associated, and generates the pairing relationship between each article and each electronic tag.
The above-mentioned article of the embodiment of the present invention and the matching method of electronic tag only need to can give object by the image of acquisition
Product and electronic tag pairing, without manually matching in advance to article and label in advance, have preferably saved human cost, have improved
The matching efficiency of article and electronic tag.
The present embodiment, can be in detecting target image when the location information of the location information of each article and each electronic tag
Target image is input in the target detection model that training obtains in advance, each article is obtained by target detection model inspection and is existed
The location information of location information and each electronic tag in the target image in target image.Wherein, the instruction of target detection model
White silk process, which may is that, inputs to target for the training image collection for carrying article position label and electronic tag location tags in advance
Detection model calculates loss according to the difference between the reality output and desired output of target detection model in the training process,
The network parameter of target detection model is adjusted using back-propagation algorithm, until the loss function value of target detection model (can
Characterize the difference between reality output and desired output) deconditioning when being lower than preset value, target detection model at this time can be compared with
Accurately to detect the position of article and electronic tag in the picture, testing result meets expected results.
In order to promote detection accuracy, target detection model provided in this embodiment can use two stages (two-
Stage) detection model, two stages detection model and the difference of single phase (one-stage) detection model are that two stages detect mould
Type is first using initial block predicting candidate frame, then based on candidate frame prediction target frame (that is, comprising article or electronic tag
Frame), and single phase detection model is directly to predict target frame with initial block.In contrast, the present embodiment is detected using two stages
The precision of model is higher, more conducively accurately examines to the target image for including various article and multiple electronic tags
It surveys.When it is implemented, two stages detection model can be using such as Faster R-CNN and related mutation (for example, using feature
Pyramid network extraction Analysis On Multi-scale Features Faster R-CNN model) etc. neural network models realize.
In a specific embodiment, in recognition target image the Item Information of each article and each electronic tag body
When part mark, it is referred to following steps realization:
(1) location information based on each article in the target image takes the images of items of each article from target image.
Such as, after mark is comprising the target frame of each article in the target image, be directly based upon the target frame of each article to target image into
Row shearing, obtains the images of items of each article.
(2) location information based on each electronic tag in the target image takes each electronic tag from target image
Label image.Such as, after mark is comprising the target frame of each electronic tag in the target image, it is directly based upon the mesh of each electronic tag
Mark frame shears target image, obtains the images of items of each article.
(3) Item Information of each article is obtained from each images of items, and each electronics mark is obtained from each label image
The identity of label.In one embodiment, it is contemplated that the identification complexity of article and electronic tag, therefore can be by article
It is separately identified with electronic tag, such as, the images of items of each article can be input to the article identification mould that training obtains in advance
In type, the Item Information of each article is identified by article identification model；The label image of each electronic tag is input to preparatory instruction
In the tag recognition model got, the identity shown on each electronic tag is identified by tag recognition model.
Article identification model and tag recognition model are similar with the training step of above-mentioned target detection model, mainly model
The factors such as structure, training set and loss function are different；Such as, the training set of article identification model is to carry Item Information label
Images of items, the training set of tag recognition model is the electronic tag image for carrying identity label.The present embodiment mentions
Such as Resnet model, Xception model realization can be used in the article identification model and tag recognition model of confession, has higher
Accuracy of identification.
Identity in label image provided in this embodiment may include at least one component；Such as, one
Identity in label image is " 195325 " string number, then each number is a component.Certainly, identity
It also may include the characters such as a, b, c, &, # in mark, each character is just used as a component.
In one embodiment, tag recognition model may include that marker element detection unit, marker element take list
Member, marker element recognition unit and marker element assembled unit.Based on this, the label image of each electronic tag is being input to mark
It signs in identification model, when identifying the identity shown on each electronic tag by tag recognition model, is referred to hold as follows
Row:
Step 1, the label image of each electronic tag is input to marker element detection unit, is detected by marker element single
Member detection obtains the position of each component of identity in each label image.Specifically, marker element detection unit can
To be a kind of target detection model, the target to be detected of the target detection model is the component in identity (can letter
Referred to as marker element), which can be obtained by training in advance, and the target detection model that training obtains is detectable
The position of each component in outgoing label image can also mark the position of each component in label image by framework.
Step 2, the position based on each component in each label image, takes unit by marker element and takes each group
At the element image of element.It is understood that usually each component shared region in label image is smaller, in order to
Preferably component is identified, marker element takes unit can be based on the position of component in label image, will
The element image of each component takes out, in order to carry out elemental recognition individually for element image.In view of detecting
Component location information may not enough precisely, in practical applications, can also finely tune according to actual needs and take region,
Such as, can the location information based on component by include component region to be taken amplify, to guarantee
Enough include entire component, helps subsequent preferably to identify the element image taken out.
Step 3, each element image is input to marker element recognition unit, each member is identified by marker element recognition unit
Component in sketch map picture.Specifically, marker element recognition unit can be a kind of Model of Target Recognition, the target identification
The target to be identified of model is above-mentioned component, which can be obtained by training in advance, and training obtains
Model of Target Recognition may recognize that each component.
Step 4, the position based on each component in each label image, will identify that by marker element assembled unit
Each composition element combinations form the identity shown on each electronic tag.For example identify the label figure an of electronic tag
It, can be according to " 1 ", " 9 ", " 5 " detected before as in after each component respectively " 1 ", " 9 ", " 5 " " 3 " " 2 " " 5 "
The position of " 3 " " 2 " " 5 " in label image is combined it, is formed " 195325 "；That is, the electronics mark can be finally obtained
The identity for signing display is 195325.
By the above-mentioned means, can relatively accurately be identified to the identity shown on each electronic tag.
On the basis of known contents and the pairing relationship of electronic tag, the above method further include: obtain the mark of each article
Label display information；Based on pairing relationship, the label of each article is shown that information is handed down to electronic tag corresponding with each article.?
In concrete application, the corresponding label of the article can be searched according to the Item Information identified and shows information, label shows information
It may include one of association identification code of Item Title, item price, the associated date of article, article etc. or a variety of；It is all
Such as, label in retail shop show information may include product name (or title abbreviation), commodity price, commodity date of manufacture
Deng；Specifically can flexible setting according to actual needs, details are not described herein.
For ease of understanding, the pairing schematic diagram for present embodiments providing a kind of commodity and electronic tag shown in Fig. 4, at this
Illustrate that a width includes the target image of various article and electronic tag in figure first, with schematically being outlined with dotted line frame
A kind of article and a kind of electronic tag (specifically can be and obtained by target detection model inspection, do not illustrate to detect in Fig. 4
Journey), then by Model of Target Recognition, respectively obtain the identity of the Item Information and electronic tag of article.Target image
On any article and electronic tag be all that the identity mark of respective position, Item Information and electronic tag is determined using aforesaid way
Know, by the above-mentioned means, the pairing of article and electronic tag can be obtained as a result, being with article and electronic tag one-to-one correspondence
Example, pairing result can be found in shown in table 1:
Table 1
By the above-mentioned means, can determine the pairing relationship of article and electronic tag, it will so as to be based on Item Information
The label of each article shows that information is written to corresponding electronic tag.
In conclusion the matching method of above-mentioned article and electronic tag provided in this embodiment, can preferably save people
Power cost effectively promotes the matching efficiency of article and electronic tag.
Embodiment three:
Corresponding to the matching method of article provided in embodiment two and electronic tag, the embodiment of the invention provides one
The contrast means of kind of article and electronic tag, a kind of structural frames of the contrast means of shown in Figure 5 article and electronic tag
Figure, the device comprise the following modules:
Image collection module 502, for obtain include various article and multiple electronic tags target image；
Position detecting module 504, for detecting the position of the location information of each article and each electronic tag in target image
Information；
Identification module 506, for identification in target image the Item Information of each article and each electronic tag identity；
Matching module 508, for being believed according to the location information and Item Information of each article and the position of each electronic tag
Breath and identity, determine the pairing relationship between each article and each electronic tag.
The above-mentioned article of the embodiment of the present invention and the contrast means of electronic tag only need to can give object by the image of acquisition
Product and electronic tag pairing, without manually matching in advance to article and label in advance, have preferably saved human cost, have improved
The matching efficiency of article and electronic tag.
In one embodiment, above-mentioned apparatus further includes mark distribution module, more for being given using the mode that is randomly assigned
A electronic tag issues identity；Wherein, identity includes one of number, character, identification code or a variety of.
In one embodiment, above-mentioned position detecting module is used for: target image is input to what training in advance obtained
In target detection model, the location information and each electronics mark of each article in the target image are obtained by target detection model inspection
The location information of label in the target image.In a specific embodiment, above-mentioned target detection model is two stages to detect mould
Type.
In one embodiment, above-mentioned identification module is used for: based on the location information of each article in the target image, from
The images of items of each article is taken in target image；Location information based on each electronic tag in the target image, from target figure
The label image of each electronic tag is taken as in；Obtain the Item Information of each article from each images of items, and from each label
The identity of each electronic tag is obtained in image.
In a specific embodiment, above-mentioned identification module is further used for for the images of items of each article being input to pre-
In the article identification model that first training obtains, the Item Information of each article is identified by article identification model；By each electronic tag
Label image be input in the obtained tag recognition model of training in advance, identified on each electronic tag by tag recognition model
The identity of display.Further, the identity in a label image includes at least one component；The mark
Label identification model includes that marker element detection unit, marker element take unit, marker element recognition unit and marker element group
Close unit；Above-mentioned identification module is also used to: the label image of each electronic tag being input to the marker element and detects list
Member detects to obtain the position of each component of identity in each label image by the marker element detection unit
It sets；Based on the position of each component in each label image, unit is taken by the marker element and is taken respectively
The element image of the component；Each element image is input to the marker element recognition unit, passes through the mark
Know elemental recognition unit and identifies the component in each element image；Based on each composition in each label image
The position of element combines to form each electronics by each component that the marker element assembled unit will identify that
The identity shown on label.
In one embodiment, above-mentioned matching module is used for: according to the location information of each article and each electronic tag
Location information determines electronic tag corresponding with each article according to preset location matches relationship；Wherein, location matches are closed
System includes the positional relationship of article and corresponding electronic tag；By the Item Information of each article electronics corresponding with each article
The identity of label is associated, and generates the pairing relationship between each article and each electronic tag.
In one embodiment, above-mentioned apparatus further include: display data obtaining module and display information issue module,
In, the label that display data obtaining module is used to obtain each article shows information；Display information issue module for based on match
The label of each article is shown that information is handed down to electronic tag corresponding with each article by relationship.
In a specific embodiment, above-mentioned label shows that information includes the association of Item Title, item price, article
Date, article one of association identification code or a variety of.
The technical effect of device provided by the present embodiment, realization principle and generation is identical with previous embodiment, for letter
It describes, Installation practice part does not refer to place, can refer to corresponding contents in preceding method embodiment.
Example IV:
The embodiment of the invention also provides the pair system of a kind of article and electronic tag, which includes: Image Acquisition
Device, processor and storage device；Wherein, image collecting device is for acquiring target image；Calculating is stored on storage device
Machine program, computer program execute the method as provided by embodiment two when being run by processor.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description
Specific work process, can refer to corresponding processes in the foregoing method embodiment, details are not described herein.
Further, the present embodiment additionally provides a kind of computer readable storage medium, the computer readable storage medium
On be stored with computer program, the matching method of above-mentioned article and electronic tag is executed when computer program is run by processor
Step.
The matching method of article and electronic tag provided by the embodiment of the present invention, the computer program of apparatus and system produce
Product, the computer readable storage medium including storing program code, before the instruction that said program code includes can be used for execution
Method described in the embodiment of the method for face, specific implementation can be found in embodiment of the method, and details are not described herein.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
In the description of the present invention, it should be noted that term " center ", "upper", "lower", "left", "right", "vertical",
The orientation or positional relationship of the instructions such as "horizontal", "inner", "outside" be based on the orientation or positional relationship shown in the drawings, merely to
Convenient for description the present invention and simplify description, rather than the device or element of indication or suggestion meaning must have a particular orientation,
It is constructed and operated in a specific orientation, therefore is not considered as limiting the invention.In addition, term " first ", " second ",
" third " is used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention
Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention, should all cover in protection of the invention
Within the scope of.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (13)
1. the matching method of a kind of article and electronic tag, which is characterized in that the type of the article is multiple, the electronics mark
The quantity of label is multiple, and each electronic tag currently shows respective identity；A variety of articles and multiple institutes
Electronic tag is stated to be arranged on supporter；The described method includes:
It obtains comprising there are many target images of the article and multiple electronic tags；
Detect the location information of the location information of each article and each electronic tag in the target image；
Identify the identity of the Item Information of each article and each electronic tag in the target image；
According to the location information of each article and Item Information and the location information and identity mark of each electronic tag
Know, determines the pairing relationship between each article and each electronic tag.
2. the method according to claim 1, wherein described believe according to the location information and article of each article
Location information and the identity of breath and each electronic tag, determine between each article and each electronic tag
Pairing relationship the step of, comprising:
According to the location information of the location information of each article and each electronic tag, according to preset location matches
The determining electronic tag corresponding with each article of relationship；Wherein, the location matches relationship includes article and corresponding
The positional relationship of electronic tag；
The identity of the Item Information of each article electronic tag corresponding with each article is associated, is generated each
Pairing relationship between the article and each electronic tag.
3. the method according to claim 1, wherein the method also includes:
The label for obtaining each article shows information；
Based on the pairing relationship, the label of each article is shown that information is handed down to electronics mark corresponding with each article
Label.
4. the method according to claim 1, wherein obtaining comprising there are many article and multiple electricity
Before the step of target image of subtab, the method also includes:
Identity is issued to multiple electronic tags using the mode that is randomly assigned；Wherein, the identity include number,
One of character, identification code are a variety of.
5. the method according to claim 1, wherein the position for detecting each article in the target image
The step of location information of confidence breath and each electronic tag, comprising:
The target image is input in target detection model, each article is obtained by the target detection model inspection
In the location information of location information and each electronic tag in the target image in the target image.
6. according to the method described in claim 5, it is characterized in that, the target detection model is two stages detection model.
7. according to the method described in claim 5, it is characterized in that, the object for identifying each article in the target image
The step of identity of product information and each electronic tag, comprising:
Location information based on each article in the target image takes each article from the target image
Images of items；
Location information based on each electronic tag in the target image takes each electricity from the target image
The label image of subtab；
The Item Information of each article is obtained from each images of items, and each institute is obtained from each label image
State the identity of electronic tag.
8. the method according to the description of claim 7 is characterized in that described obtain each article from each images of items
Item Information, and the step of obtaining from each label image the identity of each electronic tag, comprising:
The images of items of each article is input in article identification model, is identified by the article identification model each described
The Item Information of article；
The label image of each electronic tag is input in tag recognition model, is identified by the tag recognition model each
The identity shown on the electronic tag.
9. according to the method described in claim 8, it is characterized in that, the identity in a label image includes at least
One component；The tag recognition model includes marker element detection unit, marker element takes unit, marker element is known
Other unit and marker element assembled unit；
The label image by each electronic tag is input in tag recognition model, is known by the tag recognition model
The step of identity shown on not each electronic tag, comprising:
The label image of each electronic tag is input to the marker element detection unit, is detected by the marker element
Unit detects to obtain the position of each component of identity in each label image；
Based on the position of each component in each label image, unit is taken by the marker element and is taken respectively
The element image of the component；
Each element image is input to the marker element recognition unit, is identified by the marker element recognition unit each
Component in the element image；
Based on the position of each component in each label image, will be identified by the marker element assembled unit
Each component out combines the identity to be formed and be shown on each electronic tag.
10. according to the method described in claim 3, it is characterized in that, the label shows that information includes Item Title, article valence
One of lattice, the associated date of article, association identification code of article are a variety of.
11. the contrast means of a kind of article and electronic tag, which is characterized in that the type of the article is multiple, the electronics
The quantity of label is multiple, and each electronic tag currently shows respective identity；A variety of articles and multiple
The electronic tag is arranged on supporter；Described device includes:
Image collection module, for obtaining comprising there are many target images of the article and multiple electronic tags；
Position detecting module, for detecting the location information of each article and each electronic tag in the target image
Location information；
Identification module, for identification in the target image Item Information of each article and each electronic tag identity
Mark；
Matching module, for according to the location information and Item Information of each article and the position of each electronic tag
Information and identity determine the pairing relationship between each article and each electronic tag.
12. the pair system of a kind of article and electronic tag, which is characterized in that the system comprises: image collecting device, processing
Device and storage device；
Described image acquisition device, for acquiring target image；
Computer program is stored on the storage device, the computer program is executed when being run by the processor as weighed
Benefit requires 1 to 10 described in any item methods.
13. a kind of computer readable storage medium, computer program, feature are stored on the computer readable storage medium
The step of being, the described in any item methods of the claims 1 to 10 executed when the computer program is run by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811084413.7A CN109271935A (en) | 2018-09-17 | 2018-09-17 | The matching method of article and electronic tag, apparatus and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811084413.7A CN109271935A (en) | 2018-09-17 | 2018-09-17 | The matching method of article and electronic tag, apparatus and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109271935A true CN109271935A (en) | 2019-01-25 |
Family
ID=65189625
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811084413.7A Pending CN109271935A (en) | 2018-09-17 | 2018-09-17 | The matching method of article and electronic tag, apparatus and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109271935A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110674902A (en) * | 2019-09-29 | 2020-01-10 | 京东方科技集团股份有限公司 | Method and device for updating content of electronic tag |
| CN110930585A (en) * | 2019-12-06 | 2020-03-27 | 创新奇智(成都)科技有限公司 | Method and system for assisting in identifying commodities by using image tags |
| CN111159314A (en) * | 2019-12-31 | 2020-05-15 | 合肥美的智能科技有限公司 | Electronic tag association method and device, electronic equipment and storage medium |
| CN111695646A (en) * | 2019-03-11 | 2020-09-22 | 北京京东尚科信息技术有限公司 | Automatic article delivery method and device |
| CN112085783A (en) * | 2019-06-12 | 2020-12-15 | 浙江汉朔电子科技有限公司 | Electronic price tag position detection device and method |
| CN112395918A (en) * | 2019-08-16 | 2021-02-23 | 浙江汉朔电子科技有限公司 | Goods shelf identification method, device and system |
| CN112862532A (en) * | 2021-02-10 | 2021-05-28 | 深兰科技（上海）有限公司 | Display control method and related device for electronic price tags |
| CN112906848A (en) * | 2021-03-29 | 2021-06-04 | 上海华兴数字科技有限公司 | Operation metering system and method |
| CN113255435A (en) * | 2021-04-09 | 2021-08-13 | 浙江大华技术股份有限公司 | Article monitoring method and device, computer equipment and storage medium |
| WO2021196836A1 (en) * | 2020-03-30 | 2021-10-07 | 北京沃东天骏信息技术有限公司 | Method and apparatus for positioning express parcel |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102930264A (en) * | 2012-09-29 | 2013-02-13 | 李炳华 | System and method for acquiring and analyzing commodity display information based on image identification technology |
| CN104866849A (en) * | 2015-04-30 | 2015-08-26 | 天津大学 | Food nutrition label identification method based on mobile terminal |
| CN104899820A (en) * | 2014-03-11 | 2015-09-09 | 腾讯科技（北京）有限公司 | Method, system and device for adding tag to image |
| CN107895181A (en) * | 2017-11-28 | 2018-04-10 | 北京旷视科技有限公司 | The control method of electronic tag, apparatus and system |
| CN108334912A (en) * | 2017-01-19 | 2018-07-27 | 浙江汉朔电子科技有限公司 | Article display aided management system |
| CN108416412A (en) * | 2018-01-23 | 2018-08-17 | 浙江瀚镪自动化设备股份有限公司 | A kind of logistics compound key recognition methods based on multitask deep learning |
-
2018
- 2018-09-17 CN CN201811084413.7A patent/CN109271935A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102930264A (en) * | 2012-09-29 | 2013-02-13 | 李炳华 | System and method for acquiring and analyzing commodity display information based on image identification technology |
| CN104899820A (en) * | 2014-03-11 | 2015-09-09 | 腾讯科技（北京）有限公司 | Method, system and device for adding tag to image |
| CN104866849A (en) * | 2015-04-30 | 2015-08-26 | 天津大学 | Food nutrition label identification method based on mobile terminal |
| CN108334912A (en) * | 2017-01-19 | 2018-07-27 | 浙江汉朔电子科技有限公司 | Article display aided management system |
| CN107895181A (en) * | 2017-11-28 | 2018-04-10 | 北京旷视科技有限公司 | The control method of electronic tag, apparatus and system |
| CN108416412A (en) * | 2018-01-23 | 2018-08-17 | 浙江瀚镪自动化设备股份有限公司 | A kind of logistics compound key recognition methods based on multitask deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 刘浩等: "《物流信息技术》", 30 April 2007 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111695646A (en) * | 2019-03-11 | 2020-09-22 | 北京京东尚科信息技术有限公司 | Automatic article delivery method and device |
| CN112085783A (en) * | 2019-06-12 | 2020-12-15 | 浙江汉朔电子科技有限公司 | Electronic price tag position detection device and method |
| CN112395918A (en) * | 2019-08-16 | 2021-02-23 | 浙江汉朔电子科技有限公司 | Goods shelf identification method, device and system |
| CN112395918B (en) * | 2019-08-16 | 2024-03-01 | 汉朔科技股份有限公司 | Goods shelf identification method, device and system |
| CN110674902A (en) * | 2019-09-29 | 2020-01-10 | 京东方科技集团股份有限公司 | Method and device for updating content of electronic tag |
| CN110930585A (en) * | 2019-12-06 | 2020-03-27 | 创新奇智(成都)科技有限公司 | Method and system for assisting in identifying commodities by using image tags |
| CN110930585B (en) * | 2019-12-06 | 2022-04-19 | 创新奇智(浙江)科技有限公司 | Method and system for assisting in identifying commodities by using image tags |
| CN111159314A (en) * | 2019-12-31 | 2020-05-15 | 合肥美的智能科技有限公司 | Electronic tag association method and device, electronic equipment and storage medium |
| WO2021196836A1 (en) * | 2020-03-30 | 2021-10-07 | 北京沃东天骏信息技术有限公司 | Method and apparatus for positioning express parcel |
| CN112862532B (en) * | 2021-02-10 | 2023-11-24 | 深兰智能科技研究院(宁波)有限公司 | Display control method and related device for electronic price tag |
| CN112862532A (en) * | 2021-02-10 | 2021-05-28 | 深兰科技（上海）有限公司 | Display control method and related device for electronic price tags |
| CN112906848A (en) * | 2021-03-29 | 2021-06-04 | 上海华兴数字科技有限公司 | Operation metering system and method |
| CN113255435A (en) * | 2021-04-09 | 2021-08-13 | 浙江大华技术股份有限公司 | Article monitoring method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109271935A (en) | The matching method of article and electronic tag, apparatus and system | |
| CN108416403B (en) | Method, system, equipment and storage medium for automatically associating commodity with label | |
| US11151427B2 (en) | Method and apparatus for checkout based on image identification technique of convolutional neural network | |
| US10540551B2 (en) | Generation of two-dimensional and three-dimensional images of items for visual recognition in checkout apparatus | |
| CN108364005A (en) | Automatic identifying method, system, equipment and the storage medium of price tag | |
| CN104794519B (en) | A kind of cloud identification system and cloud discrimination method | |
| CN108647553A (en) | Rapid expansion method, system, equipment and the storage medium of model training image | |
| CN110175590A (en) | A kind of commodity recognition method and device | |
| CN109784323A (en) | Method, apparatus, electronic equipment and the computer storage medium of image recognition | |
| CN106469285B (en) | Method and system for positioning article and computer readable recording medium | |
| CN109934093B (en) | Method for identifying goods on shelf, computer readable medium and identification system | |
| CN108345912A (en) | Commodity rapid settlement system based on RGBD information and deep learning | |
| Tonioni et al. | Product recognition in store shelves as a sub-graph isomorphism problem | |
| CN107918767B (en) | Object detection method, device, electronic equipment and computer-readable medium | |
| CN104792398A (en) | Integrated scale based on fruit and vegetable identification | |
| CN111325492B (en) | Supply chain optimization method and system | |
| WO2019192231A1 (en) | Product positioning method and device, apparatus, and storage medium | |
| WO2020134102A1 (en) | Article recognition method and device, vending system, and storage medium | |
| JP2019125144A (en) | Merchandise information management program, method and device, and merchandise management program, method and device | |
| CN112100425A (en) | Label labeling method and device based on artificial intelligence, electronic equipment and medium | |
| CN109242060A (en) | New restocking product fast searching method, system, equipment and storage medium | |
| CN109840503A (en) | A kind of method and device of determining information | |
| Kim et al. | Discovering characteristic landmarks on ancient coins using convolutional networks | |
| WO2021179138A1 (en) | Method and system for analyzing commodities on supermarket shelf | |
| CN113935774A (en) | Image processing method, image processing device, electronic equipment and computer storage 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190125 |
|
| RJ01 | Rejection of invention patent application after publication |