CN110751110A - Identity image information verification method, device, equipment and storage medium - Google Patents
Identity image information verification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN110751110A CN110751110A CN201911016075.8A CN201911016075A CN110751110A CN 110751110 A CN110751110 A CN 110751110A CN 201911016075 A CN201911016075 A CN 201911016075A CN 110751110 A CN110751110 A CN 110751110A
- Authority
- CN
- China
- Prior art keywords
- image information
- identity
- identity image
- verification
- result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/40—Spoof detection, e.g. liveness detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses an identity image information verification method, an identity image information verification device, identity image information verification equipment and a storage medium. The method comprises the steps that the identity image information category to which identity image information to be checked belongs is judged through a first convolutional neural network, wherein the identity image information category comprises positive identity image information and negative identity image information; if the identity image information is judged to belong to the positive identity image information, verifying the identity card number in the identity image information to obtain a first verification result; verifying the name, the identification card number and the face image in the identity image information to obtain a second verification result; judging whether a non-passing result exists in the checking result, wherein the checking result comprises a first checking result and a second checking result; and if the non-passing result does not exist in the verification result, judging that the identity image information passes the verification. The invention can avoid the falsified certificate information from passing verification, reduce the workload of manual verification and improve the automation rate of identity card verification.
Description
Technical Field
The invention relates to the technical field of pattern recognition, in particular to an identity image information verification method, an identity image information verification device, identity image information verification equipment and a computer readable storage medium.
Background
In order to facilitate the entry of the certificate information, the application of automatic identification card information acquisition based on an Optical Character Recognition (OCR) technology in the fields of finance, security and the like has been relatively wide. Although the identification card recognition technology is applied to many actual business scenes at present, the automation rate of the business process is improved, and the work and the life of people are facilitated. However, the identification of the card surface information of the conventional identity card, namely the photographing identification of the conventional identity card, is mainly used in daily life, but the following problems exist in practical use:
(1) the identification of the invalid identity card lacks discriminability, and the behavior of tampering certificate information and the like cannot be blocked, so that the background manual auditing pressure is increased;
(2) other certificate information such as a user's account book and a passport which are uploaded by a part of clients by mistake cannot be identified, and the clients can be required to upload again after manual review, but one or two days of time is wasted in the middle of uploading, so that the service efficiency and the client experience are influenced;
(3) the identity card types are not completely covered, most of identification systems can only identify conventional identity cards, so that many clients cannot use the automatic information extraction function, the certificates are not qualified, and the time cost for requiring the clients to replace the certificates is increased.
As described above, how to provide a verification method capable of determining and identifying a plurality of kinds of identification card information is a problem to be solved urgently.
The above information disclosed in this background section is only for enhancement of understanding of the background of the invention and therefore it may contain information that does not constitute prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
In view of the above, the present invention provides a method, an apparatus, a device and a computer readable storage medium for verifying identity image information.
Additional features and advantages of the invention will be set forth in the detailed description which follows, or may be learned by practice of the invention.
According to an aspect of the present invention, there is provided an identity image information verification method, including: judging the identity image information category to which the identity image information to be checked belongs through a first convolutional neural network, wherein the identity image information category comprises positive identity image information and negative identity image information; if the identity image information is judged to belong to the positive identity image information, verifying the identity card number in the identity image information to obtain a first verification result; verifying the name, the identification card number and the face image in the identity image information to obtain a second verification result; judging whether a non-passing result exists in the checking result, wherein the checking result comprises the first checking result and the second checking result; and if the non-passing result does not exist in the verification result, judging that the identity image information passes the verification.
According to an embodiment of the invention, the method further comprises: if the identity image information is judged to belong to the reverse identity image information, checking the validity period in the identity image information to obtain a third checking result; the verification result further comprises the third verification result.
According to an embodiment of the present invention, if it is determined that the identity image information belongs to the positive identity image information, before the verifying the identity card number in the identity image information, the method further includes: performing optical character recognition on the sub-image to be recognized in the identity image information to obtain a recognized character string; matching the character string with a format corresponding to the identity image information according to the type of the identity image information to obtain a matched field; after the obtaining the first verification result, further comprising: obtaining a first verification result value according to the first verification result, and matching the first verification result value with the content of the corresponding identity card number in the field; after the obtaining of the second verification result, the method further includes: and obtaining a second verification result value according to the second verification result, and matching the second verification result value with the corresponding name in the field and the content of the face image.
According to an embodiment of the present invention, if it is determined that the identity image information belongs to the reverse identity image information, before the verifying the validity period in the identity image information, the method further includes: performing optical character recognition on a sub-image to be recognized in the identity image information to obtain a recognized character string; matching the character string with a format corresponding to the identity image information according to the type of the identity image information to obtain a matched field; after the obtaining of the third verification result, further comprising: and obtaining a third verification result value according to the third verification result, and matching the third verification result value with the content, corresponding to the validity period, in the field.
According to an embodiment of the invention, the method further comprises: if the non-passing result exists in the verification result, judging that the identity image information does not pass the verification, and obtaining non-passing verification information; and obtaining the verification item information corresponding to the failure result, and associating the verification item information with the failure verification information.
According to an embodiment of the present invention, the determining, by the first convolutional neural network, the identity image information category to which the identity image information to be verified belongs includes: and outputting the confidence coefficient that the identity image information to be verified belongs to the identity image information category and the position of the sub-image in the identity image information through a first convolutional neural network.
According to an embodiment of the present invention, before the determining, by the first convolutional neural network, the identity image information category to which the identity image information to be verified belongs, the method further includes: judging whether the definition of the uploaded image meets a preset standard or not through a second convolutional neural network to obtain a first judgment result; judging whether the uploaded image contains an identity card image or not through a second convolutional neural network to obtain a second judgment result; and if the first judgment result is yes and the second judgment result is yes, obtaining identity image information corresponding to the uploaded image.
According to another aspect of the present invention, there is provided an identity image information verification apparatus, including: the identity image classification module is used for judging the identity image information category to which the identity image information to be checked belongs through a first convolutional neural network, wherein the identity image information category comprises positive identity image information and negative identity image information; the compliance studying and judging module is connected with the identity image classification module and comprises a first checking module, a second checking module and a comprehensive studying and judging module, wherein: the first verification module is used for verifying the identity card number in the identity image information after the identity image classification module judges that the identity image information belongs to the positive identity image information, so as to obtain a first verification result; the second verification module is used for verifying the name, the identity card number and the face image in the identity image information to obtain a second verification result; the comprehensive studying and judging module is connected with the first checking module and the second checking module, and is used for judging whether a failed result exists in checking results, wherein the checking results comprise the first checking result and the second checking result; the comprehensive studying and judging module is also used for judging that the identity image information passes the verification when the failure result does not exist in the verification result.
According to an embodiment of the present invention, the compliance studying and judging module further includes a third verification module, the third verification module is connected to the comprehensive studying and judging module, and the third verification module is configured to verify a validity period in the identity image information after determining that the identity image information belongs to the reverse identity image information, so as to obtain a third verification result; the verification result further comprises the third verification result.
According to an embodiment of the invention, the apparatus further comprises: the character recognition module is connected with the identity image classification module and is used for carrying out optical character recognition on the subimage to be recognized in the identity image information to obtain a recognized character string; the structural module is connected with the identity image classification module, the character recognition module and the compliance studying and judging module, and comprises a disassembling and assembling module and a structural output module, wherein: the disassembling and assembling module is used for matching the character string with the format corresponding to the identity image information according to the type of the identity image information to obtain a matched field; and the structured output module is used for obtaining a verification result value according to the verification result and matching the verification result value with the corresponding content in the field.
According to an embodiment of the invention, the device further comprises an image quality inspection module connected with the identity image classification module, wherein the image quality inspection module is used for judging whether the definition of the uploaded image meets a preset standard through a second convolutional neural network to obtain a first judgment result;
the image quality inspection module is further configured to judge whether the uploaded image includes an identity card image through a second convolutional neural network, and obtain a second judgment result;
the image quality inspection module is further configured to obtain identity image information corresponding to the uploaded image when the first determination result is yes and the second determination result is yes.
According to still another aspect of the present invention, there is provided an identity image information verification apparatus, including: a memory, a processor and executable instructions stored in the memory and executable in the processor, the processor implementing any of the methods described above when executing the executable instructions.
According to yet another aspect of the present invention, there is provided a computer-readable storage medium having stored thereon computer-executable instructions which, when executed by a processor, implement any of the methods described above.
According to the identity image information verification method provided by the embodiment of the invention, after the identity image information category to which the identity image information to be verified belongs is judged through the first convolutional neural network, the identity card number, the name and the face image in the face identity image information are comprehensively verified, so that whether the identity card to be verified is an effective identity card or not can be judged, the tampered certificate information is prevented from passing verification, the workload of manual verification is reduced, and the automation rate of identity card verification is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.
Fig. 1 is a flowchart illustrating an identity image information verification method according to an exemplary embodiment.
Fig. 2 is a flowchart illustrating another identity image information verification method according to an exemplary embodiment.
Fig. 3 is a flowchart illustrating another identity image information verification method according to an exemplary embodiment.
Fig. 4 is a flowchart illustrating another identity image information verification method according to an exemplary embodiment.
Fig. 5 is a block diagram illustrating an identity image information verification apparatus according to an exemplary embodiment.
Fig. 6 is a block diagram illustrating another identity image information verification apparatus according to an exemplary embodiment.
Fig. 7 is a block diagram illustrating yet another identity image information verification apparatus according to an exemplary embodiment.
Fig. 8 is a block diagram illustrating yet another identity image information verification apparatus according to an exemplary embodiment.
Fig. 9 is a schematic structural diagram illustrating an identity image information verification apparatus according to an exemplary embodiment.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The drawings are merely schematic illustrations of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to provide a thorough understanding of embodiments of the invention. One skilled in the relevant art will recognize, however, that the invention may be practiced without one or more of the specific details, or with other methods, apparatus, steps, and so forth. In other instances, well-known structures, methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the invention.
Furthermore, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise. The symbol "/" generally indicates that the former and latter associated objects are in an "or" relationship.
In the present invention, unless otherwise explicitly specified or limited, the terms "connected" and the like are to be understood broadly, e.g., can be electrically connected or can communicate with each other; may be directly connected or indirectly connected through an intermediate. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
As described above, the related technologies lack discriminability for identifying the invalid identity card, and cannot prevent the behavior of tampering certificate information and the like, so that the background manual auditing pressure is increased, the service efficiency is low, and the customer experience is poor. Therefore, the invention provides a method, after judging the identity image information category to which the identity image information to be verified belongs through the convolutional neural network, comprehensively verifying the identity card number, the name and the face image in the identity image information, thereby judging whether the identity card to be verified is an effective identity card, avoiding that tampered certificate information passes verification, reducing the workload of manual verification and improving the automation rate of identity card verification.
Fig. 1 is a flowchart illustrating an identity image information verification method according to an exemplary embodiment. The method shown in fig. 1 can be applied to a server side of an identity image information verification system, for example.
Referring to fig. 1, a method 10 includes:
in step S102, the identity image information category to which the identity image information to be verified belongs is determined by the first convolutional neural network, where the identity image information category includes positive identity image information and negative identity image information.
In some embodiments, a 53-layer full convolution neural network is adopted to determine the category of the identity image information to be verified, and the position of each sub-image of the identity image information to be verified in the identity image information to be verified is accurately segmented and determined.
In order to realize one-time output of the target position and the category, in a full convolution neural network framework, five regression values { x, y, w, h, p } are used for representing the position of the sub-image, wherein { x, y } represents a coordinate point of the upper left corner of a rectangular region where the sub-image is located, { w, h } represents the width and height of the rectangular region where the sub-image is located, and p represents the confidence that the current rectangular region contains the sub-image. The identity image information category is set to six types: the front side of the conventional identity card, the back side of the conventional identity card, the front side of the temporary identity card, the front side of the identity card copy, the back side of the identity card copy and the like. Therefore, after a single identity image information image is input into the full convolution neural network, an output vector with dimension N × 11 is obtained, where N represents the number of sub-images detected by the full convolution neural network (for example, if two sub-images on the front and back sides exist in a common identity card image, N is 2; if only one sub-image on the front side exists in a temporary identity card image, N is 1), and 11 dimensions are equal to 6 identity image information categories +5 regression values.
The classification result of the fully convolutional neural network will give the following output structure:
each sub-array respectively represents the attribute of each detected sub-image, wherein 6 c values respectively correspond to the confidence degrees that the current sub-image belongs to six identity image information categories, and the maximum value in the 6 c values represents the category to which the current sub-image belongs most probably; the following four values x and y respectively represent coordinate values of the upper left corner and the lower right corner of the rectangular area of the sub-image; the last p-value represents the confidence that the current rectangular region contains the sub-image. For example, it can be set that under the condition that p >0.2, the first 10 values of the array of the dimension where the next step is to be identified can be used. The value of the actual p needs to be trained and verified according to the actual data of the service.
In step S104, if it is determined that the identity image information belongs to the positive identity image information, the identity card number in the identity image information is verified to obtain a first verification result.
In some embodiments, the number of digits and the content of the ID number are legally verified based on the encoding rule of the last verification code of the current valid second-generation ID number, so as to avoid invalid ID numbers. The validation rules are as follows:
where i denotes the position number (1, 2.. multidot.18) of the 18-digit ID number from right to left, αiIndicating the number value at the ith position; w is aiAnd expressing the weighting factor at the ith position, wherein the calculation formula of the weighting factor is as follows:
wi＝(2i-1)％11
the symbol% represents the remainder of the division of the calculation predecessor and successor numbers.
Whether the identity card number is legal or not can be verified based on the above formula, and if the identity card number is legal, the first verification result is passed; and if the certificate number is illegal, the first verification result is failed, and the user is prompted to upload the image again or modify the certificate number manually in the first verification result.
In step S106, the name, the identification number and the face image in the identity image information are verified to obtain a second verification result;
in some embodiments, after the identity card number passes the validity verification of the previous step, in order to avoid human tampering with the content of the identity card, for example: intentionally shielding the certificate photo, tampering the name or the identity card number and the like, and performing higher-level security verification on the legality of the content of the identity card, for example, optionally, further judging whether the identity image information comprises name information, identity card number information and face image information; and if the identity image information does not comprise at least one item of information of name information, identity card number information and face image information, the second verification result is failed.
Optionally, a mode of verifying three elements of name + identity card number + face image is adopted, the common citizen identity card information base in the database of the public security department is connected, the three elements are integrated to verify the validity of the identity document content, and if the citizens of the common citizen identity card information base corresponding to the three elements are inconsistent, the second verification result is failed.
In step S108, determining whether a failure result exists in the verification result, where the verification result includes a first verification result and a second verification result;
in step S110, if the failure result does not exist in the verification result, it is determined that the identity image information passes the verification. In some embodiments, the object to be verified and the judgment rule can be adjusted according to the actual service scene, if the insurance service does not allow the adoption of the identity card copy, for the service, the result of the classification based on the identity image information is preferentially judged whether the identity card copy is the copy, and if the identity card copy is the copy, the verification result of the identity image information is directly judged to be failed; if not, the subsequent identification number and three-element check are carried out. The invention is not limited thereto.
According to the identity image information verification method provided by the embodiment of the invention, after the identity image information category to which the identity image information to be verified belongs is judged through the first convolutional neural network, the identity card number, the name and the face image in the face identity image information are comprehensively verified, so that whether the identity card to be verified is an effective identity card or not can be judged, the tampered certificate information is prevented from passing verification, the workload of manual verification is reduced, and the automation rate of identity card verification is improved.
Fig. 2 is a flowchart illustrating another identity image information verification method according to an exemplary embodiment. The method shown in fig. 2 can be applied to a server side of an identity image information verification system, for example.
Referring to fig. 2, the method 20 includes:
in step S202, the identity image information category to which the identity image information to be verified belongs is determined by the first convolutional neural network, where the identity image information category includes positive identity image information and negative identity image information.
In some embodiments, a 53-layer full convolution neural network is adopted to determine the category of the identity image information to be verified, and the position of each sub-image of the identity image information to be verified in the identity image information to be verified is accurately segmented and determined. See example 1 for a detailed description of the classification method.
In step S204, if it is determined that the identity image information belongs to the positive identity image information, the identity card number in the identity image information is verified to obtain a first verification result.
In some embodiments, the number of digits and the content of the ID number are legally verified based on the encoding rule of the last verification code of the current valid second-generation ID number, so as to avoid invalid ID numbers. See example 1 for a detailed description of the validation rules.
In step S206, the name, the identification number and the face image in the identity image information are verified to obtain a second verification result.
In some embodiments, after the identity card number passes the validity verification of the previous step, to avoid human tampering with the identity card content, a higher level of security verification needs to be performed on the validity of the identity card content. See example 1 for a detailed description of the validation method.
In step S208, if it is determined that the identity image information belongs to the reverse identity image information, the validity period in the identity image information is checked to obtain a third checking result.
In some embodiments, a third verification for verifying the validity of the identity image information determined to be the reverse side of the regular identity card may be added. Alternatively, if there is no regular positive identity card in the classification result of identity image information represented by the N × 11-dimensional vector, the result of the third verification is directly a non-passing verification, because if there is a negative image of the identity card, then it must be present at the same time.
Optionally, for the reverse side of the conventional identity card, a third verification for verifying the validity of the validity period may be performed, and if the validity period is illegal, the third verification result is a non-passing verification result. Firstly, calculating the age corresponding to the identity card number according to the positive identity card number of the conventional identity card, and then checking the age and the validity period according to the following rules:
5 years of validity-less than 16 years of age;
a 10 year expiration date of 16 years old or more and 25 years old or less;
effective period of 20 years, namely 26 years old or more and 45 years old or less;
long term effect-greater than or equal to 46 years of age.
In some embodiments, a fourth verification for verifying the validity of the validity period may be added to the identity image information determined as the positive of the temporary identity card, and if the validity period is illegal, the fourth verification result is a non-passing verification. The validity period of the temporary identity card is fixed for 3 months, and any differential validity period is illegal.
In step S210, it is determined whether there is a failed result in the verification result, where the verification result includes a first verification result, a second verification result, and a third verification result. In some embodiments, the verification result may further include a fourth verification result for verifying the validity period of the temporary identity card, and the verification process is as before.
In step S212, if the non-passing result does not exist in the verification result, it is determined that the identity image information passes the verification.
According to the identity image information verification method provided by the embodiment of the invention, after the identity image information category to which the identity image information to be verified belongs is judged through the first convolutional neural network, the validity period in the (reverse) identity image information is verified while the identity number, the name and the face image in the forward identity image information are comprehensively verified, so that the credibility of the verification result is increased, the tampered identity information is prevented from passing verification, the workload of manual verification is reduced, and the automation rate of identity card verification is improved.
Fig. 3 is a flowchart illustrating another identity image information verification method according to an exemplary embodiment. The method shown in fig. 3 can be applied to a server side of an identity image information verification system, for example.
Referring to fig. 3, the method 30 includes:
in step S302, the identity image information category to which the identity image information to be verified belongs is determined through the first convolutional neural network, where the identity image information category includes positive identity image information and negative identity image information.
In some embodiments, a 53-layer full convolution neural network is adopted to determine the category of the identity image information to be verified, and the position of each sub-image of the identity image information to be verified in the identity image information to be verified is accurately segmented and determined. See example 1 for a detailed description of the classification method.
In step S304, if it is determined that the identity image information belongs to the positive identity image information, optical character recognition is performed on the sub-image to be recognized in the identity image information to obtain a recognized character string. In some embodiments, the sub-images segmented by the full convolution neural network are sent to an image OCR recognition engine, text data is extracted from the sub-images, and the extracted text data is returned in the form of line character strings.
In step S306, the character string is matched with the format corresponding to the identity image information according to the type of the identity image information, and a matched field is obtained. In some embodiments, the character strings returned by the OCR recognition engine are disassembled, assembled and matched according to the format of the identity image information (the type of the format is obtained based on the obtained identity image information type in the above steps), so as to obtain the key-return value (key-value) matching. Taking the positive identity image information as an example, the key-value combination of fields such as name, sex, date of birth, address, identification card number and the like is realized.
In step S308, the identification number in the identification image information is verified to obtain a first verification result.
In some embodiments, the number of digits and the content of the ID number are legally verified based on the encoding rule of the last verification code of the current valid second-generation ID number, so as to avoid invalid ID numbers. See example 1 for a detailed description of the validation rules.
In step S309, a first verification result value is obtained according to the first verification result, and the first verification result value is matched with the content of the corresponding identification number in the field.
In step S310, the name, the identification number and the face image in the identity image information are verified to obtain a second verification result.
In some embodiments, after the identity card number passes the validity verification of the previous step, to avoid human tampering with the identity card content, a higher level of security verification needs to be performed on the validity of the identity card content. See example 1 for a detailed description of the validation method.
In step S311, a second verification result value is obtained according to the second verification result, and the second verification result value is matched with the corresponding name in the field and the content of the face image.
In step S312, it is determined whether there is a failed result in the verification result, where the verification result includes the first verification result and the second verification result. In some embodiments, the verification result may further include a third and a fourth verification results for verifying the validity period of the identity card, and the third and the fourth verification processes are as described in embodiment 2.
In step S314, if the failure result does not exist in the verification result, it is determined that the identity image information passes the verification.
In step S316, if the non-passing result exists in the verification result, it is determined that the identity image information does not pass the verification, and the non-passing verification information is obtained.
In step S318, the verification item information corresponding to the failed result is obtained, and the verification item information is associated with the failed verification information.
In some embodiments, the final result is output in the form of a key-value, for example, for a conventional original (including a front side and a back side) of the identification card, if the verification result is passed, the output includes:
if the verification result is not passed, the output content comprises:
according to the identity image information verification method provided by the embodiment of the invention, after the identity image information category to which the identity image information to be verified belongs is judged through the first convolutional neural network, OCR recognition is carried out on the sub-image to be recognized in the identity image information, then the recognized character string is matched with the format corresponding to the identity image information category, after comprehensive verification is carried out on the identity card number, the name and the face image in the front identity image information, each keyword information corresponding to the comprehensive verification result is output or the cause description is failed, so that the high-efficiency output of the identity image information verification result is realized, and the business operation efficiency and the automation rate of the identity card verification are improved.
Fig. 4 is a flowchart illustrating another identity image information verification method according to an exemplary embodiment. The method shown in fig. 4 can be applied to a server side of an identity image information verification system, for example.
Referring to fig. 4, the method 40 includes:
in step S402, determining whether the sharpness of the uploaded image meets a preset standard through a second convolutional neural network, to obtain a first determination result;
in step S404, determining whether the uploaded image includes an identity card image through a second convolutional neural network, to obtain a second determination result;
in step S406, if the first determination result is yes and the second determination result is yes, the identity image information corresponding to the uploaded image is obtained.
In some embodiments, a full convolution neural network comprising two outputs is used to perform preliminary quality inspection on the uploaded image. The primary quality inspection mainly detects two aspects, namely whether the definition of an uploaded image is qualified or not; and secondly, whether the uploaded image contains the identity card or not. The output of the full convolution neural network is { p1, p2}, p1 represents the confidence that the uploaded image contains the identity card, and p2 represents the confidence that the uploaded image is qualified in definition. The thresholds of p1 and p2 are generally obtained by training according to actual data under different service scene data. For example, assuming that 0.35 and 0.02 are thresholds for p1, p2, respectively, then:
if p1 is less than 0.35, the uploaded image is judged not to contain the identity card, and the client is required to retransmit the image;
if p1 is greater than 0.35 and p2 is less than 0.02, judging that the definition of the uploaded image is unqualified, and requiring the client to retransmit;
if p1>0.35, p2>0.02, the preliminary quality inspection is passed.
In step S408, the identity image information category to which the identity image information to be verified belongs is determined by the first convolutional neural network, where the identity image information category includes positive identity image information and negative identity image information.
In some embodiments, a 53-layer full convolution neural network is adopted to determine the category of the identity image information to be verified, and the position of each sub-image of the identity image information to be verified in the identity image information to be verified is accurately segmented and determined. See example 1 for a detailed description of the classification method.
In step S410, if it is determined that the identity image information belongs to the positive identity image information, the identity card number in the identity image information is verified to obtain a first verification result.
In some embodiments, the number of digits and the content of the ID number are legally verified based on the encoding rule of the last verification code of the current valid second-generation ID number, so as to avoid invalid ID numbers. See example 1 for a detailed description of the validation rules.
In step S412, the name, the identification number and the face image in the identity image information are verified to obtain a second verification result.
In some embodiments, after the identity card number passes the validity verification of the previous step, to avoid human tampering with the identity card content, a higher level of security verification needs to be performed on the validity of the identity card content. See example 1 for a detailed description of the validation method.
In step S414, it is determined whether there is a failed result in the verification result, where the verification result includes the first verification result and the second verification result.
In step S416, if the failure result does not exist in the verification result, it is determined that the identity image information passes the verification.
According to the identity image information verification method provided by the embodiment of the invention, whether the definition of the uploaded image meets the preset standard or not and whether the uploaded image contains an identity card image or not is judged through the second convolutional neural network to carry out primary quality inspection, then the identity image information category of the identity image information passing the primary quality inspection is judged through the first convolutional neural network, and then the identity card number, the name and the face image in the face identity image information are comprehensively verified, so that the primary control of the identity image quality is realized, the credibility of the verification result is increased, the tampered certificate information is prevented from passing verification, the workload of manual verification is reduced, and the automation rate of the identity card verification is improved.
Fig. 5 is a block diagram illustrating an identity image information verification apparatus according to an exemplary embodiment.
As shown in fig. 5, the apparatus 50 includes: an identity image classification module 502, configured to determine, through a first convolutional neural network, an identity image information category to which identity image information to be verified belongs, where the identity image information category includes positive identity image information and negative identity image information;
a compliance judging module 504 connected to the identity image classifying module 502, wherein the compliance judging module 504 includes a first checking module 5041, a second checking module 5042 and a comprehensive judging module 5043, and wherein:
the first verification module 5041 is configured to verify the identity card number in the identity image information after the identity image classification module 502 determines that the identity image information belongs to the positive identity image information, and obtain a first verification result;
the second verification module 5042 is configured to verify the name, the identification card number, and the face image in the identity image information to obtain a second verification result;
the comprehensive study and judgment module 5043 is connected to the first verification module 5041 and the second verification module 5042, and the comprehensive study and judgment module 5043 is configured to judge whether a failed result exists in the verification result, where the verification result includes a first verification result and a second verification result;
the comprehensive study and judgment module 5043 is further configured to judge that the identity image information passes the verification if no failure result exists in the verification result.
Fig. 6 is a block diagram illustrating an identity image information verification apparatus according to an exemplary embodiment.
As shown in fig. 6, the apparatus 60 includes: an identity image classification module 602, configured to determine, through a first convolutional neural network, an identity image information category to which identity image information to be checked belongs, where the identity image information category includes positive identity image information and negative identity image information;
the compliance studying and judging module 604 is connected to the identity image classifying module 602, and the compliance studying and judging module 604 includes a first checking module 6041, a second checking module 6042, a third checking module 6043 and a comprehensive studying and judging module 6044, wherein:
a first verification module 6041, configured to verify the identity card number in the identity image information after the identity image classification module 602 determines that the identity image information belongs to the positive identity image information, and obtain a first verification result;
the second verification module 6042 is configured to verify the name, the identification card number, and the face image in the identity image information to obtain a second verification result;
a third verification module 6043, configured to verify the validity period in the identity image information after determining that the identity image information belongs to the reverse-side identity image information, so as to obtain a third verification result;
the comprehensive study and judgment module 6044 is connected to the first verification module 6041, the second verification module 6042 and the third verification module 6043, and the comprehensive study and judgment module 6044 is configured to judge whether a failed result exists in a verification result, where the verification result includes a first verification result, a second verification result and a third verification result;
the comprehensive study and judgment module 6044 is further configured to determine that the identity image information passes the verification when the failure result does not exist in the verification result.
Fig. 7 is a block diagram illustrating another identity image information verification apparatus according to an exemplary embodiment.
As shown in fig. 7, the apparatus 70 includes: an identity image classification module 702, configured to determine, through a first convolutional neural network, an identity image information category to which identity image information to be verified belongs, where the identity image information category includes positive identity image information and negative identity image information;
the character recognition module 703 is connected with the identity image classification module 702, and is used for performing optical character recognition on the sub-image to be recognized in the identity image information to obtain a recognized character string;
a compliance study and judgment module 704 connected to the identity image classification module 702, wherein the compliance study and judgment module 704 includes a first verification module 7041, a second verification module 7042, a third verification module 7043 and a comprehensive study and judgment module 7044, wherein:
the first verification module 7041 is configured to verify the identity card number in the identity image information after the identity image classification module 702 determines that the identity image information belongs to the positive identity image information, so as to obtain a first verification result;
the second verification module 7042 is configured to verify the name, the identification number, and the face image in the identity image information to obtain a second verification result;
the third verification module 7043 is configured to verify the validity period in the identity image information after determining that the identity image information belongs to the reverse identity image information, so as to obtain a third verification result;
the comprehensive research and judgment module 7044 is connected to the first verification module 7041, the second verification module 7042 and the third verification module 7043, and the comprehensive research and judgment module 7044 is configured to judge whether a failed result exists in the verification result, where the verification result includes a first verification result, a second verification result and a third verification result;
the comprehensive research and judgment module 7044 is further configured to judge that the identity image information passes the verification when the failure result does not exist in the verification result;
the structuring module 705 is connected to the identity image classification module 702, the character recognition module 703 and the compliance study and judgment module 704, and the structuring module 705 includes a disassembling and assembling module 7051 and a structuring output module 7052, wherein:
the disassembling and assembling module 7051 is configured to match the character string with a format corresponding to the identity image information according to the category of the identity image information to obtain a matched field;
and the structured output module 7052 is configured to obtain a verification result value according to the verification result, and match the verification result value with the corresponding content in the field.
Fig. 8 is a block diagram illustrating yet another identity image information verification apparatus according to an exemplary embodiment.
As shown in fig. 8, the apparatus 80 includes: the image quality inspection module 801 is used for judging whether the definition of the uploaded image meets a preset standard through a second convolutional neural network to obtain a first judgment result;
the image quality inspection module 801 is further configured to determine whether the uploaded image includes an identity card image through a second convolutional neural network, and obtain a second determination result;
the image quality inspection module 801 is further configured to obtain identity image information corresponding to the uploaded image when the first determination result is yes and the second determination result is yes.
The identity image classification module 802 is connected to the image quality inspection module 801 and configured to determine, through a first convolutional neural network, an identity image information category to which the identity image information to be checked belongs, where the identity image information category includes positive identity image information and negative identity image information;
the character recognition module 803 is connected to the identity image classification module 802, and is configured to perform optical character recognition on a sub-image to be recognized in the identity image information to obtain a recognized character string;
a compliance judging module 804 connected to the identity image classifying module 802, wherein the compliance judging module 804 includes a first verification module 8041, a second verification module 8042, a third verification module 8043 and a comprehensive judging module 8044, wherein:
the first verification module 8041 is configured to verify the identity card number in the identity image information after the identity image classification module 802 determines that the identity image information belongs to the positive identity image information, and obtain a first verification result;
the second verification module 8042 is configured to verify the name, the identification number, and the face image in the identity image information to obtain a second verification result;
the third verification module 8043 is configured to, after determining that the identity image information belongs to the reverse-side identity image information, verify a validity period in the identity image information to obtain a third verification result;
the comprehensive judging module 8044 is connected to the first verification module 8041, the second verification module 8042, and the third verification module 8043, and the comprehensive judging module 8044 is configured to judge whether a failed result exists in the verification result, where the verification result includes a first verification result, a second verification result, and a third verification result;
the comprehensive study and judgment module 8044 is further configured to judge that the identity image information passes the verification when the failure result does not exist in the verification result;
the structural module 805 is connected to the identity image classification module 802, the character recognition module 803 and the compliance study and judgment module 804, and the structural module 805 includes a disassembly and assembly module 8051 and a structural output module 8052, in which:
the disassembling and assembling module 8051 is used for matching the character string with the format corresponding to the identity image information according to the category of the identity image information to obtain a matched field;
and the structured output module 8052 is configured to obtain a verification result value according to the verification result, and match the verification result value with the corresponding content in the field.
The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor includes an identity image classification module and a compliance study and judgment module. The names of the modules do not limit the modules themselves in some cases, for example, the compliance judging module may also be described as a "module for judging whether the identity image information is valid".
It should be noted that the apparatus shown in fig. 9 is only an example of a computer system, and should not bring any limitation to the function and the scope of the application of the embodiment of the present invention.
As shown in fig. 9, the apparatus 900 includes a Central Processing Unit (CPU)901 that can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)902 or a program loaded from a storage section 908 into a Random Access Memory (RAM) 903. In the RAM903, various programs and data necessary for the operation of the apparatus 900 are also stored. The CPU901, ROM 902, and RAM903 are connected to each other via a bus 904. An input/output (I/O) interface 905 is also connected to bus 904.
The following components are connected to the I/O interface 905: an input portion 906 including a keyboard, a mouse, and the like; an output section 907 including components such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 908 including a hard disk and the like; and a communication section 909 including a network interface card such as a LAN card, a modem, or the like. The communication section 909 performs communication processing via a network such as the internet. The drive 910 is also connected to the I/O interface 905 as necessary. A removable medium 911 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 910 as necessary, so that a computer program read out therefrom is mounted into the storage section 908 as necessary.
In particular, according to an embodiment of the present invention, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the invention include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 909, and/or installed from the removable medium 911. The computer program performs the above-described functions defined in the method of the present invention when executed by a Central Processing Unit (CPU) 901.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: the system comprises a memory, a processor and executable instructions stored in the memory and executable in the processor, wherein the processor executes the executable instructions to realize the method.
Exemplary embodiments of the present invention are specifically illustrated and described above. It is to be understood that the invention is not limited to the precise construction, arrangements, or instrumentalities described herein; on the contrary, the invention is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims (10)
1. An identity image information verification method is characterized by comprising the following steps:
judging the identity image information category to which the identity image information to be checked belongs through a first convolutional neural network, wherein the identity image information category comprises positive identity image information and negative identity image information;
if the identity image information is judged to belong to the positive identity image information, verifying the identity card number in the identity image information to obtain a first verification result;
verifying the name, the identification card number and the face image in the identity image information to obtain a second verification result;
judging whether a non-passing result exists in the checking result, wherein the checking result comprises the first checking result and the second checking result;
and if the non-passing result does not exist in the verification result, judging that the identity image information passes the verification.
2. The method of claim 1, further comprising:
if the identity image information is judged to belong to the reverse identity image information, checking the validity period in the identity image information to obtain a third checking result;
the verification result further comprises the third verification result.
3. The method of claim 2, wherein if it is determined that the identity image information belongs to the reverse identity image information, before the verifying the validity period in the identity image information, further comprising:
performing optical character recognition on a sub-image to be recognized in the identity image information to obtain a recognized character string;
matching the character string with a format corresponding to the identity image information according to the type of the identity image information to obtain a matched field;
after the obtaining of the third verification result, further comprising: and obtaining a third verification result value according to the third verification result, and matching the third verification result value with the content, corresponding to the validity period, in the field.
4. The method of claim 1, wherein if it is determined that the identity image information belongs to the positive identity image information, before the verifying the identity card number in the identity image information, further comprising:
performing optical character recognition on the sub-image to be recognized in the identity image information to obtain a recognized character string;
matching the character string with a format corresponding to the identity image information according to the type of the identity image information to obtain a matched field;
after the obtaining the first verification result, further comprising: obtaining a first verification result value according to the first verification result, and matching the first verification result value with the content of the corresponding identity card number in the field;
after the obtaining of the second verification result, the method further includes: and obtaining a second verification result value according to the second verification result, and matching the second verification result value with the corresponding name in the field and the content of the face image.
5. The method of claim 1 or 2, further comprising: if the non-passing result exists in the verification result, judging that the identity image information does not pass the verification, and obtaining non-passing verification information;
and obtaining the verification item information corresponding to the failure result, and associating the verification item information with the failure verification information.
6. The method according to claim 1 or 2, wherein the determining, by the first convolutional neural network, the identity image information category to which the identity image information to be verified belongs includes:
and outputting the confidence coefficient that the identity image information to be verified belongs to the identity image information category and the position of the sub-image in the identity image information through a first convolutional neural network.
7. The method according to claim 1 or 2, before the determining, by the first convolutional neural network, the identity image information category to which the identity image information to be verified belongs, further comprising:
judging whether the definition of the uploaded image meets a preset standard or not through a second convolutional neural network to obtain a first judgment result;
judging whether the uploaded image contains an identity card image or not through a second convolutional neural network to obtain a second judgment result;
and if the first judgment result is yes and the second judgment result is yes, obtaining identity image information corresponding to the uploaded image.
8. An identity image information verification device, comprising:
the identity image classification module is used for judging the identity image information category to which the identity image information to be checked belongs through a first convolutional neural network, wherein the identity image information category comprises positive identity image information and negative identity image information;
the compliance studying and judging module is connected with the identity image classification module and comprises a first checking module, a second checking module and a comprehensive studying and judging module, wherein:
the first verification module is used for verifying the identity card number in the identity image information after the identity image classification module judges that the identity image information belongs to the positive identity image information, so as to obtain a first verification result;
the second verification module is used for verifying the name, the identity card number and the face image in the identity image information to obtain a second verification result;
the comprehensive studying and judging module is connected with the first checking module and the second checking module, and is used for judging whether a failed result exists in checking results, wherein the checking results comprise the first checking result and the second checking result;
the comprehensive studying and judging module is also used for judging that the identity image information passes the verification when the failure result does not exist in the verification result.
9. An identity image information verification device, comprising: memory, processor and executable instructions stored in the memory and executable in the processor, characterized in that the processor implements the method according to any of claims 1-7 when executing the executable instructions.
10. A computer-readable storage medium having stored thereon computer-executable instructions, which when executed by a processor, implement the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911016075.8A CN110751110A (en) | 2019-10-24 | 2019-10-24 | Identity image information verification method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911016075.8A CN110751110A (en) | 2019-10-24 | 2019-10-24 | Identity image information verification method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110751110A true CN110751110A (en) | 2020-02-04 |
Family
ID=69279722
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911016075.8A Pending CN110751110A (en) | 2019-10-24 | 2019-10-24 | Identity image information verification method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110751110A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021196935A1 (en) * | 2020-04-01 | 2021-10-07 | 深圳壹账通智能科技有限公司 | Data checking method and apparatus, electronic device, and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN106874968A (en) * | 2016-12-21 | 2017-06-20 | 江苏国光信息产业股份有限公司 | A kind of China second-generation identity card distinguishing method between true and false of efficient robust |
| 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 |
| CN106991421A (en) * | 2017-03-22 | 2017-07-28 | 湖南联信科技有限公司 | A kind of ID card information extraction system |
| CN109657673A (en) * | 2017-10-11 | 2019-04-19 | 阿里巴巴集团控股有限公司 | Image-recognizing method and terminal |
| CN110135992A (en) * | 2019-05-14 | 2019-08-16 | 北京智签科技有限公司 | The acquisition methods and acquisition device of block chain network Fabric-CA digital certificate |
-
2019
- 2019-10-24 CN CN201911016075.8A patent/CN110751110A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN106874968A (en) * | 2016-12-21 | 2017-06-20 | 江苏国光信息产业股份有限公司 | A kind of China second-generation identity card distinguishing method between true and false of efficient robust |
| CN106991421A (en) * | 2017-03-22 | 2017-07-28 | 湖南联信科技有限公司 | A kind of ID card information extraction system |
| CN109657673A (en) * | 2017-10-11 | 2019-04-19 | 阿里巴巴集团控股有限公司 | Image-recognizing method and terminal |
| CN110135992A (en) * | 2019-05-14 | 2019-08-16 | 北京智签科技有限公司 | The acquisition methods and acquisition device of block chain network Fabric-CA digital certificate |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021196935A1 (en) * | 2020-04-01 | 2021-10-07 | 深圳壹账通智能科技有限公司 | Data checking method and apparatus, electronic device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107798299B (en) | Bill information identification method, electronic device and readable storage medium | |
| WO2021042747A1 (en) | Invoice picture recognition and verification method and system, device, and readable storage medium | |
| WO2020253508A1 (en) | Abnormal cell detection method and apparatus, and computer readable storage medium | |
| WO2021259096A1 (en) | Identity authentication method, apparatus, electronic device, and storage medium | |
| CN109871845B (en) | Certificate image extraction method and terminal equipment | |
| CN111046879A (en) | Certificate image classification method and device, computer equipment and readable storage medium | |
| CN112036295B (en) | Bill image processing method and device, storage medium and electronic equipment | |
| CN111476268A (en) | Method, device, equipment and medium for training reproduction recognition model and image recognition | |
| CN108491866B (en) | Pornographic picture identification method, electronic device and readable storage medium | |
| CN112668575B (en) | Key information extraction method and device, electronic equipment and storage medium | |
| CN112508145B (en) | Electronic seal generation and verification method and device, electronic equipment and storage medium | |
| CN111783896A (en) | Image identification method and system based on kernel method | |
| CN112396047B (en) | Training sample generation method and device, computer equipment and storage medium | |
| CN111415336A (en) | Image tampering identification method and device, server and storage medium | |
| CN112487982A (en) | Merchant information auditing method, system and storage medium | |
| CN110751110A (en) | Identity image information verification method, device, equipment and storage medium | |
| CN117523586A (en) | Check seal verification method and device, electronic equipment and medium | |
| CN113066223A (en) | Automatic invoice verification method and device | |
| CN117115833A (en) | Certificate classification method, device, equipment and storage medium | |
| CN116612486A (en) | Risk group identification method and system based on image identification and graph calculation | |
| CN116485344A (en) | Intelligent collection method and device for online claim settlement materials, electronic equipment and medium | |
| CN113434912B (en) | Material compliance verification method and device | |
| CN113177543B (en) | Certificate identification method, device, equipment and storage medium | |
| CN112686244B (en) | Automatic approval method, device, equipment and medium based on picture processing interface | |
| CN113569839A (en) | Certificate identification method, system, device and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200204 |