CN108133207A - The image of auxiliary items closes the method, apparatus and electronic equipment of rule - Google Patents
The image of auxiliary items closes the method, apparatus and electronic equipment of rule Download PDFInfo
- Publication number
- CN108133207A CN108133207A CN201711192125.9A CN201711192125A CN108133207A CN 108133207 A CN108133207 A CN 108133207A CN 201711192125 A CN201711192125 A CN 201711192125A CN 108133207 A CN108133207 A CN 108133207A
- Authority
- CN
- China
- Prior art keywords
- article
- image
- rule
- character area
- visual field
- 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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/243—Aligning, centring, orientation detection or correction of the image by compensating for image skew or non-uniform image deformations
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Studio Devices (AREA)
Abstract
The embodiment of the present application discloses a kind of method, apparatus of the image conjunction rule of auxiliary items and electronic equipment, this method include：Detect the compliance of the image of article；If detecting, the image of article does not conform to rule, and auxiliary user makes the image of the article close rule.
Description
Technical field
This application involves electronic information process field, the image for relating more specifically to auxiliary items closes the method, apparatus of rule
And electronic equipment.
Background technology
User is provided using optical character identification (Optical Character Recognition, OCR) technology at present
Certificate photograph handled, so as to extract and identify the method for the user information on certificate photograph, the bodies such as finance in internet
Part certification scene has obtained commonly used.
In reality scene, the camera function shooting certificate photograph of the operating system of user's using terminal equipment, entirely
The gatherer process of certificate photograph gives user to complete completely, but since user shoots the various (example of environment complexity of certificate photograph
Such as, different lighting angles and intensity) and user take pictures that horizontal height is different (for example, can focus to target object, to take pictures
When hand whether have shake), cause the quality of certificate photograph that user takes also irregular, without conform to quality requirements (or
Person, which says, does not conform to rule) certificate photograph subsequent OCR algorithm recognition accuracy can be caused to reduce even fail, reduce user identity and recognize
The success rate of card influences user experience.
Therefore, the method that a kind of image of auxiliary items of demand closes rule, to overcome above-mentioned technical problem.
Invention content
A kind of image for being designed to provide auxiliary items of the application closes the method, apparatus and electronic equipment of rule, can
When the image of article does not conform to rule, auxiliary user makes the image of article close rule, avoids the knowledge of image caused by not conforming to the image of rule
Other accuracy rate is low, authenticating user identification success rate is low and the problem of poor user experience.
In order to solve the above technical problems, what the embodiment of the present application was realized in：
In a first aspect, the method that the image for providing a kind of auxiliary items closes rule, including：
Detect the compliance of the image of article；
If detecting, the image of article does not conform to rule, and auxiliary user makes the image of the article close rule.
Second aspect, the image for providing a kind of auxiliary items close the device of rule, including：
First processing units detect the compliance of the image of article；
Second processing unit, if detecting, the image of article does not conform to rule, and auxiliary user makes the image of the article close rule.
The third aspect provides a kind of electronic equipment, including：
Processor；And
The memory of storage computer executable instructions is arranged to, the executable instruction is when executed using described
Processor performs following operate：
Detect the compliance of the image of article；
If detecting, the image of article does not conform to rule, and auxiliary user makes the image of the article close rule.
Fourth aspect, provides a kind of computer-readable medium, the computer-readable medium storage one or more program,
One or more of programs by the electronic equipment including multiple application programs when being performed so that the electronic equipment perform with
Lower operation：
Detect the compliance of the image of article；
If detecting, the image of article does not conform to rule, and auxiliary user makes the image of the article close rule.
By above technical solution provided by the embodiments of the present application as it can be seen that the conjunction of the image of the embodiment of the present application detection article is advised
Property, and when the image for detecting article does not conform to rule, auxiliary user makes the image of article close rule.The method of the embodiment of the present application,
It can avoid that recognition accuracy caused by not conforming to the image of rule is low, authenticating user identification success rate is low and poor user experience is asked
Topic.
Description of the drawings
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or it will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments described in application, for those of ordinary skill in the art, in the premise of not making the creative labor property
Under, it can also be obtained according to these attached drawings other attached drawings.
Fig. 1 is the signal map flow chart for the method that rule are closed according to the image of the auxiliary items of one embodiment of the application.
Fig. 2 is the schematic diagram according to the image template of one embodiment of the application.
Fig. 3 is the schematic diagram according to the posture of the image of the correction article of one embodiment of the application.
Fig. 4 is the schematic flow chart for the method that rule are closed according to the image of the auxiliary items of one specific embodiment of the application.
Fig. 5 is the structure diagram according to the electronic equipment of the embodiment of the present application.
Fig. 6 is the structure diagram for the device that rule are closed according to the image of the auxiliary items of the embodiment of the present application.
Specific embodiment
In order to make those skilled in the art better understand the technical solutions in the application, below in conjunction with the application reality
The attached drawing in example is applied, the technical solution in the embodiment of the present application is clearly and completely described, it is clear that described implementation
Example is merely a part but not all of the embodiments of the present application.Based on the embodiment in the application, this field is common
Technical staff's all other embodiments obtained without creative efforts should all belong to the application protection
Range.
In the embodiment of the present application, electronic equipment can be terminal device, and terminal device both includes wireless signal receiver
Equipment, only have the equipment of the wireless signal receiver of non-emissive ability, and the equipment including receiving and emitting hardware,
With the reception that two-way communication on bidirectional communication link, can be performed and the equipment of transmitting hardware.This equipment can include：
Honeycomb or other communication equipments, with single line display or multi-line display or without multi-line display honeycomb or
Other communication equipments；PCS Personal Communications System (Personal Communicat1ns Service, PCS), can with combine voice,
Data processing, fax and/or communication ability；Personal digital assistant (Personal Digital Assistant, PDA),
It can include radio frequency receiver, pager, the Internet/intranet access, web browser, notepad, calendar and/or the whole world
Alignment system (Global Posit1ning System, GPS) receiver；Conventional laptop and/or palmtop computer or its
His equipment, has and/or the conventional laptop including radio frequency receiver and/or palmtop computer or other equipment.Here
Used terminal device can be portable, can transport, in the vehicles (aviation, sea-freight and/or land) or
Person is suitable for and/or is configured in local runtime and/or with distribution form, operates in any other position in the earth and/or space
Put operation.Terminal device used herein above can also be communication terminal, access terminals, music/video playback terminal, such as can
To be PDA, mobile internet device (Mobile Internet Device, MID) and/or there is music/video playing function
Mobile phone.
In the embodiment of the present application, article can be certificate, and certificate refers to the certificate and text for proving identity, experience etc.
Part, certificate includes but not limited to identity document class certificate, property proves class certificate, certificate class certificate, legal documents class certificate, ticket
According to class certificate, guarantee statement class certificate.Wherein, identity document class certificate includes but not limited to resident identification card, household register, shield
According to, Hongkong and Macro's pass, marriage certificate, social security card and medical insurance card, property proves that class certificate includes but not limited to bank card, bankbook, deposits
List and borrowing agreements.Certificate class certificate includes but not limited to diploma, degree's diploma and honorary certificate.Legal documents class certificate includes
But it is not limited to labour contract, rent a house contract and insurance policy.Bill class certificate includes but not limited to invoice.Guarantee statement class certificate includes
But it is not limited to guarantee card.
Fig. 1 is the flow chart for the method that rule are closed according to the image of the auxiliary items of one embodiment of the application.The side of Fig. 1
The device that method 100 is closed rule by the image of auxiliary items performs.As illustrated in FIG. 1, at S102, the conjunction of the image of article is detected
Rule property.
It is understood that detecting the compliance of the image of article at S102, substantially detecting the image of article is
It is no to close rule.
At S104, if detecting, the image of article does not conform to rule, and auxiliary user makes the image of the article close rule.
It should be noted that in S104, auxiliary user makes the image of article close the image conjunction that rule can be auxiliary items
The acquisition parameters (for example, light filling intensity) of the image of the device adjust automatically article of rule come cause the image of article close rule or
User is assisted to can also be the image conjunction rule of article and provides a user feedback information, user is instructed to perform phase by feedback information
The operation answered is so that the image of article closes rule.
Optionally, if being detected at S102, the image of article closes rule, at S104, obtains the letter carried on the image of article
Breath, the information carried on the image of article is compared with the information in target data source, according to comparison as a result, determining object
The authenticity of product.
As an example it is assumed that article is identity card, if then being detected at S102, the image of article closes rule, at S104
The letter carried on identification (Optical Character Recognition, OCR) algorithm acquisition identity card is accorded with using optical identification
Breath, such as：The information such as name, identification card number, home address and the term of validity, then by the information extracted and AUTHORITATIVE DATA source
(for example, public security online information of keeping on file) is compared, if information comparison success, illustrate identity card be it is true, otherwise
It is false to illustrate the identity card.
As can be seen that the scheme of method 100, is detected, and detecting article to whether the image of article closes rule
When image does not conform to rule, the image that can assist user makes article closes rule, so as to ensure subsequently to being carried on the image of article
Information recognition success rate.And when the image for detecting article closes rule, it can directly acquire on the image of article and carry
Information, do not need to user's click keys and take pictures, reduce the complexity of user's operation, improve the usage experience of user.
Optionally, as one embodiment, the compliance of the image of article is detected in S102, including：Detecting article is
No complete be presented on is shot in the visual field.
Specifically, in some embodiments, as illustrated in FIG. 2, by taking article is identity card as an example, in the image of identity card
Image template in gatherer process is provided or is known as guiding interface, identity card is put into the corresponding region of image template by guiding user
It takes pictures, so as to which the posture for ensureing the certificate of shooting is in the main true, such as left figure in Fig. 2 (including size and angle of inclination)
Shown, when shooting identity card front, user's " head portrait is put into frame, and adjusts light " is prompted, in shooting identity
During the back side of card, user's " national emblem is put into frame, and adjusts light " is prompted, user can put according to the prompting of image template
Identity card is put, ensures that the posture of identity card is correct.In this case, whether the image for detecting article is corresponding in image template
In region, if detecting the image of article in the corresponding region of image template, it is determined that the shooting that is presented on that article is completed regards
Yezhong.Due to the use of image template, it can so that user is apparent from article needs which type of position ability be placed into
It obtains closing the image of rule, improves the experience of user.
Specifically, in further embodiments, whether detection article is completely presented in the shooting visual field and can specifically lead to
In the following manner is crossed to realize：Determine the long side of article and the ratio of short side；If it is determined that the ratio is pre-set ratio, and article
The distance at the edge of angle point and target image is greater than or equal to pre-determined distance, it is determined that article is completely presented on the shooting visual field
In.
Optionally, as an example, determine that the long side of article and the ratio of short side include：Determine the seat of the angle point of article
Cursor position according to the position coordinates of the angle point of article, determines the long side of article and the ratio of short side.In the angle point for determining article
It can be determined during coordinate position according to Corner character algorithm.
It should be noted that the angle point of article is it can be appreciated that the key point of article, generally for general certificate
Speech, the key point of certificate is exactly four angle points of certificate.The algorithm based on deep learning Recurrent networks may be used to training number
Training pattern is obtained according to being trained, i.e. Corner character algorithm.For certificate, the form of training data carries card for one
Position (x, the y) coordinate of 4 angle points of picture and certificate of the image of part in figure, the loss function used in the training process
It can be Euclidean distance loss function (Eculidean Loss).In actual use, an image with certificate is given
Input picture, training pattern can predict the position coordinates of 4 angle points of certificate.
Specifically, in some embodiments, after 4 angular coordinates of certificate are predicted, it is long certificate can be calculated
Side and the ratio of short side, if the ratio is approached with effective rate, and the coordinate of 4 angle points is not close to the edge of input picture,
Then it is believed that certificate is complete, i.e., certificate is completely presented in the shooting visual field.
Further, in some embodiments, if it is determined that the posture of the image of article is not targeted attitude, by article
The posture correction of image is targeted attitude.As illustrated in FIG. 3, in left figure (before posture correction), according to the 4 of certificate angle points
Coordinate determine that the posture of certificate is not the vertical and horizontal plumbness in front, then be right figure by the image flame detection of certificate (after posture correction)
Shown state.For example, after the coordinate position of 4 angle points of certificate is determined, transformation (Affine is penetrated by anti-
Transform it is) the vertical and horizontal plumbness in front by the correction of certificate posture, would be even more beneficial to the text on the image to certificate in this way
Block domain is positioned and is identified.
Optionally, at S102, the compliance for detecting the image of article further includes：Detection shooting whether there is institute in the visual field
State article.It is shot when detecting there are during the article in the visual field, whether detection article is completely presented in the shooting visual field.
That is before whether detection article is completely presented in the shooting visual field, need to carry out article existence inspection.
Optionally, as an example, the inspection to article existence is realized using 2 sorting algorithms based on deep learning
It looks into.So-called 2 classification has referred to 2 classifications, this 2 classifications are respectively：There are article and there is no articles, wherein existence
Corresponding product are that article section there is a situation where or completely be present in the shooting visual field, are not have completely there is no article is corresponding
Article is present in the situation in the shooting visual field.2 classifications are trained respectively by a collection of training sample in the training process
Obtain 2 depth of assortment learning models.In actual use, if predicting the shooting visual field by 2 depth of assortment learning models
The middle probability there are article is more than certain threshold value, then it is assumed that there are article in the shooting visual field, otherwise it is assumed that in the shooting visual field not
There are articles.If it is determined that in the shooting visual field, there is no articles, then can return to user certain mistake or prompt message, example
User can such as be prompted：It does not detect XX certificates, camera is please aligned to your XX certificates.
Optionally, at S102, the compliance for detecting the image of article further includes：Detect whether article is target class object
Product.When it is target class article to detect article, whether detection article is completely presented in the shooting visual field.That is,
In S102, can directly detect article whether be completely presented on shooting the visual field in, can also first detect shooting the visual field in whether
There are the articles, and when determining to shoot there are during the article in the visual field, whether detection article is completely presented on the shooting visual field
In, it can also be with the presence or absence of the article in the first detection shooting visual field, if there are the article, detectable substances in the shooting visual field
Whether product are target class article, if detecting target class article during article, detect whether article is completely presented on shooting
In the visual field.
Optionally, as an example, it uses and realizes article whether for target based on the multi-classification algorithm of deep learning
The detection of article.By taking article is certificate as an example, each classification is a kind of certificate, is corresponding with a batch based on the certificate
Training picture sample.Using the picture sample (assuming that having N classes certificate) of all these certificates, and it is aided with a batch without any certificate
Picture sample, to train N+1 depth of assortment learning models.In actual use, judged by N+1 depth of assortment learning model
Classification belonging to certificate, it is to be understood that, can when predicting the classification belonging to certificate using N+1 depth of assortment learning model
The probability that a certificate belongs to each classification can be predicted, the classification of maximum probability is determined as to the classification belonging to certificate.If N
The probability that+1 depth of assortment learning model prediction certificate belongs to each classification is below a threshold value, then it is assumed that without card in the shooting visual field
Part.
Further, if it is not target classification that the classification belonging to certificate is predicted using N+1 depth of assortment learning models,
When i.e. certificate is not target class certificate, user can be given and prompted accordingly, by taking target class certificate is identity card as an example, if inspection
It is not identity card to measure certificate, and user can be prompted " to detect other certificates of non-identity card, can only identify identity card, please incite somebody to action
Identity card is put into the shooting visual field ".If it is determined that user can then be prompted " not detect that XX is demonstrate,proved without certificate in the shooting visual field
Camera is please directed at your XX certificates by part ".It is understood that based on the multi-classification algorithm of deep learning to the classification of article
The result being identified has complementation with above-mentioned 2 sorting algorithms based on deep learning to the result of the inspection of the existence of article
Property, the false recognition rate of the identification to the existence of article can be reduced by different models, improves user experience.
Optionally, at S102, the compliance for detecting the image of article includes：Whether the quality of detection target image meets
Preset quality requirement, target image include the image of the article.It is understood that the scheme at S102, in detectable substance
During the compliance of the image of product, whether the quality that can only detect target image meets preset quality requirement, can also first detect
Whether article is completely presented in the shooting visual field, if article is completely presented in the shooting visual field, further detects target
Whether the quality of image meets preset quality requirement.
Optionally, in some embodiments, before whether the quality for determining target image meets preset quality requirement, also
Including：Whether the posture for determining the image of article is targeted attitude, however, it is determined that the posture of the image of the article is not the mesh
Posture is marked, is the targeted attitude by the posture correction of the image of the article.The side of the posture of the image of specific determining article
The method of the image of method and correction article is identical with method as described herein above, and details are not described herein.
Optionally, in some embodiments, determine whether the quality of target image meets preset quality requirement, including：Really
The clarity of the character area of the image of earnest product；According to the clarity of the character area and default clarity, target is determined
Whether the quality of image meets preset quality requirement.For example, default clarity is characterized with default clarity score value, according to based on returning
Return the deep learning model of network, determine the clarity score value of character area.If clarity score value is greater than or equal to default clear
Clear degree score value, it is determined that the quality of target image meets preset quality requirement.If the clarity score value of character area is less than default
Clarity score value, then using the information carried on optical identification symbol OCR algorithm identification character area, if word cannot be identified successfully
The information carried on region, it is determined that the quality of target image is unsatisfactory for preset quality requirement.
Further, if the information that is carried on character area cannot be identified successfully, at S104, auxiliary user makes institute
The image for stating article closes rule, including：The first information is shown to user, and the first information improves word for user to be prompted to perform
The operation of the clarity in region.Corresponding, user can adjust focal length or article during shooting when seeing the first information
Placement location etc. so that the clarity of the character area on the image of article is met the requirements.
It optionally, may by article for for certificate, the character area on the image of certificate is navigated to using OCR algorithm
Multiple character areas can be generated, the clarity of each character area is carried out using the deep learning model based on Recurrent networks
Marking if the marking value of some character area is less than certain threshold value, then is identified the region with OCR algorithm, and seeing is
It is no to get rational result, if it is possible to get rational result, then it is assumed that the clarity of the character area meets
It is required that it if cannot get rational as a result, illustrating that the image of certificate does not conform to rule, the image that assisting user makes certificate closes
Rule, for example, returning to user response operation prompt information, which for example can be that " image is excessively fuzzy, please protect
Demonstrate,prove image clearly ".
Optionally, in further embodiments, determine whether the quality of target image meets preset quality requirement, including：
Determine that the depth of exposure of the character area on the image of article belongs to the text on the image of over-exposed the first probability or article
The reflective degree in block domain belongs to reflective the second excessive probability；According to the first probability or the second probability, target image is determined
Whether quality meets preset quality requirement.That is, determining whether the quality of target image meets preset quality and require to include
The detection of excessive or strong reflective phenomenon is exposed to target image.
Specifically, in some embodiments, according to based on two classification deep learning model, determine first probability or
Second probability.It corrects to obtain positive form for example, the image of article first is carried out posture using method as described herein above
Article, the character area on the image of article is then navigated to using OCR algorithm, multiple character areas may be generated.It
The deep learning model based on two classification is used afterwards to predict that each character area belongs to over-exposed the first probability or prediction
Each character area belongs to second probability of reflective excessively (strong in other words reflective), if the first probability or the second probability are less than one
Fixed threshold value, then the depth of exposure in comment region be not belonging to over-exposed or reflective degree be not belonging to it is reflective excessively, into
And illustrate the quality of target image and meet preset quality requirement.If the first probability or the second probability are more than certain threshold value,
Using the information carried on OCR algorithm identification character area, if the information carried on character area cannot be identified successfully, it is determined that
The quality of target image is unsatisfactory for preset quality requirement.
Further, if the information that is carried on character area cannot be identified successfully, at S104, auxiliary user makes institute
The image for stating article closes rule, including：The second information is shown to user, and second information reduces article for user to be prompted to perform
The depth of exposure of image or the operation of reflective degree.Corresponding, user can adjust article when seeing the second information
Placement location so that the depth of exposure of the character area on the image of article or reflective degree are met the requirements.
In above-mentioned all embodiments, positioning is carried out to the character area on the image of article, deep learning list may be used
Secondary detector (Single Shot MultiBox Detector, SSD) frame is realized, to the information carried on character area
It is identified and the full line Text region based on shot and long term memory network (Long Short-Term Memory, LSTM) may be used
Frame is realized.But the embodiment of the present application is not calculated the identification of information carried on character area localization method and character area
Method is defined.
Fig. 4 is the schematic flow for the method that rule are closed according to the image of the auxiliary items of one specific embodiment of the application
Figure, the method 200 of Fig. 4 are closed the device execution of rule by the image of auxiliary items, are described so that article is certificate as an example in Fig. 4,
A kind of only example.As illustrated in FIG. 4, at S202, certificate existence inspection.
2 sorting algorithms described in the method 100 may be used to check certificate existence.
At S204, if confirming in S202, there are certificate, type of credential identifications.
Likewise it is possible to using the class of the prediction certificate of the multi-classification algorithm based on deep learning described in the method 100
Type.
At S206, if the type that certificate is identified at S204 is target type, certificate integrity checking is carried out.
Specifically, when carrying out certificate integrity checking, the side using image template described in method 100 may be used
Method examination of document integrality or using the complete of the coordinate position examination of document by certificate angle point described in method 100
Property.
At S208, if the type that certificate is determined at S206 is target type, certificate posture correction is carried out.
It is understood that in S208, so-called certificate posture correction essence is the posture progress to the image of certificate
Correction, the method specifically corrected can penetrate transformation after the coordinate position of 4 angle points of certificate is determined by anti-
The correction of certificate posture is the vertical and horizontal plumbness in front by (Affine Transform).
At S210, word intelligibility evaluation.
Specifically, at least one character area on the image of certificate is navigated to using OCR algorithm, is then based on returning net
The deep learning model of network is assessed come the clarity to character area, and the method specifically assessed can refer in method 100
Associated description, details are not described herein.
At S212, depth of exposure or reflective degree detecting.
Specifically, the deep learning model that can give two classification comes the depth of exposure to each character area or reflective journey
Degree is detected, and the method specifically detected can refer to the associated description in method 100, and details are not described herein.
At S214, literal line detection.
At S216, literal line identification.
Optionally, using the literal line on the image using OCR recognizers detection certificate and to being carried in literal line
Information be identified.
At S218, document information checking.
It is understood that the document information checking at S218 is the information that will be identified at S216 by AUTHORITATIVE DATA source
It is compared, if compared successfully, it may be said that the authenticity of clear proof part.
Optionally, at S218, document information checking is carried out using word fuzzy matching algorithm.
Further, if document information checking can successfully prompt user to veritify successfully in S218, if certificate is believed
Breath veritifies failure, then user is prompted to veritify failure, certificate is not true certificate.
Therefore, the method for method 200, can ensure collected certificate image it is true, it is complete, there is high quality, energy
Good input enough is provided for subsequent authentication, the operation provided to the user and Product Experience.
The method that rule are closed according to the image of the auxiliary items of the embodiment of the present application is described in detail above in association with Fig. 1 to Fig. 4.
Below in conjunction with Fig. 5 detailed descriptions according to the electronic equipment of the embodiment of the present application.With reference to figure 5, in hardware view, electronic equipment packet
Processor is included, optionally, including internal bus, network interface, memory.Wherein, memory may include memory, such as at a high speed
Random access memory (Random-Access Memory, RAM), it is also possible to further include nonvolatile memory (non-
Volatile memory), for example, at least 1 magnetic disk storage etc..Certainly, which is also possible that other business institutes
The hardware needed.
Processor, network interface and memory can be connected with each other by internal bus, which can be industry
Standard architecture (Industry Standard Architecture, ISA) bus, Peripheral Component Interconnect standard
(Peripheral Component Interconnect, PCI) bus or expanding the industrial standard structure (Extended
Industry Standard Architecture, EISA) bus etc..The bus can be divided into address bus, data/address bus,
Controlling bus etc..For ease of representing, only represented in Fig. 5 with a four-headed arrow, it is not intended that an only bus or one kind
The bus of type.
Memory, for storing program.Specifically, program can include program code, and said program code includes calculating
Machine operational order.Memory can include memory and nonvolatile memory, and provide instruction and data to processor.
Processor reads in corresponding computer program to memory and then is run from nonvolatile memory, in logical layer
The image that auxiliary items are formed on face closes the device of rule.Processor performs the program that memory is stored, and specifically for performing
It operates below：
Detect the compliance of the image of article；
If detecting, the image of article does not conform to rule, and auxiliary user makes the image of the article close rule.
The image of the above-mentioned auxiliary items as disclosed in the application Fig. 1 and embodiment illustrated in fig. 4 closes the side that the device of rule performs
Method can be applied to realize in processor or by processor.Processor may be a kind of IC chip, have signal
Processing capacity.During realization, each step of the above method can by the integrated logic circuit of the hardware in processor or
The instruction of person's software form is completed.Above-mentioned processor can be general processor, including central processing unit (Central
Processing Unit, CPU), network processing unit (Network Processor, NP) etc.；It can also be Digital Signal Processing
Device (Digital Signal Processor, DSP), application-specific integrated circuit (Application Specific Integrated
Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or other can
Programmed logic device, discrete gate or transistor logic, discrete hardware components.It can realize or perform the application implementation
Disclosed each method, step and logic diagram in example.General processor can be that microprocessor or the processor can also
It is any conventional processor etc..The step of method with reference to disclosed in the embodiment of the present application, can be embodied directly in hardware decoding
Processor performs completion or performs completion with the hardware in decoding processor and software module combination.Software module can position
In random access memory, flash memory, read-only memory, programmable read only memory or electrically erasable programmable memory, register
In the storage medium for waiting this fields maturation.The storage medium is located at memory, and processor reads the information in memory, with reference to it
Hardware completes the step of above method.
The electronic equipment can also carry out the method for Fig. 1 and Fig. 4, and realize that the image of auxiliary items closes the device of rule in Fig. 1
With the function of embodiment illustrated in fig. 4, details are not described herein for the embodiment of the present application.
Certainly, other than software realization mode, other realization methods are not precluded, for example patrol in the electronic equipment of the application
Collect mode of device or software and hardware combining etc., that is to say, that the executive agent of following process flow is not limited to each patrol
Collect unit or hardware or logical device.
The embodiment of the present application also proposed a kind of computer readable storage medium, the computer-readable recording medium storage one
A or multiple programs, the one or more program include instruction, which works as is held by the electronic equipment including multiple application programs
During row, method that the electronic equipment can be made to perform Fig. 1 and embodiment illustrated in fig. 4, and specifically for performing following methods：
Detect the compliance of the image of article；
If detecting, the image of article does not conform to rule, and auxiliary user makes the image of the article close rule.
Fig. 6 is the structure diagram that the image of the auxiliary items of one embodiment of the application closes the device of rule.It please refers to
Fig. 6, in a kind of Software Implementation, the image of auxiliary items, which closes the device 600 advised, may include：601 He of first processing units
Second processing unit 602, wherein,
First processing units 601 detect the compliance of the image of article；
Second processing unit 602, if detecting, the image of article does not conform to rule, and auxiliary user closes the image of the article
Rule.
The device of rule is closed according to the image of the auxiliary items of the embodiment of the present application, detects the compliance of the image of article, and
When the image for detecting article does not conform to rule, auxiliary user makes the image of article close rule, and the image for not conforming to rule can be avoided to cause
Recognition accuracy is low, authenticating user identification success rate is low and the problem of poor user experience.
Optionally, as one embodiment, the first processing units 601：
Detect whether the article is completely presented in the shooting visual field.
Optionally, as one embodiment, the first processing units 601：
Whether the quality of detection target image meets preset quality requirement, and the target image includes the figure of the article
Picture.
Optionally, as one embodiment, the first processing units 601：
It detects in the shooting visual field with the presence or absence of the article；
If detecting, there are the articles in the shooting visual field, detect whether the article is completely presented on shooting
In the visual field.
Optionally, as one embodiment, the first processing units 601：
Detect whether the article is target class article；
If it is determined that the article is target class article, then detect whether the article is completely presented on the shooting visual field
In.
Optionally, as one embodiment, the first processing units 601：
The image of the article is detected whether in the corresponding region of image template；
If detect the image of the article in the corresponding region of described image template, it is determined that the article is complete
It is presented in the shooting visual field.
Optionally, as one embodiment, the first processing units 601：
Determine the long side of the article and the ratio of short side；
If it is determined that the ratio is pre-set ratio, and the angle point of the article and the distance at the edge of the target image are big
In or equal to pre-determined distance, it is determined that the article is completely presented in the shooting visual field.
Optionally, as one embodiment, the first processing units 601：
Determine the coordinate position of the angle point of the article；
According to the position coordinates of the angle point of the article, the long side of the article and the ratio of short side are determined.
Optionally, as one embodiment, the quality of the determining target image whether meet preset quality requirement it
Before, the first processing units 601：
Whether the posture for determining the image of the article is targeted attitude；
If it is determined that the posture of the image of the article is not the targeted attitude, the posture of the image of the article is corrected
For the targeted attitude.
Optionally, as one embodiment, the first processing units 601：
Determine the clarity of the character area of the image of the article；
According to the clarity of the character area and default clarity, determine the target image quality whether meet it is pre-
If quality requirement.
Optionally, as one embodiment, the default clarity is characterized with default clarity score value；
Wherein, the first processing units 601：
According to the deep learning model based on Recurrent networks, the clarity score value of the character area is determined.
Optionally, as one embodiment, the first processing units 601：
If the clarity score value is less than the default clarity score value, identified using optical character identification OCR algorithm
The information carried on the character area；
If it cannot successfully identify the information carried on the character area, it is determined that the quality of the target image is unsatisfactory for
Preset quality requirement.
Optionally, as one embodiment, the second processing unit 602：
The first information is shown to user, and the first information is used to that user to be prompted to perform the clear of the raising character area
The operation of degree.
Optionally, as one embodiment, the first processing units 601：
Determine that the depth of exposure of the character area on the image of the article belongs to over-exposed the first probability or described
The reflective degree of character area on the image of article belongs to reflective the second excessive probability；
According to the first probability or second probability, determine whether the quality of the target image meets preset quality and want
It asks.
Optionally, as one embodiment, the first processing units 601：
According to the deep learning model based on two classification, first probability or second probability are determined.
Optionally, as one embodiment, the first processing units 601：
If first probability or second probability are more than predetermined probabilities, the literal field is identified using OCR algorithm
The information carried on domain；
If it cannot successfully identify the information carried on the character area, it is determined that the quality of the target image is unsatisfactory for
Preset quality requirement.
Optionally, as one embodiment, the second processing unit 602：
The second information is shown to user, and second information is used for the exposure that user is prompted to perform the image for reducing the article
The operation of light path degree or reflective degree.
Optionally, as one embodiment, the first processing units 601：
The character area is determined using OCR algorithm.
Optionally, as one embodiment, the first processing units 601：
If detecting, the image of the article closes rule, obtains the information carried on the image of the article；
The information carried on the image of the article is compared with the information in target data source；
According to comparison as a result, determining the authenticity of the article.
Optionally, as one embodiment, the article is certificate.
The device 600 that the image of auxiliary items closes rule can also carry out the method for Fig. 1 and embodiment illustrated in fig. 4, and realize auxiliary
The image of article is helped to close the device advised in Fig. 1 and the function of embodiment illustrated in fig. 4, details are not described herein for the embodiment of the present application.
In short, the foregoing is merely the preferred embodiment of the application, it is not intended to limit the protection domain of the application.
It is all within spirit herein and principle, any modification, equivalent replacement, improvement and so on should be included in the application's
Within protection domain.
System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity,
Or it is realized by having the function of certain product.A kind of typical realization equipment is computer.Specifically, computer for example may be used
Think personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant, media play
It is any in device, navigation equipment, electronic mail equipment, game console, tablet computer, wearable device or these equipment
The combination of equipment.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer-readable instruction, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), fast flash memory bank or other memory techniques, CD-ROM read-only memory (CD-ROM),
Digital versatile disc (DVD) or other optical storages, magnetic tape cassette, the storage of tape magnetic rigid disk or other magnetic storage apparatus
Or any other non-transmission medium, available for storing the information that can be accessed by a computing device.It defines, calculates according to herein
Machine readable medium does not include temporary computer readable media (transitory media), such as data-signal and carrier wave of modulation.
It should also be noted that, term " comprising ", "comprising" or its any other variant are intended to nonexcludability
Comprising so that process, method, commodity or equipment including a series of elements are not only including those elements, but also wrap
Include other elements that are not explicitly listed or further include for this process, method, commodity or equipment it is intrinsic will
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that wanted including described
Also there are other identical elements in the process of element, method, commodity or equipment.
Each embodiment in this specification is described by the way of progressive, identical similar portion between each embodiment
Point just to refer each other, and the highlights of each of the examples are difference from other examples.Especially for system reality
For applying example, since it is substantially similar to embodiment of the method, so description is fairly simple, related part is referring to embodiment of the method
Part explanation.
Claims (23)
1. the method that a kind of image of auxiliary items closes rule, including：
Detect the compliance of the image of article；
If detecting, the image of article does not conform to rule, and auxiliary user makes the image of the article close rule.
2. according to the method described in claim 1, it is described detection article image compliance, including：
Detect whether the article is completely presented in the shooting visual field.
3. method according to claim 1 or 2, the compliance of the image of the detection article, including：
Whether the quality of detection target image meets preset quality requirement, and the target image includes the image of the article.
4. according to the method described in claim 3, the compliance of the image of the detection article, further includes：
It detects in the shooting visual field with the presence or absence of the article；
Wherein, whether the detection article is completely presented in the shooting visual field, including：
If detecting, there are the articles in the shooting visual field, detect whether the article is completely presented on the shooting visual field
In.
5. according to the method described in claim 4, the compliance of the image of the detection article, further includes：
Detect whether the article is target class article；
Wherein, whether the detection article is completely presented in the shooting visual field, including：
If it is determined that the article is target class article, then detect whether the article is completely presented in the shooting visual field.
6. detect whether the article is completely presented in the shooting visual field according to the method described in claim 5, described,
Including：
The image of the article is detected whether in the corresponding region of image template；
If detect the image of the article in the corresponding region of described image template, it is determined that the article is completely presented
In the shooting visual field.
7. detect whether the article is completely presented in the shooting visual field according to the method described in claim 5, described,
Including：
Determine the long side of the article and the ratio of short side；
If it is determined that the ratio is pre-set ratio, and the distance at the edge of the angle point of the article and the target image be more than or
Equal to pre-determined distance, it is determined that the article is completely presented in the shooting visual field.
8. according to the method described in claim 7, it is described determine the article long side and short side ratio, including：
Determine the coordinate position of the angle point of the article；
According to the position coordinates of the angle point of the article, the long side of the article and the ratio of short side are determined.
9. according to the method described in claim 8, the determining target image quality whether meet preset quality requirement it
Before, it further includes：
Whether the posture for determining the image of the article is targeted attitude；
If it is determined that the posture of the image of the article is not the targeted attitude, it is institute by the posture correction of the image of the article
State targeted attitude.
10. according to the method described in claim 9, whether the quality of the determining target image meets preset quality requirement, wrap
It includes：
Determine the clarity of the character area of the image of the article；
According to the clarity of the character area and default clarity, determine whether the quality of the target image meets default matter
Amount requirement.
11. according to the method described in claim 10, the default clarity is characterized with default clarity score value；
Wherein, the clarity of the character area of the image for determining the article, including：
According to the deep learning model based on Recurrent networks, the clarity score value of the character area is determined.
12. according to the method described in claim 10, the clarity according to the character area and default clarity, determine
Whether the quality of the target image meets preset quality requirement, including：
If the clarity score value is less than the default clarity score value, using described in the identification of optical character identification OCR algorithm
The information carried on character area；
If it cannot successfully identify the information carried on the character area, it is determined that the quality of the target image is unsatisfactory for presetting
Quality requirement.
13. according to the method for claim 12, the auxiliary user makes the image of the article close rule, including：
The first information is shown to user, and the first information is used for the clarity that user is prompted to perform the raising character area
Operation.
14. the method according to any one of claim 10 to 13, it is pre- whether the quality of the determining target image meets
If quality requirement further includes：
Determine that the depth of exposure of the character area on the image of the article belongs to the first over-exposed probability or the article
Image on the reflective degree of character area belong to reflective the second excessive probability；
According to the first probability or second probability, determine whether the quality of the target image meets preset quality requirement.
15. according to the method for claim 14, determine that the depth of exposure of the character area on the image of the article belongs to
It is general that the reflective degree of character area on the first over-exposed probability or the image of the article belongs to reflective excessive second
Rate, including：
According to the deep learning model based on two classification, first probability or second probability are determined.
16. it is according to the method for claim 14, described according to first probability or second probability, determine the mesh
Whether the quality of logo image meets preset quality requirement, including：
If first probability or second probability are more than predetermined probabilities, identified on the character area using OCR algorithm
The information of carrying；
If it cannot successfully identify the information carried on the character area, it is determined that the quality of the target image is unsatisfactory for presetting
Quality requirement.
17. according to the method for claim 16, the auxiliary user makes the image of the article close rule, including：
The second information is shown to user, and second information is used for the exposure journey that user is prompted to perform the image for reducing the article
The operation of degree or reflective degree.
18. it according to the method described in claim 10, further includes：
The character area is determined using OCR algorithm.
19. method according to claim 1 or 2, further includes：
If detecting, the image of the article closes rule, obtains the information carried on the image of the article；
The information carried on the image of the article is compared with the information in target data source；
According to comparison as a result, determining the authenticity of the article.
20. method according to claim 1 or 2, the article is certificate.
21. a kind of image of auxiliary items closes the device of rule, including：
First processing units detect the compliance of the image of article；
Second processing unit, if detecting, the image of article does not conform to rule, and auxiliary user makes the image of the article close rule.
22. a kind of electronic equipment, including：
Processor；And
The memory of storage computer executable instructions is arranged to, the executable instruction uses the processing when executed
Device performs following operate：
Detect the compliance of the image of article；
If detecting, the image of article does not conform to rule, and auxiliary user makes the image of the article close rule.
23. a kind of computer-readable medium, the computer-readable medium storage one or more program is one or more of
Program by the electronic equipment including multiple application programs when being performed so that the electronic equipment performs following operate：
Detect the compliance of the image of article；
If detecting, the image of article does not conform to rule, and auxiliary user makes the image of the article close rule.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711192125.9A CN108133207A (en) | 2017-11-24 | 2017-11-24 | The image of auxiliary items closes the method, apparatus and electronic equipment of rule |
| PCT/CN2018/104925 WO2019100814A1 (en) | 2017-11-24 | 2018-09-11 | Method and apparatus for assisting image of article complaying with requirements, and electronic device |
| TW107133136A TWI701603B (en) | 2017-11-24 | 2018-09-20 | Method, device and electronic equipment for image compliance of auxiliary articles |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711192125.9A CN108133207A (en) | 2017-11-24 | 2017-11-24 | The image of auxiliary items closes the method, apparatus and electronic equipment of rule |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108133207A true CN108133207A (en) | 2018-06-08 |
Family
ID=62388927
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711192125.9A Pending CN108133207A (en) | 2017-11-24 | 2017-11-24 | The image of auxiliary items closes the method, apparatus and electronic equipment of rule |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN108133207A (en) |
| TW (1) | TWI701603B (en) |
| WO (1) | WO2019100814A1 (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019100814A1 (en) * | 2017-11-24 | 2019-05-31 | 阿里巴巴集团控股有限公司 | Method and apparatus for assisting image of article complaying with requirements, and electronic device |
| CN110650239A (en) * | 2018-06-26 | 2020-01-03 | 百度在线网络技术（北京）有限公司 | Image processing method, image processing device, computer equipment and storage medium |
| CN110647881A (en) * | 2019-09-19 | 2020-01-03 | 腾讯科技（深圳）有限公司 | Method, device, equipment and storage medium for determining card type corresponding to image |
| CN110889470A (en) * | 2018-09-07 | 2020-03-17 | 京东数字科技控股有限公司 | Method and apparatus for processing image |
| CN111091126A (en) * | 2019-12-12 | 2020-05-01 | 京东数字科技控股有限公司 | Certificate image reflection detection method, device, equipment and storage medium |
| CN111126098A (en) * | 2019-12-24 | 2020-05-08 | 京东数字科技控股有限公司 | Certificate image acquisition method, device, equipment and storage medium |
| CN111178347A (en) * | 2019-11-22 | 2020-05-19 | 京东数字科技控股有限公司 | Method, device and equipment for detecting fuzziness of certificate image and storage medium |
| CN111246113A (en) * | 2020-03-05 | 2020-06-05 | 上海瑾盛通信科技有限公司 | Image processing method, device, equipment and storage medium |
| CN111860475A (en) * | 2019-04-28 | 2020-10-30 | 北京市商汤科技开发有限公司 | Image processing method and device, electronic device and storage medium |
| CN112165571A (en) * | 2020-09-09 | 2021-01-01 | 支付宝实验室(新加坡)有限公司 | Certificate image acquisition method, device and equipment |
| CN113361300A (en) * | 2020-03-04 | 2021-09-07 | 阿里巴巴集团控股有限公司 | Identification information identification method, device, equipment and storage medium |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110516739B (en) * | 2019-08-27 | 2022-12-27 | 创新先进技术有限公司 | Certificate identification method, device and equipment |
| CN110879988B (en) * | 2019-11-22 | 2024-06-11 | 潍坊捷尔网络科技有限公司 | Method, client, device, server and computer readable medium for detecting information compliance |
| CN111553431A (en) * | 2020-04-30 | 2020-08-18 | 上海眼控科技股份有限公司 | Picture definition detection method and device, computer equipment and storage medium |
| CN112785659A (en) * | 2021-01-28 | 2021-05-11 | 特赞（上海）信息科技有限公司 | Enterprise case material picture detection method, device, equipment and storage medium |
| CN115706854A (en) * | 2021-08-06 | 2023-02-17 | 北京小米移动软件有限公司 | Camera control method and device for foot type robot and foot type robot |
| CN115019300B (en) * | 2022-08-09 | 2022-10-11 | 成都运荔枝科技有限公司 | Method for automated warehouse goods identification |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2648515Y (en) * | 2003-07-18 | 2004-10-13 | 四川中科院信息技术有限公司 | Auto-collector for identity card and picture word information of bus ticket |
| CN1558597A (en) * | 2004-01-16 | 2004-12-29 | 深圳市特种证件研究制作中心 | Network based image quality identification method |
| CN1804858A (en) * | 2005-01-10 | 2006-07-19 | 赵国成 | Novel assistant positioning system for implementing OCR function on mobile terminals with camera |
| CN102867179A (en) * | 2012-08-29 | 2013-01-09 | 广东铂亚信息技术股份有限公司 | Method for detecting acquisition quality of digital certificate photo |
| CN104504321A (en) * | 2015-01-05 | 2015-04-08 | 湖北微模式科技发展有限公司 | Method and system for authenticating remote user based on camera |
| CN106886774A (en) * | 2015-12-16 | 2017-06-23 | 腾讯科技（深圳）有限公司 | The method and apparatus for recognizing ID card information |
| CN107209896A (en) * | 2015-02-03 | 2017-09-26 | 居米奥公司 | System and method for being imaged identification information |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7215828B2 (en) * | 2002-02-13 | 2007-05-08 | Eastman Kodak Company | Method and system for determining image orientation |
| CN103927552A (en) * | 2014-04-23 | 2014-07-16 | 北京奇虎科技有限公司 | Method and device for matching answers of target test questions |
| CN105139404B (en) * | 2015-08-31 | 2018-12-21 | 广州市幸福网络技术有限公司 | A kind of the license camera and shooting quality detection method of detectable shooting quality |
| CN108133207A (en) * | 2017-11-24 | 2018-06-08 | 阿里巴巴集团控股有限公司 | The image of auxiliary items closes the method, apparatus and electronic equipment of rule |
-
2017
- 2017-11-24 CN CN201711192125.9A patent/CN108133207A/en active Pending
-
2018
- 2018-09-11 WO PCT/CN2018/104925 patent/WO2019100814A1/en active Application Filing
- 2018-09-20 TW TW107133136A patent/TWI701603B/en active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2648515Y (en) * | 2003-07-18 | 2004-10-13 | 四川中科院信息技术有限公司 | Auto-collector for identity card and picture word information of bus ticket |
| CN1558597A (en) * | 2004-01-16 | 2004-12-29 | 深圳市特种证件研究制作中心 | Network based image quality identification method |
| CN1804858A (en) * | 2005-01-10 | 2006-07-19 | 赵国成 | Novel assistant positioning system for implementing OCR function on mobile terminals with camera |
| CN102867179A (en) * | 2012-08-29 | 2013-01-09 | 广东铂亚信息技术股份有限公司 | Method for detecting acquisition quality of digital certificate photo |
| CN104504321A (en) * | 2015-01-05 | 2015-04-08 | 湖北微模式科技发展有限公司 | Method and system for authenticating remote user based on camera |
| CN107209896A (en) * | 2015-02-03 | 2017-09-26 | 居米奥公司 | System and method for being imaged identification information |
| CN106886774A (en) * | 2015-12-16 | 2017-06-23 | 腾讯科技（深圳）有限公司 | The method and apparatus for recognizing ID card information |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019100814A1 (en) * | 2017-11-24 | 2019-05-31 | 阿里巴巴集团控股有限公司 | Method and apparatus for assisting image of article complaying with requirements, and electronic device |
| CN110650239A (en) * | 2018-06-26 | 2020-01-03 | 百度在线网络技术（北京）有限公司 | Image processing method, image processing device, computer equipment and storage medium |
| CN110650239B (en) * | 2018-06-26 | 2021-03-16 | 百度在线网络技术（北京）有限公司 | Image processing method, image processing device, computer equipment and storage medium |
| CN110889470A (en) * | 2018-09-07 | 2020-03-17 | 京东数字科技控股有限公司 | Method and apparatus for processing image |
| CN110889470B (en) * | 2018-09-07 | 2023-11-07 | 京东科技控股股份有限公司 | Method and apparatus for processing image |
| CN111860475A (en) * | 2019-04-28 | 2020-10-30 | 北京市商汤科技开发有限公司 | Image processing method and device, electronic device and storage medium |
| CN111860475B (en) * | 2019-04-28 | 2023-12-19 | 北京市商汤科技开发有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN110647881B (en) * | 2019-09-19 | 2023-09-05 | 腾讯科技（深圳）有限公司 | Method, device, equipment and storage medium for determining card type corresponding to image |
| CN110647881A (en) * | 2019-09-19 | 2020-01-03 | 腾讯科技（深圳）有限公司 | Method, device, equipment and storage medium for determining card type corresponding to image |
| CN111178347A (en) * | 2019-11-22 | 2020-05-19 | 京东数字科技控股有限公司 | Method, device and equipment for detecting fuzziness of certificate image and storage medium |
| CN111178347B (en) * | 2019-11-22 | 2023-12-08 | 京东科技控股股份有限公司 | Ambiguity detection method, ambiguity detection device, ambiguity detection equipment and ambiguity detection storage medium for certificate image |
| CN111091126A (en) * | 2019-12-12 | 2020-05-01 | 京东数字科技控股有限公司 | Certificate image reflection detection method, device, equipment and storage medium |
| CN111126098A (en) * | 2019-12-24 | 2020-05-08 | 京东数字科技控股有限公司 | Certificate image acquisition method, device, equipment and storage medium |
| CN111126098B (en) * | 2019-12-24 | 2023-11-07 | 京东科技控股股份有限公司 | Certificate image acquisition method, device, equipment and storage medium |
| CN113361300A (en) * | 2020-03-04 | 2021-09-07 | 阿里巴巴集团控股有限公司 | Identification information identification method, device, equipment and storage medium |
| CN111246113A (en) * | 2020-03-05 | 2020-06-05 | 上海瑾盛通信科技有限公司 | Image processing method, device, equipment and storage medium |
| CN112165571A (en) * | 2020-09-09 | 2021-01-01 | 支付宝实验室(新加坡)有限公司 | Certificate image acquisition method, device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| TWI701603B (en) | 2020-08-11 |
| TW201926131A (en) | 2019-07-01 |
| WO2019100814A1 (en) | 2019-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108133207A (en) | The image of auxiliary items closes the method, apparatus and electronic equipment of rule | |
| EP3522072B1 (en) | Method and apparatus for verifying certificates and identities | |
| US11055524B2 (en) | Data extraction pipeline | |
| US11256943B2 (en) | Method and apparatus for verifying identity document, electronic device, and storage medium | |
| US10715550B2 (en) | Method and device for application information risk management | |
| JP2022512123A (en) | Identity authentication method, device and server | |
| CN111652223A (en) | Certificate identification method and device | |
| US20200074148A1 (en) | Method, apparatus, and system for resource transfer | |
| CN109190539A (en) | Face identification method and device | |
| JP2018532188A (en) | Image-based CAPTCHA challenge | |
| CN112561684A (en) | Financial fraud risk identification method and device, computer equipment and storage medium | |
| US8144945B2 (en) | Method, apparatus and computer program product for providing an orientation independent face detector | |
| CN114220097B (en) | Screening method, application method and system of image semantic information sensitive pixel domain based on attack resistance | |
| CN111275105A (en) | Certificate verification method and device and electronic equipment | |
| CN110008664A (en) | Authentication information acquisition, account-opening method, device and electronic equipment | |
| CN110263805B (en) | Certificate verification and identity verification method, device and equipment | |
| CN106897586A (en) | A kind of application programming interface API right management methods and device | |
| US11392679B2 (en) | Certificate verification | |
| CN111340640A (en) | Insurance claim settlement material auditing method, device and equipment | |
| Yao et al. | Deep learning for phishing detection | |
| CN112434689A (en) | Method, device and equipment for identifying information in picture and storage medium | |
| Al-Zahrani et al. | Secure Real‐Time Artificial Intelligence System against Malicious QR Code Links | |
| CN114386013A (en) | Automatic student status authentication method and device, computer equipment and storage medium | |
| EP3933687B1 (en) | An image processing method and system | |
| CN113743396A (en) | Method and device for identifying injection attack in certificate identification process |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1255228 Country of ref document: HK |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180608 |