CN109767238A - Product discriminating method, device, equipment and storage medium based on image recognition - Google Patents
Product discriminating method, device, equipment and storage medium based on image recognition Download PDFInfo
- Publication number
- CN109767238A CN109767238A CN201811537629.4A CN201811537629A CN109767238A CN 109767238 A CN109767238 A CN 109767238A CN 201811537629 A CN201811537629 A CN 201811537629A CN 109767238 A CN109767238 A CN 109767238A
- Authority
- CN
- China
- Prior art keywords
- product
- parameters
- image
- product parameters
- image recognition
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000003860 storage Methods 0.000 title claims abstract description 20
- 238000004806 packaging method and process Methods 0.000 claims abstract description 69
- 238000004519 manufacturing process Methods 0.000 claims description 55
- 239000004615 ingredient Substances 0.000 claims description 28
- 238000001514 detection method Methods 0.000 claims description 24
- 239000000203 mixture Substances 0.000 claims description 19
- 238000012795 verification Methods 0.000 claims description 15
- 238000012216 screening Methods 0.000 claims description 12
- 238000012019 product validation Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 230000008676 import Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 2
- 239000000047 product Substances 0.000 description 421
- 239000008267 milk Substances 0.000 description 14
- 210000004080 milk Anatomy 0.000 description 14
- 235000013336 milk Nutrition 0.000 description 14
- 239000000843 powder Substances 0.000 description 13
- 238000012790 confirmation Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 239000006227 byproduct Substances 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012856 packing Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000005802 health problem Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000002417 nutraceutical Substances 0.000 description 1
- 235000021436 nutraceutical agent Nutrition 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a kind of product discriminating method, device, equipment and storage medium based on image recognition, which comprises the Packaging image for obtaining the product of picture pick-up device shooting passes through image recognition model and identifies the first product parameters in Packaging image；When pre-stored second product parameters mismatch in the first product parameters and database, prompting product is personation.The present invention screens that its is true and false and be prompted to user by carrying out image recognition to product packaging and after obtaining product information, allows user to buy safe and secure product, greatly improves user experience.
Description
Technical field
The present invention relates to field of image recognition, and in particular to a kind of product discriminating method based on image recognition, is set device
Standby and storage medium.
Background technique
Currently, being obtained increasingly with the improvement of people's living standards, the food health of children with the development of science and technology
More concern, the but currently, health problem of foodstuff product (such as milk powder) is generally existing, for example, on the market milk powder the problem of
It emerges one after another.Milk powder is a kind of popular nutraceutical, his quality directly affects the body of people especially infant
Body health.Therefore, the quality problems of milk powder be one be worth many people pay close attention to the problem of, appearance regular for existing milk powder
Quality problems, many brand manufacturers all develop the quality instrument of detection milk powder, but detect by quality instrument equal
The milk powder for needing to destroy milk outer packing taking-up the inside is detected, and it is true and false can not to identify milk powder in the case where outer Packing Sound；
And ordinary consumer generally can not carry out detecting this mode using quality instrument, but can according to the traditional method, with the naked eye
The mode that observation and memory look back the up-to-standard products bought before this is judged, or knows news or other trails again
After message, arbitrarily think that all milk powder poor qualities in certain brands or certain places of production are (even up-to-standard at its
In the case where), above-mentioned judgment mode subjective consciousness is too strong, has no foundation for the judgement of the quality problems of milk powder, can not be accurate
Determine the quality problems of milk powder.
Therefore, currently it is badly in need of that a kind of operation is convenient, it can the foodstuffs product quality problem such as accurate comprehensive identification milk powder
Product discriminating method.
Summary of the invention
The embodiment of the present invention provides a kind of product discriminating method, device, equipment and storage medium based on image recognition, this
Invention can screen that its is true and false and be prompted to user by carrying out image recognition to product packaging and after obtaining product information,
Allow user to buy safe and secure product, greatly improves user experience.
A kind of product discriminating method based on image recognition, comprising:
The Packaging image of the product of picture pick-up device shooting is obtained, and the Packaging image is inputted into preset image recognition mould
Type identifies the first product parameters in the Packaging image by described image identification model；
Detect whether first product parameters match with the second product parameters pre-stored in database；
When pre-stored second product parameters mismatch in first product parameters and the database, institute is prompted
Product is stated as personation.
A kind of product screening device based on image recognition, comprising:
Module is obtained, the Packaging image of the product for obtaining picture pick-up device shooting, and the Packaging image is inputted in advance
If image recognition model, the first product parameters in the Packaging image are identified by described image identification model；
First detection module, for detect first product parameters whether with the second product pre-stored in database
Parameter matching；
First cue module is joined for the second product pre-stored in first product parameters and the database
When number mismatches, prompt the product for personation.
A kind of computer equipment, including memory, processor and storage are in the memory and can be in the processing
The computer-readable instruction run on device, the processor are realized above-mentioned based on image knowledge when executing the computer-readable instruction
The step of other product discriminating method.
A kind of computer readable storage medium, the computer-readable recording medium storage have computer-readable instruction, institute
State the step of above-mentioned product discriminating method based on image recognition is realized when computer-readable instruction is executed by processor.
Product discriminating method, device, equipment and storage medium provided by the invention based on image recognition, by product
Packaging image carry out image recognition, to extract the first product parameters in the Packaging image；Simultaneously in the database in advance
All the second product parameters relevant to product can collecting are stored, in first product parameters and database in advance
When second product parameters of storage mismatch, prompt the product for personation.The present invention can be by carrying out figure to product packaging
It as identifying and after obtaining product information, screens that its is true and false and be prompted to user, user is allowed to buy safe and secure production
Product greatly improve user experience.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without creative efforts, can also obtain according to these attached drawings
Obtain other attached drawings.
Fig. 1 is the application environment schematic diagram of the product discriminating method in one embodiment of the invention based on image recognition；
Fig. 2 is the flow chart of the product discriminating method in one embodiment of the invention based on image recognition；
Fig. 3 is the flow chart of the product discriminating method in another embodiment of the present invention based on image recognition；
Fig. 4 is the flow chart of the step S20 of the product discriminating method in one embodiment of the invention based on image recognition；
Fig. 5 is the flow chart of the step S20 of the product discriminating method in another embodiment of the present invention based on image recognition；
Fig. 6 is the functional block diagram of the product screening device in one embodiment of the invention based on image recognition；
Fig. 7 is the functional block diagram of the product screening device in another embodiment of the present invention based on image recognition；
Fig. 8 is the principle frame of the first detection module of the product screening device in one embodiment of the invention based on image recognition
Figure；
Fig. 9 is the principle of the first detection module of the product screening device in another embodiment of the present invention based on image recognition
Block diagram；
Figure 10 is the schematic diagram of computer equipment in one embodiment of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
Product discriminating method provided by the invention based on image recognition, can by product (such as milk powder) pack into
Row image recognition and after obtaining product information, screens that its is true and false and be prompted to user, user is bought safe and secure
Product, greatly improve user experience.The present invention can be applicable in the application environment such as Fig. 1, wherein client (computer
Equipment) it is communicated by network with server.Wherein, client (computer equipment) includes but is not limited to for various personal meters
Calculation machine, laptop, smart phone, tablet computer, camera and portable wearable device.Server can be with independent
The server cluster of server either multiple servers composition is realized.
In one embodiment, it as shown in Fig. 2, providing a kind of product discriminating method based on image recognition, answers in this way
It is illustrated for the server in Fig. 1, includes the following steps S10-S30:
S10 obtains the Packaging image of the product of picture pick-up device shooting, and the Packaging image is inputted preset image and is known
Other model identifies the first product parameters in the Packaging image by described image identification model；
Wherein, the picture pick-up device can be the picture pick-up device built in client (such as mobile terminal), can also for
The picture pick-up device of the client communication connection；After the product that user confirms that it is screened, this can be shot
The Packaging image of product, that is, extracting the packet of the product by the picture pick-up device recorded video and from the video of recording
Image is filled, or directly shoots the Packaging image；Server receives the Packaging image that the picture pick-up device takes, can
To be identified by described image identification model to the first product parameters in the Packaging image, and will be obtained after identification
First product parameters storage in the database.
Understandably, first product parameters refer to product brand, the product for including in the Packaging image of the product
Suitable Age section, the product place of production, product formula etc. parameter type are one such or a variety of.In first product parameters
In, product brand, product Suitable Age section, the product place of production, product formula etc. are all uniquely corresponding to the product.
Wherein, the training process of described image identification model is as follows: the different product packaging samples of preset quantity are obtained,
Correspond to same first product parameters in each product packaging sample, it can be by the inclusion of the image recognition model of initial parameter
The product packaging sample is identified, and is obtained from the first product parameters identified in the product packaging sample and the production
Product pack the whole degree of deviation of corresponding first product parameters of sample, and it is preset to judge whether the whole degree of deviation is greater than
Deviation threshold；If the entirety degree of deviation is greater than deviation threshold, the initial parameter of the first image identification model is carried out
Adjustment, and return execution it is described by adjusting the described image identification model after initial parameter to the product packaging sample into
Row identification, until the whole degree of deviation is less than or equal to deviation threshold；If the entirety degree of deviation is less than or equal to deviation threshold
Value then prompts the training of described image identification model to complete.
In the present embodiment one side, first product parameters of described image identification model identification are the Packaging image
In text, first product parameters identified by described image identification model in the Packaging image, comprising:
The text in the Packaging image is identified by image recognition model, by preset keyword with identified
The text matched, will with the writing record of the Keywords matching be and the keyword it is associated first produce
Product parameter.That is, firstly the need of the text (including number or character etc.) identified in the Packaging image, and again by the text
After being converted to first product parameters, product can be screened according to first product parameters.During the text may be
Text, English, German etc..
Be previously stored in the database with each associated keyword of first product parameters, for example, it is described first produce
Product parameter is product formula, and the keyword can be set as the keywords such as formula, ingredient, as long as at this point, scheming in the packaging
It recognizes and is formulated after this keyword as in, the word content that can recognize this section is stored as first product parameters
In product formula.
Understandably, in one embodiment, first product parameters can be to be arranged in the Packaging image to prevent
Puppet indicates, includes anti-counterfeiting information (such as security code) in the anti-false sign, at this point, in the present embodiment in a first aspect, described
The first product parameters in the Packaging image are identified by image recognition model, comprising: pass through image recognition model extraction institute
The anti-counterfeiting information in anti-false sign is stated, the anti-counterfeiting information includes the address of security code and verifying website.
It is described the first product parameters in the Packaging image are identified by image recognition model after, comprising: obtain institute
The address for stating the security code for including in anti-counterfeiting information and verifying website jumps to and the address information of the verifying website automatically
Website is verified, after in verifying website described in the security code automatic input, obtains the verifying letter of verifying website feedback
Breath；The verification information is prompted to user；It is true and the Product Validation is personation that the verification information, which includes the Product Validation,
Two kinds.
In the second aspect of the present embodiment, first product identified by image recognition model in the Packaging image
Parameter, comprising: by the anti-counterfeiting information in anti-false sign described in image recognition model extraction, the anti-counterfeiting information includes security code
With anti-fake hotline number；It is described the first product parameters in the Packaging image are identified by image recognition model after,
It include: to obtain the security code and anti-fake hotline number for including in the anti-counterfeiting information, and anti-fake hot line described in automatic dialing
The security code when needing typing security code in the verification process of the anti-fake hotline, is converted to language by telephone number
Automatic input after sound obtains the verification information of the anti-fake hotline feedback；The verification information is prompted to user；It is described
Verification information include the Product Validation be true and the Product Validation be personation two kinds.
It understandably, can also be the anti-false signs such as bar code or two dimensional code from the anti-false sign, described first produces
The product place of production in product parameter can be scanned from the bar code or the anti-false signs such as two dimensional code on Packaging image
Out, for example, the formulation standard of the place of production information in bar code is by International Article Numbering Association's unified organizational system, such as: 489 represent
Hong Kong, 94 represent New Zealand, 84 represent Spain, 76 represent Switzerland, 80-83 represents Italy, 87 represent Holland, 880 representatives
South Korea etc.；Therefore, as long as scanning bar code or the corresponding number of identification bar code, that is, may recognize that the product place of production.Institute
State whether detection first product parameters match with the second product parameters pre-stored in database, it can be according to following step
Described in rapid S20.
In the present embodiment another aspect, first product parameters of described image identification model identification are packaging figure
Picture profile and color as in, it is described to identify that the first product in the Packaging image is joined by described image identification model
Number, comprising:
By the picture profile and color in Packaging image described in image recognition model extraction, and determine the picture profile
Whether matched with color with preset brand representative image, it, will be with the brand generation when being matched with the brand representative image
The associated product brand of table image is set as the product brand in first product parameters.That is, depositing in advance in the database
Contain with the associated brand representative image of each product brand, the brand representative image can for its advertising words with uniqueness or
The picture of mouthpiece can also be the picture etc. of its registered trademark.
Understandably, it as long as picture profile and color in the Packaging image are matched with the brand representative image, represents
The product belongs to the product brand.When the picture profile and color and the brand representative image mismatch, illustrate simultaneously
The product brand is not looked for, the product brand can be obtained by the step S101-102 at this time, if still can not obtain
To product brand, user can be manually entered or choose the product brand, if the product brand does not store in the database
Its corresponding information can be by the first product parameters of the product and its during screening after completing to the examination of the product
The all or part of data generated are stored into the database.
S20, detects whether first product parameters match with the second product parameters pre-stored in database；
Wherein, second product parameters refer to it is pre-stored can search current all product brands (including
Sub-brand name under product brand) and the product brand each parameter, for example, product Suitable Age section, the product place of production, product are matched
Side, each home made article disabling ingredient (including the toxic component mentioned in defective product information) and limitation use the limitation hundred of ingredient
Divide ratio etc..Understandably, in the present embodiment, second product parameters include but is not limited to all first product ginsengs
Parameter type in number；For example, first product parameters refer to the product brand for including in the Packaging image of the product, produce
The parameter types such as product Suitable Age section, the product place of production, product formula are one such or a variety of, in the particular embodiment, institute
Stating in the second product parameters can also can further include on this basis only comprising the parameter type in first product parameters
Other parameter types (such as each home made article disabling ingredient (and limitation use ingredient limitation percentage etc.), that is, described
Parameter type in second product parameters can be set according to demand.
In one embodiment, first product parameters include product brand, the product place of production, as shown in figure 4, the step
S20 includes:
S201 is transferred join with associated second product of the product brand in first product parameters in the database
Number；That is, since the first product parameters described in the step S10 include product brand, first according to the product
With associated second product parameters of the product brand in brand called data library, compared for subsequent.
S202 is detected in second product parameters transferred and is produced with the presence or absence of the product in first product parameters
Ground；
That is, due to all product places of production that the product brand has been stored in advance in database, as long as detection
Whether there are the product parameters in first product parameters in second product parameters transferred, that is, can determine whether the production
Whether product brand has the product place of production shown on the Packaging image.
S203 confirms first product parameters and institute when there is no the product place of production in first product parameters
Pre-stored second product parameters in database are stated to mismatch.
That is, representing institute there is no when the product place of production shown on the Packaging image in the confirmation product brand
Pre-stored second product parameters in the first product parameters and the database are stated to mismatch.At this point, since the packaging is schemed
As the upper product place of production is not belonging to one in each product place of production of the product brand, which may be fake and forged production
Product, it is therefore desirable to prompt user in the step S30.
In one embodiment, first product parameters further include product formula, as shown in figure 4, the step S202 it
After include:
S204 is detected in second product parameters and is somebody's turn to do when there are the product place of production in first product parameters
The associated product formula in the product place of production, if consistent with the product formula in first product parameters；
It is produced that is, the product place of production in confirmation first product parameters belongs to the corresponding product of the product brand
After one in ground, need to judge at this time production described in the product place of production product formula whether on the Packaging image
The product formula of (namely in first product parameters) is consistent.Further, in second product parameters with the product place of production
Associated product formula when consistent with the product formula in first product parameters, prompts the product qualified.
Preferably, the S204 includes:
Detect whether the product formula in first product parameters includes to preset the product disabling ingredient of country, or detection
Whether the product limitation for the default country for including in the product formula in first product parameters is more than limit using ingredient
Determine percentage；In this step, it is necessary first to whether detect in the ingredient in the product formula comprising default country's disabling
Harmful substance (namely product disabling ingredient or product limitation use ingredient), to prompt user.Wherein, the default country
Be set by the user, for example, can be set as user is currently located country, also may be set to user feel standard more reasonably other
Country, at this point it is possible to use standard (product disabling ingredient or the limit of ingredient with the product disabling ingredient or limitation for presetting national state
System includes in the standard using the restriction percentage of ingredient) it is whether qualified to judge the product.
Comprising the default country product disable ingredient, or comprising the default country product limit use at
When whether dividing more than its restriction percentage, prompt the product harmful；That is, in the product comprising presetting having for national defined
When evil substance, needs the situation being prompted to user, whether continue to buy the product with for reference.
Do not include the default country product disabling ingredient or comprising the default country product limitation use
When ingredient is less than it and limits percentage, detect in second product parameters with the associated product formula in the product place of production,
It is whether consistent with the product formula in first product parameters.That is, passing through inspection when not including harmful substance in the product
Whether the product brand produced the product formula in first product parameters in the product place of production, to determine described
Whether one product parameters match with the second product parameters pre-stored in the database, and then judge whether the product is false
Emit product.
S205, when inconsistent with product formula in first product parameters, confirm first product parameters with
Pre-stored second product parameters mismatch in the database.
The various countries of requirement due to to(for) product formula is different, and the product formula in each place of production may be different.
Similarly, if the product of place of production production is exported to country variant, may the product of same brand and model can be directed to country variant
Requirement production different product formula product, therefore, the place of production in second product parameters may be associated with
One or more product formulas.At this point it is possible to confirming the product brand in all product formulas in the product place of production not
When comprising product formula in first product parameters, confirms and be stored in advance in first product parameters and the database
The second product parameters mismatch, at this point, the product may be counterfeit and shoddy goods, it is therefore desirable to be mentioned in the step S30
Show user.
In one embodiment, first product parameters further include product importing country, as shown in figure 5, the step
Include: after S204
S206 is obtained in first product parameters when consistent with the product formula in first product parameters
The product composition requirement of product importing country；That is, in the present embodiment, if product is import, also needing to confirm the time
Whether the product composition requirement of product importing country (i.e. the country of the import product) is met.
Whether S207, the product formula detected in first product parameters meet the product composition requirement；At this point, will
The product composition of product formula and the product importing country in first product parameters requires to compare, described in judgement
Whether the product formula in the first product parameters is within the scope of the product composition required standard, if so, determining to meet
The product composition requirement；Otherwise determine not meeting the product composition requirement.
S208 prompts the product to meet the product importing country import and wants when meeting the product composition requirement
It asks；The prompt may be displayed in the current display interface of client.
S209, when not meeting the product composition requirement, prompt the product do not meet the product importing country into
Mouth requires.The prompt may be displayed in the current display interface of client.
S30 is mentioned when pre-stored second product parameters mismatch in first product parameters and the database
Show the product for personation.
That is, determining pre-stored second product in first product parameters and the database in above-mentioned steps
When parameter mismatches, illustrate that the product may be personation, it will be appreciated that ground can also prompt the vacation of product in one embodiment
Emit probability is how many.
The personation probability can be calculated by preset personation calculative rule of the probability, the personation probability calculation
Rule can by first on the internet grab news, each product brand official website statement etc. information, obtain it later
In fake products data, and then judge the matching degree of the above-mentioned unmatched product and the fake products data, with
Determine that it is palmed off probability and illustrates that never A produced product to the brand in some place of production for example, certain brand product has delivered statement,
And in above-mentioned steps S203, detect with first product parameters unmatched in second product parameters, include
The product place of production be just exactly the brand mentioned never produced product in above-mentioned statement place of production A, at this point it is possible to obtain one
It is as follows that item palms off calculative rule of the probability: if the corresponding product place of production of the product brand is A, the personation probability of the product is
100%.For another example, authoritative media report X brand Y batch products are personation, but the product brand official does not confirm, at this time
It can be concluded that a personation calculative rule of the probability is as follows: if the corresponding product batches of X product brand are Y, the vacation of the product
Emitting probability is 80%；The personation probability can be prompted to user according to the personation calculative rule of the probability at this time.
In one embodiment, as shown in figure 3, further comprising the steps of S40-S60 after the step S20:
S40, when first product parameters are matched with the second product parameters pre-stored in the database, detection
Whether first product parameters meet user preferences；
Wherein, the user preferences include user preferences (user be manually entered or the user that collected bought before this
) brand, the place of production, user the product Suitable Age section (number of segment and age due to the setting of each product brand that currently set
The contrast relationship of section is all inconsistent, and therefore, the product Suitable Age section, which refers to, converts the number of segment that each product brand is set
For the data after unified age bracket) etc. it is one such or a variety of.In this embodiment, first product parameters with
When pre-stored second product parameters match in the database, that is, obtain and preset user preferences content (user
Sets itself or Server Default choose one of above-mentioned user preferences or a variety of), and by above-mentioned user preferences content and institute
It states first product parameters that product extracts in the step S10 to be compared, whether (namely institute is matched with both confirmations
State whether the first product parameters meet user preferences).
S50, when meeting user preferences, by the Products Show to user；Admire at this point, user can trust to buy
The product.
S60 prompts the product and user preferences discrepancy when not meeting user preferences.For example, if brand not
Symbol, then it is XX that emphasis, which prompts current brand, preferably, other parts for meeting user preferences can also synchronize and be prompted to use
Family.
Above-described embodiment can greatly improve user experience according to user preferences recommended products.In one embodiment, institute
State method further include: receive the product information of user's input, and transfer in the database and the product information associated second
Product parameters；The product information refers to the contents such as product brand, product Suitable Age section, the product place of production, product formula.
In one embodiment, as shown in fig. 6, providing a kind of product screening device based on image recognition, image should be based on
The product discriminating method based on image recognition corresponds in the product screening device and above-described embodiment of identification.It is described to be based on figure
As the product screening device of identification includes:
Module 11 is obtained, the Packaging image of the product for obtaining picture pick-up device shooting, and the Packaging image is inputted
Preset image recognition model identifies the first product parameters in the Packaging image by described image identification model；
First detection module 12, for detect first product parameters whether in database it is pre-stored second produce
The matching of product parameter；
First cue module 13, for pre-stored second product in first product parameters and the database
When parameter mismatches, prompt the product for personation.
In one embodiment, as shown in fig. 7, described device further include:
Second detection module 14, for pre-stored second product in first product parameters and the database
When parameter matches, detect whether first product parameters meet user preferences；
Recommending module 15, for when meeting user preferences, by the Products Show to user；
Second cue module 16, for when not meeting user preferences, prompting the product and user preferences not to meet it
Place.
In one embodiment, the acquisition module 11 is also used to: by image recognition model in the Packaging image
Text is identified, preset keyword is matched with the identified text, by the institute with the Keywords matching
Stating writing record is and associated first product parameters of the keyword；
In one embodiment, the acquisition module 11 is also used to: by Packaging image described in image recognition model extraction
Picture profile and color, and determine whether the picture profile and color match with preset brand representative image, with institute
When stating the matching of brand representative image, first product parameters will be set as with the associated product brand of brand representative image
In product brand.In one embodiment, first product parameters are the anti-false sign being arranged in the Packaging image；
In one embodiment, the acquisition module 11 is also used to: by anti-false sign described in image recognition model extraction
Anti-counterfeiting information；
Described device is also used to: the address of the security code for including in the anti-counterfeiting information and verifying website is obtained, it is automatic to jump
The verifying website with the address information of the verifying website is gone to, by it in verifying website described in the security code automatic input
Afterwards, the verification information of verifying website feedback is obtained；Or obtain the security code and anti-fake hot line for including in the anti-counterfeiting information
Telephone number, and anti-fake hotline number described in automatic dialing, need to record in the verification process of the anti-fake hotline
When entering security code, the security code is converted into automatic input after voice, obtains the verifying of the anti-fake hotline feedback
Information；The verification information is prompted to user, it is true and the Product Validation is false that the verification information, which includes the Product Validation,
Emit two kinds.
In one embodiment, first product parameters include product brand, the product place of production；As shown in figure 8, described first
Detection module 12 includes:
Unit 121 is transferred, is associated with for transferring in the database with the product brand in first product parameters
The second product parameters；
First detection unit 122, for detecting in second product parameters transferred with the presence or absence of first product
The product place of production in parameter；
First confirmation unit 123, for when there is no the product place of production in first product parameters, confirming described the
Pre-stored second product parameters mismatch in one product parameters and the database.
In one embodiment, first product parameters further include product formula；As shown in figure 9, the first detection mould
Block 12 further include:
Second detection unit 124, for detecting described second when there are the product place of production in first product parameters
In product parameters with the associated product formula in the product place of production, if it is consistent with the product formula in first product parameters；
Second confirmation unit 125, for when inconsistent with product formula in first product parameters, described in confirmation
Pre-stored second product parameters mismatch in first product parameters and the database；
In one embodiment, the second detection unit 124 is also used to: the product in detection first product parameters is matched
Whether the product comprising default country disables the institute for including in the product formula in ingredient, or detection first product parameters for side
Whether state the product limitation for presetting country using ingredient is more than restriction percentage；Comprising the default country product disabling at
Point, or comprising the default country product limitation using ingredient whether be more than its restriction percentage when, prompt the product
It is harmful；Do not include the default country product disabling ingredient or comprising the default country product limit use ingredient
When being less than it and limiting percentage, detect in second product parameters with the associated product formula in the product place of production, if
It is consistent with the product formula in first product parameters.
In one embodiment, first product parameters further include product importing country；As shown in figure 9, first inspection
Survey module 12 also further include:
Acquiring unit 126 is produced for when consistent with the product formula in first product parameters, obtaining described first
The product composition requirement of product importing country in product parameter；
Third detection unit 127, for detecting whether the product formula in first product parameters meets the product
Component requirements；
First prompt unit 128, for prompting the product to meet the product when meeting the product composition requirement
Importing country import requirement；
Second prompt unit 129, it is described for when not meeting the product composition requirement, prompting the product not meet
Product importing country import requirement.
Specific restriction about the product screening device based on image recognition may refer to know above for based on image
The restriction of other product discriminating method, details are not described herein.Each mould in the above-mentioned product screening device based on image recognition
Block can be realized fully or partially through software, hardware and combinations thereof.Above-mentioned each module can be embedded in the form of hardware or independence
In processor in computer equipment, it can also be stored in a software form in the memory in computer equipment, in order to
Processor, which calls, executes the corresponding operation of the above modules.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 10.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium be stored with operating system, computer-readable instruction and
Database.The built-in storage provides ring for the operation of operating system and computer-readable instruction in non-volatile memory medium
Border.To realize a kind of product discriminating method based on image recognition when the computer-readable instruction is executed by processor.
In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory
And the computer-readable instruction that can be run on a processor, processor perform the steps of when executing computer-readable instruction
The Packaging image of the product of picture pick-up device shooting is obtained, and the Packaging image is inputted into preset image recognition mould
Type identifies the first product parameters in the Packaging image by described image identification model；
Detect whether first product parameters match with the second product parameters pre-stored in database；
When pre-stored second product parameters mismatch in first product parameters and the database, institute is prompted
Product is stated as personation.
In one embodiment, a kind of computer readable storage medium is provided, computer-readable instruction is stored thereon with,
It is performed the steps of when computer-readable instruction is executed by processor
The Packaging image of the product of picture pick-up device shooting is obtained, and the Packaging image is inputted into preset image recognition mould
Type identifies the first product parameters in the Packaging image by described image identification model；
Detect whether first product parameters match with the second product parameters pre-stored in database；
When pre-stored second product parameters mismatch in first product parameters and the database, institute is prompted
Product is stated as personation.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer-readable instruction, it is non-volatile that the computer-readable instruction can be stored in one
Property computer-readable storage medium in, the computer-readable instruction is when being executed, it may include as above-mentioned each method embodiment
Process.Wherein, to memory, storage, database or other media used in each embodiment provided by the present invention
Any reference may each comprise non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory
(ROM), programming ROM (PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.It is volatile
Property memory may include random access memory (RAM) or external cache.By way of illustration and not limitation, RAM
It is available in many forms, such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram
(DDRSDRAM), enhanced SDRAM (ESDRAM), synchronization link DRAM (SLDRAM), the direct RAM of memory bus (RDRAM),
Direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit or module division progress for example, in practical application, can according to need and by above-mentioned function distribution by difference
Functional unit or module complete, i.e., the internal structure of described device is divided into different functional unit or module, with complete
All or part of function described above.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of product discriminating method based on image recognition characterized by comprising
The Packaging image of the product of picture pick-up device shooting is obtained, and the Packaging image is inputted into preset image recognition model,
The first product parameters in the Packaging image are identified by described image identification model；
Detect whether first product parameters match with the second product parameters pre-stored in database；
When pre-stored second product parameters mismatch in first product parameters and the database, the production is prompted
Product are personation.
2. the product discriminating method based on image recognition as described in claim 1, which is characterized in that described to pass through described image
Identification model identifies the first product parameters in the Packaging image, comprising:
The text in the Packaging image is identified by image recognition model, by preset keyword and identified institute
It states text to be matched, will be to join with associated first product of the keyword with the writing record of the Keywords matching
Number；Or
By the picture profile and color in Packaging image described in image recognition model extraction, and determine the picture profile and face
Whether color matches with preset brand representative image, when matching with the brand representative image, will represent and scheme with the brand
As associated product brand is set as the product brand in first product parameters.
3. the product based on image recognition discriminates method for distinguishing as described in claim 1, which is characterized in that first product parameters
For the anti-false sign being arranged in the Packaging image；
First product parameters identified by described image identification model in the Packaging image, comprising:
Pass through the anti-counterfeiting information in anti-false sign described in image recognition model extraction；
After whether detection first product parameters match with the second product parameters pre-stored in database, also wrap
It includes:
The address for obtaining the security code for including in the anti-counterfeiting information and verifying website jumps to and the verifying website automatically
It is anti-to obtain the verifying website after in verifying website described in the security code automatic input for the verifying website of address information
The verification information of feedback；Or the security code and anti-fake hotline number for including in the anti-counterfeiting information are obtained, and automatic dialing institute
Anti-fake hotline number is stated, it, will be described anti-fake when needing typing security code in the verification process of the anti-fake hotline
Code is converted to automatic input after voice, obtains the verification information of the anti-fake hotline feedback；
The verification information is prompted to user, it is true and the Product Validation is personation that the verification information, which includes the Product Validation,
Two kinds.
4. the product discriminating method based on image recognition as described in claim 1, which is characterized in that first product parameters
Including product brand, the product place of production；
Whether detection first product parameters match with the second product parameters pre-stored in database, comprising:
It transfers in the database and associated second product parameters of the product brand in first product parameters；
It detects in second product parameters transferred with the presence or absence of the product place of production in first product parameters；
When there is no the product place of production in first product parameters, confirm in first product parameters and the database
Pre-stored second product parameters mismatch.
5. the product discriminating method based on image recognition as claimed in claim 4, which is characterized in that first product parameters
It further include product formula；
After whether there is the product place of production in first product parameters in second product parameters that the detection is transferred,
Include:
When there are the product place of production in first product parameters, detects in second product parameters and closed with the product place of production
The product formula of connection, if consistent with the product formula in first product parameters；
When inconsistent with product formula in first product parameters, first product parameters and the database are confirmed
In pre-stored second product parameters mismatch.
6. the product discriminating method based on image recognition as claimed in claim 5, which is characterized in that the detection described second
In product parameters with the associated product formula in the product place of production, if it is consistent with the product formula in first product parameters,
Include:
Detect whether the product formula in first product parameters includes default national product disabling ingredient, or described in detection
Whether the product limitation for the default country for including in the product formula in the first product parameters is more than restriction hundred using ingredient
Divide ratio；
Disable ingredient in the product comprising the default country, or comprising the product limitation of the default country using ingredient be
It is not no when being more than that it limits percentage, prompt the product harmful；
Do not include the default country product disabling ingredient or comprising the default country product limit use ingredient
When being less than it and limiting percentage, detect in second product parameters with the associated product formula in the product place of production, if
It is consistent with the product formula in first product parameters.
7. the product discriminating method based on image recognition as claimed in claim 5, which is characterized in that first product parameters
It further include product importing country；
It is described when there are the product place of production in first product parameters, detect in second product parameters and produced with the product
The associated product formula in ground, if after consistent with the product formula in first product parameters, further includes:
When consistent with the product formula in first product parameters, the product importer in first product parameters is obtained
The product composition requirement of family；
Detect whether the product formula in first product parameters meets the product composition requirement；
When meeting the product composition requirement, the product is prompted to meet the product importing country import requirement；
When not meeting the product composition requirement, the product is prompted not meet the product importing country import requirement.
8. a kind of product screening device based on image recognition characterized by comprising
Module is obtained, the Packaging image of the product for obtaining picture pick-up device shooting, and Packaging image input is preset
Image recognition model identifies the first product parameters in the Packaging image by described image identification model；
First detection module, for detect first product parameters whether with the second product parameters pre-stored in database
Matching；
First cue module, for pre-stored second product parameters not to be in first product parameters and the database
When matching, prompt the product for personation.
9. a kind of computer equipment, including memory, processor and storage are in the memory and can be in the processor
The computer-readable instruction of upper operation, which is characterized in that the processor is realized when executing the computer-readable instruction as weighed
Benefit requires the step of product discriminating method described in 1 to 7 any one based on image recognition.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer-readable instruction, special
Sign is, realizes when the computer-readable instruction is executed by processor and is known as described in any one of claim 1 to 7 based on image
The step of other product discriminating method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811537629.4A CN109767238A (en) | 2018-12-15 | 2018-12-15 | Product discriminating method, device, equipment and storage medium based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811537629.4A CN109767238A (en) | 2018-12-15 | 2018-12-15 | Product discriminating method, device, equipment and storage medium based on image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109767238A true CN109767238A (en) | 2019-05-17 |
Family
ID=66450645
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811537629.4A Pending CN109767238A (en) | 2018-12-15 | 2018-12-15 | Product discriminating method, device, equipment and storage medium based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109767238A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111815335A (en) * | 2020-06-11 | 2020-10-23 | 兰州集智信息技术有限公司 | Service platform and method for judging authenticity of product |
| CN112161936A (en) * | 2020-09-29 | 2021-01-01 | 杭州海康威视数字技术股份有限公司 | Optical inspection device for cigarette packets |
| CN112270664A (en) * | 2020-04-16 | 2021-01-26 | 上海扩博智能技术有限公司 | Transparent packaging product detection method, system, equipment and storage medium |
| CN112329673A (en) * | 2020-11-12 | 2021-02-05 | 北京文通科技有限公司 | Anti-counterfeiting fiber identification method, anti-counterfeiting identification device and storage medium |
| CN112508362A (en) * | 2020-11-24 | 2021-03-16 | 江苏省质量和标准化研究院 | Product export information processing method and device, electronic equipment and storage medium |
| CN113420677A (en) * | 2021-06-25 | 2021-09-21 | 联仁健康医疗大数据科技股份有限公司 | Method and device for determining reasonable image, electronic equipment and storage medium |
| CN113780074A (en) * | 2021-08-04 | 2021-12-10 | 五邑大学 | Method and device for detecting quality of wrapping paper and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070228166A1 (en) * | 2006-04-04 | 2007-10-04 | Ho Chung Lui | System for detecting couterfeiting products using camera |
| CN104537541A (en) * | 2014-12-23 | 2015-04-22 | 广东欧珀移动通信有限公司 | Method and device for verifying security code |
| CN104899752A (en) * | 2015-06-19 | 2015-09-09 | 北京慧眼天下科技有限公司 | Product false proof method and system |
| CN108830622A (en) * | 2018-06-30 | 2018-11-16 | 合肥浪金防伪科技有限公司 | A kind of novel commodity cloud anti-counterfeiting system method |
| CN108985285A (en) * | 2018-02-07 | 2018-12-11 | 广州集创佳禾知识产权运营有限公司 | A kind of commodity patent acquisition methods and system based on machine recognition |
-
2018
- 2018-12-15 CN CN201811537629.4A patent/CN109767238A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070228166A1 (en) * | 2006-04-04 | 2007-10-04 | Ho Chung Lui | System for detecting couterfeiting products using camera |
| CN104537541A (en) * | 2014-12-23 | 2015-04-22 | 广东欧珀移动通信有限公司 | Method and device for verifying security code |
| CN104899752A (en) * | 2015-06-19 | 2015-09-09 | 北京慧眼天下科技有限公司 | Product false proof method and system |
| CN108985285A (en) * | 2018-02-07 | 2018-12-11 | 广州集创佳禾知识产权运营有限公司 | A kind of commodity patent acquisition methods and system based on machine recognition |
| CN108830622A (en) * | 2018-06-30 | 2018-11-16 | 合肥浪金防伪科技有限公司 | A kind of novel commodity cloud anti-counterfeiting system method |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112270664A (en) * | 2020-04-16 | 2021-01-26 | 上海扩博智能技术有限公司 | Transparent packaging product detection method, system, equipment and storage medium |
| CN111815335A (en) * | 2020-06-11 | 2020-10-23 | 兰州集智信息技术有限公司 | Service platform and method for judging authenticity of product |
| CN112161936A (en) * | 2020-09-29 | 2021-01-01 | 杭州海康威视数字技术股份有限公司 | Optical inspection device for cigarette packets |
| CN112161936B (en) * | 2020-09-29 | 2024-05-24 | 杭州海康威视数字技术股份有限公司 | Optical detection device for cigarette packets |
| CN112329673A (en) * | 2020-11-12 | 2021-02-05 | 北京文通科技有限公司 | Anti-counterfeiting fiber identification method, anti-counterfeiting identification device and storage medium |
| CN112329673B (en) * | 2020-11-12 | 2024-05-17 | 北京文通科技有限公司 | Anti-fake fiber identification method, anti-fake identification method, device and storage medium |
| CN112508362A (en) * | 2020-11-24 | 2021-03-16 | 江苏省质量和标准化研究院 | Product export information processing method and device, electronic equipment and storage medium |
| CN112508362B (en) * | 2020-11-24 | 2024-04-23 | 江苏省质量和标准化研究院 | Product outlet information processing method and device, electronic equipment and storage medium |
| CN113420677A (en) * | 2021-06-25 | 2021-09-21 | 联仁健康医疗大数据科技股份有限公司 | Method and device for determining reasonable image, electronic equipment and storage medium |
| CN113420677B (en) * | 2021-06-25 | 2024-06-11 | 联仁健康医疗大数据科技股份有限公司 | Method, device, electronic equipment and storage medium for determining reasonable image |
| CN113780074A (en) * | 2021-08-04 | 2021-12-10 | 五邑大学 | Method and device for detecting quality of wrapping paper and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109767238A (en) | Product discriminating method, device, equipment and storage medium based on image recognition | |
| US20200195688A1 (en) | Systems And Methods For Takedown Of Counterfeit Websites | |
| US9165071B2 (en) | Method and system for indicating a validity rating of an entity | |
| CN106681973B (en) | Method and device for automatically filling browser forms in test | |
| CN108846676A (en) | Biological characteristic assistant payment method, device, computer equipment and storage medium | |
| US10354302B2 (en) | Methods and devices for providing fashion advice | |
| CN108810642B (en) | Bullet screen display method and device and electronic equipment | |
| Le et al. | How consumers perceive authenticity in restaurants: A study of online reviews | |
| CN109089172B (en) | Bullet screen display method and device and electronic equipment | |
| US11568460B2 (en) | Device, method, and program for commercial product reliability evaluation based on image comparison | |
| CN109872233A (en) | Contract signing method, apparatus, computer equipment and storage medium | |
| CN105450664B (en) | A kind of information processing method and terminal | |
| WO2019017178A1 (en) | Method and apparatus for dynamically identifying a user of an account for posting images | |
| CN112399129A (en) | Online video communication method and device based on small program and computer equipment | |
| CN106919821A (en) | User authentication method and device | |
| CN112085511A (en) | Anti-counterfeiting tracing code generation method, anti-counterfeiting tracing method and related system | |
| CN105100132B (en) | The method and system of terminal device, identification terminal equipment | |
| Sun et al. | Global prevalence of heated tobacco product use, 2015–22: A systematic review and meta‐analysis | |
| CN105260900A (en) | Product unique identification anti-counterfeiting method and device | |
| US20170076176A1 (en) | Method and system for displaying item related information in video streaming | |
| CN107609487B (en) | User head portrait generation method and device | |
| CN100407860C (en) | Movable terminal verifying method | |
| US20110231333A1 (en) | Registration method and registration system of network service system | |
| US20240096051A1 (en) | Determining whether a questionable video of a prominent individual is real or fake | |
| US20170039627A1 (en) | Cigar Band Recognition Interface |
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 |