CN111062374A - Identification method, device, system, equipment and readable medium of identity card information - Google Patents
Identification method, device, system, equipment and readable medium of identity card information Download PDFInfo
- Publication number
- CN111062374A CN111062374A CN201911260281.3A CN201911260281A CN111062374A CN 111062374 A CN111062374 A CN 111062374A CN 201911260281 A CN201911260281 A CN 201911260281A CN 111062374 A CN111062374 A CN 111062374A
- Authority
- CN
- China
- Prior art keywords
- identity card
- information
- character
- picture
- card picture
- 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
- 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
- G06V10/225—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 based on a marking or identifier characterising the area
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
-
- 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
Abstract
The embodiment of the application provides an identification method, device and system of identity card information, electronic equipment and a computer readable medium, and relates to the field of artificial intelligence. Wherein the method comprises the following steps: detecting the direction of characters in an identity card picture to be recognized through a character direction detection model so as to obtain character direction information of the identity card picture; correcting the identity card picture based on the character direction information of the identity card picture to obtain the corrected identity card picture; and identifying the characters in the corrected identity card picture to obtain the identity information in the identity card picture. Through the embodiment of the application, the identity information in the identity card picture can be automatically and effectively identified.
Description
Technical Field
The embodiment of the application relates to the field of artificial intelligence, in particular to a method, a device and a system for identifying identity card information, electronic equipment and a computer readable medium.
Background
In these years, with the development of the mobile internet, more and more enterprises have introduced their financial projects, most of which involve the input authentication of personal identification card information, i.e. real-name authentication, and if the personal identification card number and name are manually input, the speed is very slow and the user experience is very poor.
At present, most of identification card identification technologies are based on structural analysis of identification card images, so that identification information in the identification card images is extracted, and the fault tolerance rate is poor. When the image quality of the identity card is not high, the error rate is high. Therefore, how to automatically and effectively identify the identity information in the identity card picture becomes a technical problem to be solved urgently at present.
Disclosure of Invention
The application aims to provide an identification method, an identification device, an identification system, electronic equipment and a computer readable medium for identifying identity card information, which are used for solving the technical problem of how to automatically and effectively identify identity information in an identity card picture in the prior art.
According to a first aspect of the embodiments of the present application, a method for identifying identity card information is provided. The method comprises the following steps: detecting the direction of characters in an identity card picture to be recognized through a character direction detection model so as to obtain character direction information of the identity card picture; correcting the identity card picture based on the character direction information of the identity card picture to obtain the corrected identity card picture; and identifying the characters in the corrected identity card picture to obtain the identity information in the identity card picture.
According to a second aspect of the embodiments of the present application, there is provided an identification apparatus for identification card information. The device comprises: the first detection module is used for detecting the direction of characters in the identity card picture to be recognized through a character direction detection model so as to obtain character direction information of the identity card picture; the correction module is used for correcting the identity card picture based on the character direction information of the identity card picture so as to obtain the corrected identity card picture; and the first identification module is used for identifying the characters in the corrected identity card picture so as to obtain the identity information in the identity card picture.
According to a third aspect of the embodiments of the present application, a system for identifying identity card information is provided. The system comprises: the system comprises terminal equipment and a server in communication connection with the terminal equipment; the terminal equipment is used for sending an identity identification request carrying an identity card picture to be identified to the server; the server is configured to receive the identity identification request sent by the terminal device, analyze the identity identification request to obtain the to-be-identified identity card picture carried by the identity identification request, identify the to-be-identified identity card picture by using the identity card information identification method according to the first aspect of the above embodiment to obtain the identification result of the identity card picture, and return the identification result to the terminal device.
According to a fourth aspect of embodiments of the present application, there is provided an electronic apparatus, including: one or more processors; a computer readable medium configured to store one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method for identifying identification card information according to the first aspect of the embodiments.
According to a fifth aspect of embodiments of the present application, there is provided a computer-readable medium, on which a computer program is stored, which when executed by a processor, implements the identification method of identification card information as described in the first aspect of the embodiments above.
According to the identification scheme of the identity card information, the direction of the characters in the identity card picture to be identified is detected through the character direction detection model to obtain the character direction information of the identity card picture, the identity card picture is corrected based on the character direction information of the identity card picture to obtain the corrected identity card picture, the characters in the corrected identity card picture are identified to obtain the identity information in the identity card picture, compared with the existing other modes, the character direction information of the identity card picture is obtained through the character direction detection model, the identity card picture is corrected based on the character direction information of the identity card picture, the characters in the corrected identity card picture are identified, and the identity information in the identity card picture can be automatically and effectively identified.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
fig. 1 is a flowchart illustrating steps of a method for identifying identification card information according to an embodiment of the present application;
FIG. 2 is a flowchart illustrating steps of a method for identifying ID card information according to a second embodiment of the present application;
fig. 3A is a schematic structural diagram of an identification system for identification card information in a third embodiment of the present application;
fig. 3B is a schematic diagram of an identification process of the identification card information provided according to the third embodiment of the present application;
fig. 4 is a schematic structural diagram of an identification apparatus for identification card information according to a fourth embodiment of the present application;
fig. 5 is a schematic structural diagram of an identification apparatus for identification card information according to a fifth embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to a sixth embodiment of the present application;
fig. 7 is a hardware structure of an electronic device according to a seventh embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Referring to fig. 1, a flowchart illustrating steps of a method for identifying identity card information in a first embodiment of the present application is shown.
Specifically, the identification method for the identity card information provided by the embodiment includes the following steps:
in step S101, the direction of the characters in the identification card picture to be recognized is detected through the character direction detection model, so as to obtain the character direction information of the identification card picture.
In the embodiment of the present application, the text direction detection model may be any suitable neural network model that can implement feature extraction or target object detection, including but not limited to a convolutional neural network model, an reinforcement learning neural network model, a generation network model in an antagonistic neural network model, and the like. The specific structure of the neural network model can be set by those skilled in the art according to actual requirements, such as the number of convolutional layers, the size of convolutional core, the number of channels, and so on. The identification card picture to be identified can be an identification card picture shot by a camera of the mobile phone terminal, can also be an identification card picture shot by a camera or a video camera, and can also be a front picture and a back picture of the identification card. The text direction information may be understood as the degree of text in the identity card picture deviating from the horizontal direction, for example, when the user uses the camera of the mobile phone terminal to shoot the identity card at an angle of 10 degrees, the text direction information of the identity card picture is 10 degrees, and for example, when the user uses the camera of the mobile phone terminal to shoot the identity card at an angle of 270 degrees, the text direction information of the identity card picture is 270 degrees. It should be understood that the above description is only exemplary, and the embodiments of the present application are not limited in this respect.
In some optional embodiments, before the detecting, by the text direction detection model, the direction of the text in the identification card picture to be recognized, the method further includes: detecting the direction of characters in the identity card picture sample through the character direction detection model to be trained so as to obtain character direction detection information of the identity card picture sample; and training the character direction detection model to be trained on the basis of the character direction detection information and the character direction labeling information of the identity card picture sample so as to obtain the trained character direction detection model. Therefore, the character direction detection model to be trained can be effectively trained through the character direction detection information and the character direction labeling information of the identity card picture sample. It should be understood that the above description is only exemplary, and the embodiments of the present application are not limited in this respect.
In a specific example, the identification card picture sample can be understood as an identification card picture in a sample library, the character direction detection information can be understood as the degree of deviation of characters in the identification card picture sample detected by the character direction detection model from the horizontal direction, and the character direction marking information can be understood as the degree of deviation of characters in the identification card picture sample marked manually or by a machine from the horizontal direction. When the character direction detection model to be trained is trained on the basis of the character direction detection information and the character direction labeling information of the identity card picture sample, determining a difference value between the character direction detection information and the character direction labeling information through a target loss function; and adjusting the model parameters of the character direction detection model based on the difference value. The target loss function can be any loss function such as a cross entropy loss function, a softmax loss function, an L1 loss function, and an L2 loss function. When adjusting the model parameters of the character direction detection model, a back propagation algorithm or a random gradient descent algorithm may be used to adjust the model parameters of the character direction detection model. It should be understood that the above description is only exemplary, and the embodiments of the present application are not limited in this respect.
In a specific example, the currently obtained text direction detection information is evaluated by determining a difference value between the text direction detection information and the text direction labeling information, so as to be used as a basis for subsequently training the text direction detection model. Specifically, the difference value may be transmitted to the character direction detection model in a reverse direction, so as to iteratively train the character direction detection model. The training of the character direction detection model is an iterative process, and the embodiment of the present application only describes one training process, but it should be understood by those skilled in the art that this training mode may be adopted for each training of the character direction detection model until the training of the character direction detection model is completed. It should be understood that the above description is only exemplary, and the embodiments of the present application are not limited in this respect.
In step S102, the identity card picture is corrected based on the character direction information of the identity card picture, so as to obtain the corrected identity card picture.
In this application embodiment, when the word direction information of ID card picture is the skew right horizontal direction 90 degrees of characters in the ID card picture, it is right the ID card picture carries out dextrorotation for characters in the ID card picture skew right horizontal direction 0 degree, thereby obtain the ID card picture after correcting. For example, when the character direction information of the identity card picture is that the characters in the identity card picture deviate from the right horizontal direction by 120 degrees, the identity card picture is subjected to right rotation, so that the characters in the identity card picture deviate from the right horizontal direction by 0 degree, and the corrected identity card picture is obtained. For example, when the character direction information of the identity card picture is that the characters in the identity card picture deviate from the left horizontal direction by 90 degrees, the identity card picture is rotated leftwards, so that the characters in the identity card picture deviate from the left horizontal direction by 0 degree, and the corrected identity card picture is obtained. For example, when the character direction information of the identity card picture is that the characters in the identity card picture deviate from the left horizontal direction by 120 degrees, the identity card picture is rotated leftwards, so that the characters in the identity card picture deviate from the left horizontal direction by 0 degree, and the corrected identity card picture is obtained. It should be understood that the above description is only exemplary, and the embodiments of the present application are not limited in this respect.
In step S103, recognizing characters in the corrected identification card image to obtain the identification information in the identification card image.
In an embodiment of the present application, the identity information comprises at least one of: name, sex, ethnicity, date of birth, address, identification number, issuing authority, expiration date. It should be understood that the above description is only exemplary, and the embodiments of the present application are not limited in this respect.
In some optional embodiments, when the characters in the corrected identification card picture are recognized, the characters in the corrected identification card picture are recognized through a character recognition model, so as to obtain the identity information in the identification card picture. It should be understood that the above description is only exemplary, and the embodiments of the present application are not limited in this respect.
In one particular example, the text recognition model may be any suitable neural network model that may enable feature extraction or target object detection, including but not limited to convolutional neural network models, reinforcement learning neural network models, generative network models in antagonistic neural network models, and so forth. The specific structure of the neural network model can be set by those skilled in the art according to actual requirements, such as the number of convolutional layers, the size of convolutional core, the number of channels, and so on. It should be understood that the above description is only exemplary, and the embodiments of the present application are not limited in this respect.
According to the identification method of the identity card information, the direction of the characters in the identity card picture to be identified is detected through the character direction detection model to obtain the character direction information of the identity card picture, the identity card picture is corrected based on the character direction information of the identity card picture to obtain the corrected identity card picture, the characters in the corrected identity card picture are identified to obtain the identity information in the identity card picture, compared with the existing other modes, the character direction information of the identity card picture is obtained through the character direction detection model, the identity card picture is corrected based on the character direction information of the identity card picture, the characters in the corrected identity card picture are identified, and the identity information in the identity card picture can be automatically and effectively identified.
The identification method of the identification card information of the embodiment may be executed by any suitable device with data processing capability, including but not limited to: cameras, terminals, mobile terminals, PCs, servers, tablets, laptops, etc.
Referring to fig. 2, a flowchart illustrating steps of a method for identifying identification card information in the second embodiment of the present application is shown.
Specifically, the identification method for the identity card information provided by the embodiment includes the following steps:
in step S201, the direction of the characters in the identification card picture to be recognized is detected through the character direction detection model, so as to obtain the character direction information of the identification card picture.
Since the embodiment of step S201 is similar to that of step S101, it is not described herein again.
In step S202, the identity card picture is corrected based on the character direction information of the identity card picture, so as to obtain the corrected identity card picture.
Since the embodiment of step S202 is similar to that of step S102, it is not repeated herein.
In step S203, a text region detection model is used to detect a text region in the corrected identification card picture, so as to obtain text region information of the corrected identification card picture.
In the embodiment of the present application, the text region detection model may be any suitable neural network model that can implement feature extraction or target object detection, including but not limited to a convolutional neural network model, an reinforcement learning neural network model, a generation network model in an antagonistic neural network model, and the like. The specific structure of the neural network model can be set by those skilled in the art according to actual requirements, such as the number of convolutional layers, the size of convolutional core, the number of channels, and so on. The text region information can be understood as a text region box, namely a box at the periphery of the text region. It should be understood that the above description is only exemplary, and the embodiments of the present application are not limited in this respect.
In some optional embodiments, before detecting, by the text region detection model, the text region in the corrected identification card picture, the method further includes: detecting a character area in the corrected identity card picture sample through the character area detection model to be trained to obtain character area detection information of the identity card picture sample; and training the character area detection model to be trained on the basis of the character area detection information and the character area labeling information of the identity card picture sample so as to obtain the trained character area detection model. Therefore, the character area detection model to be trained can be effectively trained through the character area detection information and the character area labeling information of the identity card picture sample. It should be understood that the above description is only exemplary, and the embodiments of the present application are not limited in this respect.
In a specific example, the identification card picture sample may be an identification card picture in a sample library, the text region detection information may be a text region frame in the identification card picture sample detected by a text region detection model, and the text region labeling information may be a text region frame in the identification card picture sample labeled manually or by a machine. When the character region detection model to be trained is trained on the basis of the character region detection information and the character region labeling information of the identity card picture sample, determining a difference value between the character region detection information and the character region labeling information through a target loss function; and adjusting the model parameters of the character region detection model based on the difference values. The target loss function can be any loss function such as a cross entropy loss function, a softmax loss function, an L1 loss function, and an L2 loss function. When adjusting the model parameters of the text region detection model, a back propagation algorithm or a random gradient descent algorithm may be used to adjust the model parameters of the text region detection model. It should be understood that the above description is only exemplary, and the embodiments of the present application are not limited in this respect.
In a specific example, the currently obtained text region detection information is evaluated by determining a difference value between the text region detection information and the text region labeling information, so as to be used as a basis for subsequently training the text region detection model. Specifically, the difference value may be transmitted to the text region detection model in a reverse direction, so as to iteratively train the text region detection model. The training of the text region detection model is an iterative process, and the embodiment of the present application only describes one training process, but it should be understood by those skilled in the art that this training mode may be adopted for each training of the text region detection model until the training of the text region detection model is completed. It should be understood that the above description is only exemplary, and the embodiments of the present application are not limited in this respect.
In step S204, based on the corrected text region information of the identity card picture, the corrected identity card picture is cut to obtain a text region picture corresponding to the corrected identity card picture.
In the embodiment of the application, after the character region frame of the corrected identity card picture is obtained, the corrected identity card picture is cut based on the character region frame in the corrected identity card picture, so that the character region picture corresponding to the corrected identity card picture is obtained. The text region picture can be understood as a picture of a region in the text region frame. It should be understood that the above description is only exemplary, and the embodiments of the present application are not limited in this respect.
In step S205, characters in the character region picture are identified by a character identification model, so as to obtain identity information in the identity card picture.
In the embodiment of the present application, the text recognition model may be a neural network model based on an OCR (Optical character recognition) technology. The text recognition model may also be any suitable neural network model that may enable feature extraction or target object detection, including but not limited to a convolutional neural network model, an reinforcement learning neural network model, a generative network model in an antagonistic neural network model, and so forth. The specific structure of the neural network model can be set by those skilled in the art according to actual requirements, such as the number of convolutional layers, the size of convolutional core, the number of channels, and so on. It should be understood that the above description is only exemplary, and the embodiments of the present application are not limited in this respect.
In some optional embodiments, when the characters in the character region pictures are identified through a character identification model, the characters in each character region picture are identified through the character identification model to obtain character information of each character region picture; and analyzing the text information of each text area picture and the text area information corresponding to each text area picture to obtain the structured identity information in the identity card picture. Therefore, the character information of each character area picture and the character area information corresponding to each character area picture are analyzed, and the structured identity information in the identity card picture can be accurately obtained. It should be understood that the above description is only exemplary, and the embodiments of the present application are not limited in this respect.
In a specific example, the structured identity information may be understood as displaying the corresponding identity information in a corresponding text field box. For example, the name is shown in the area box of the name of the identification card, the gender is shown in the area box of the gender of the identification card, and the address is shown in the area box of the address of the identification card. It should be understood that the above description is only exemplary, and the embodiments of the present application are not limited in this respect.
In some optional embodiments, before the text in each text region picture is recognized by the text recognition model, the method further includes: identifying a character area in a character area picture sample through the character identification model to be trained to obtain character identification information of the character area picture sample; and training the character recognition model to be trained based on the character recognition information and the character labeling information of the character region picture sample so as to obtain the trained character recognition model. Therefore, the character recognition model to be trained can be effectively trained through the character recognition information and the character marking information of the character area picture sample. It should be understood that the above description is only exemplary, and the embodiments of the present application are not limited in this respect.
In a specific example, the text area picture sample can be understood as a text area picture in a sample library, the text identification information can be understood as text information in a text area picture sample identified by a text identification model, and the text marking information can be understood as text information in a text area picture sample labeled manually or by a machine. When the character recognition model to be trained is trained on the basis of the character recognition information and the character marking information of the character area picture sample, determining a difference value between the character recognition information and the character marking information through a target loss function; and adjusting the model parameters of the character recognition model based on the difference values. The target loss function can be any loss function such as a cross entropy loss function, a softmax loss function, an L1 loss function, and an L2 loss function. In adjusting the model parameters of the character recognition model, a back propagation algorithm or a stochastic gradient descent algorithm may be used to adjust the model parameters of the character recognition model. It should be understood that the above description is only exemplary, and the embodiments of the present application are not limited in this respect.
In a specific example, the currently obtained character recognition information is evaluated by determining a difference value between the character recognition information and the character tagging information, so as to be used as a basis for subsequently training the character recognition model. Specifically, the disparity value may be transmitted back to the text recognition model, thereby iteratively training the text recognition model. The training of the character recognition model is an iterative process, and the embodiment of the present application only describes one training process, but it should be understood by those skilled in the art that this training mode may be adopted for each training of the character recognition model until the training of the character recognition model is completed. It should be understood that the above description is only exemplary, and the embodiments of the present application are not limited in this respect.
According to the identification method of the identity card information provided by the embodiment of the application, the direction of the characters in the identity card picture to be identified is detected through the character direction detection model to obtain the character direction information of the identity card picture, the identity card picture is corrected based on the character direction information of the identity card picture to obtain the corrected identity card picture, the character area in the corrected identity card picture is detected through the character area detection model to obtain the character area information of the corrected identity card picture, the corrected identity card picture is cut based on the character area information of the corrected identity card picture to obtain the character area picture corresponding to the corrected identity card picture, the characters in the character area picture are identified through the character identification model to obtain the identity information in the identity card picture, compared with the other existing modes, the character direction information of the identity card picture is obtained through the character direction detection model, the identity card picture is corrected based on the character direction information of the identity card picture, the character region in the corrected identity card picture is detected through the character region detection model, the corrected identity card picture is cut based on the character region information of the corrected identity card picture, the character region picture corresponding to the corrected identity card picture is obtained, the characters in the character region picture are identified through the character identification model, the identity information in the identity card picture is obtained, the identity information in the identity card picture can be further automatically and effectively identified, and the identity information in the identity card picture can be rapidly identified.
The identification method of the identification card information of the embodiment may be executed by any suitable device with data processing capability, including but not limited to: cameras, terminals, mobile terminals, PCs, servers, tablets, laptops, etc.
Referring to fig. 3A, in order to implement the identification method of the identification information provided in the embodiment of the present application, a structural diagram of an identification system of the identification information is shown, where the system may include a server and a terminal device a, and it should be understood that the server and the terminal device a shown in fig. 3A are only exemplary illustrations and are not limited to implementation forms of the server and the terminal device a.
In practical application, the server and the terminal device a may be connected by a wired or wireless network, and specifically, may be connected by a mobile network such as GSM, GPRS, LTE, or may be connected by bluetooth, WIFI, infrared, or the like.
The server may be a service device providing services for a user, specifically, an independent application service device, or a service cluster formed by a plurality of servers, and in actual application, the server may be a cloud server, a cloud host, a virtual center, or the like.
The terminal device a may be a user-oriented terminal capable of interacting with a user, such as a mobile phone, a notebook, a computer, an iPad, an intelligent audio, and the like, and may be various self-service terminals, such as self-service machines in places such as hospitals, banks, stations, and the like, and in addition, the terminal device a may also be an intelligent machine supporting interaction, such as a chat robot, a floor sweeping robot, a meal ordering service robot, and the like. The product type and the physical form of the terminal equipment are not limited, and the terminal equipment has an interaction function and can be realized by installing interaction application programs such as finance application programs.
When the identification of the identification card information is carried out, the terminal device A can send an identification request carrying an identification card picture to be identified to the server through the network. The server receives an identity identification request sent by the terminal device A, analyzes the identity identification request to obtain the to-be-identified identity card picture carried by the identity identification request, identifies the to-be-identified identity card picture by adopting the identity card information identification method in the first embodiment or the second embodiment to obtain the identification result of the identity card picture, and returns the identification result to the terminal device A. Therefore, the identification method of the identification card information provided in the embodiment of the present application may be executed by a server, and the specific implementation process may refer to the description of the first method embodiment or the second method embodiment.
In a specific example, as shown in fig. 3B, the server receives an identity identification request sent by the terminal device, and analyzes the identity identification request to obtain an identity card picture to be identified carried in the identity identification request. After the identification card picture to be identified carried by the identification request is obtained, character direction detection is carried out by utilizing the character direction detection model to obtain character direction information of the identification card picture to be identified, and the identification card picture to be identified is corrected based on the character direction information of the identification card picture to be identified. Specifically, when the character recognition information is that the characters in the identification card picture deviate from the horizontal direction by zero degrees, the identification card picture to be recognized does not need to be corrected. When the character recognition information is that the characters in the identity card picture deviate from the horizontal direction by nonzero degree, the identity card picture to be recognized needs to be corrected. Then, detecting the corrected identity card picture by using a character region detection model to obtain a character region frame of the identity card picture, and cutting the identity card picture based on the character region frame of the identity card picture; and after the character area picture is obtained, identifying characters in the character area picture by using a character identification model. And analyzing the identification content through the identified characters and the character area frames corresponding to the character area pictures, and returning a structured identity identification result. Therefore, the identity information in the identity card picture can be automatically identified. In addition, the identification method of the identity card information provided by the embodiment of the application carries out less preprocessing on the picture, retains more original information of the picture, can better identify the identity card picture photographed by the mobile phone, can improve the tolerance of the picture, and ensures the accuracy of identity card identification. In addition, the process of manual input of the user can be omitted, and great convenience is brought to the user. It should be understood that the above description is only exemplary, and the embodiments of the present application are not limited in this respect.
Referring to fig. 4, a schematic structural diagram of an identification apparatus for identification card information in the fourth embodiment of the present application is shown.
The identification apparatus for identification card information provided by this embodiment includes: the first detection module 401 is configured to detect, through a character direction detection model, a direction of a character in an identity card picture to be recognized, so as to obtain character direction information of the identity card picture; a correction module 402, configured to correct the identity card picture based on the text direction information of the identity card picture to obtain a corrected identity card picture; the first identification module 403 is configured to identify characters in the corrected identity card picture to obtain identity information in the identity card picture.
The identification apparatus for identity card information of this embodiment is used to implement the identification method for corresponding identity card information in the foregoing multiple method embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described herein again.
Referring to fig. 5, a schematic structural diagram of an identification apparatus for identification card information in the fifth embodiment of the present application is shown.
The identification apparatus for identification card information provided by this embodiment includes: the first detection module 503 is configured to detect, through a character direction detection model, a direction of a character in an identity card picture to be recognized, so as to obtain character direction information of the identity card picture; a correction module 504, configured to correct the identity card picture based on the text direction information of the identity card picture, so as to obtain a corrected identity card picture; the first identification module 505 is configured to identify characters in the corrected identity card picture to obtain identity information in the identity card picture.
Optionally, before the first detecting module 503, the apparatus further includes: the second detection module 501 is configured to detect the direction of a character in an identity card image sample through the character direction detection model to be trained, so as to obtain character direction detection information of the identity card image sample; the training module 502 is configured to train the character direction detection model to be trained based on the character direction detection information and the character direction labeling information of the identity card image sample, so as to obtain the trained character direction detection model.
Optionally, the first identifying module 505 includes: the second detection submodule 5053 is configured to detect a text region in the corrected identity card picture through a text region detection model, so as to obtain text region information of the corrected identity card picture; the cutting submodule 5054 is configured to cut the corrected identity card picture based on the character region information of the corrected identity card picture to obtain a character region picture corresponding to the corrected identity card picture; the identifying sub-module 5055 is configured to identify, through a character identification model, characters in the character region picture to obtain identity information in the identity card picture.
Optionally, before the second detection sub-module 5053, the first identification module 505 further includes: the first detection submodule 5051 is configured to detect a text region in a corrected identity card picture sample through the text region detection model to be trained, so as to obtain text region detection information of the identity card picture sample; the training submodule 5052 is configured to train the character region detection model to be trained based on the character region detection information and the character region labeling information of the identity card image sample, so as to obtain the trained character region detection model.
Optionally, the identifier module 5055 includes: a second identifying unit 5058, configured to identify, through the text identification model, text in each text region picture to obtain text information of each text region picture; an analyzing unit 5059 is configured to analyze the text information of each text region picture and the text region information corresponding to each text region picture to obtain structured identity information in the identity card picture.
Optionally, before the second identification unit 5058, the identification submodule 5055 further includes: a first identification unit 5056, configured to identify a text region in a text region image sample through the text identification model to be trained, so as to obtain text identification information of the text region image sample; the training unit 5057 is configured to train the character recognition model to be trained based on the character recognition information and the character tagging information of the character region picture sample, so as to obtain the trained character recognition model.
The identification apparatus for identity card information of this embodiment is used to implement the identification method for corresponding identity card information in the foregoing multiple method embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described herein again.
Fig. 6 is a schematic structural diagram of an electronic device according to a sixth embodiment of the present application; the electronic device may include:
one or more processors 601;
a computer-readable medium 602, which may be configured to store one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors implement the method for identifying identification card information according to the first embodiment or the second embodiment.
Fig. 7 is a hardware structure of an electronic device according to a seventh embodiment of the present application; as shown in fig. 7, the hardware structure of the electronic device may include: a processor 701, a communication interface 702, a computer-readable medium 703 and a communication bus 704;
wherein the processor 701, the communication interface 702, and the computer-readable medium 703 are in communication with each other via a communication bus 704;
alternatively, the communication interface 702 may be an interface of a communication module, such as an interface of a GSM module;
the processor 701 may be specifically configured to: detecting the direction of characters in an identity card picture to be recognized through a character direction detection model so as to obtain character direction information of the identity card picture; correcting the identity card picture based on the character direction information of the identity card picture to obtain the corrected identity card picture; and identifying the characters in the corrected identity card picture to obtain the identity information in the identity card picture.
The Processor 701 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The computer-readable medium 703 may be, but is not limited to, a Random Access Memory (RAM), a Read-Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code configured to perform the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication section, and/or installed from a removable medium. The computer program, when executed by a Central Processing Unit (CPU), performs the above-described functions defined in the method of the present application. It should be noted that the computer readable medium described herein can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable medium can 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 storage media (RAM), a read-only storage media (ROM), an erasable programmable read-only storage media (EPROM or flash memory), an optical fiber, a portable compact disc read-only storage media (CD-ROM), an optical storage media piece, a magnetic storage media piece, or any suitable combination of the foregoing. In the present application, 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 this application, 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.
Computer program code configured to carry out operations for the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may operate over any of a variety of networks: including a Local Area Network (LAN) or a Wide Area Network (WAN) -to the user's computer, or alternatively, to an external computer (e.g., through the internet using an internet service provider).
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 application. 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 configured to implement the specified logical function(s). In the above embodiments, specific precedence relationships are provided, but these precedence relationships are only exemplary, and in particular implementations, the steps may be fewer, more, or the execution order may be modified. That is, 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 and/or flowchart illustration, and combinations of blocks in the block diagrams and/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.
The modules described in the embodiments of the present application 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 a first detection module, a remediation module, and a first identification module. For example, the first detection module may also be described as a module that detects, through a text direction detection model, a direction of text in an identification card picture to be recognized to obtain text direction information of the identification card picture.
As another aspect, the present application further provides a computer-readable medium, on which a computer program is stored, which when executed by a processor, implements the identification method of the identification card information as described in the above embodiment one or embodiment two.
As another aspect, the present application also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be present separately and not assembled into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to: detecting the direction of characters in an identity card picture to be recognized through a character direction detection model so as to obtain character direction information of the identity card picture; correcting the identity card picture based on the character direction information of the identity card picture to obtain the corrected identity card picture; and identifying the characters in the corrected identity card picture to obtain the identity information in the identity card picture.
The expressions "first", "second", "said first" or "said second" used in various embodiments of the present disclosure may modify various components regardless of order and/or importance, but these expressions do not limit the respective components. The above description is only configured for the purpose of distinguishing elements from other elements. For example, the first user equipment and the second user equipment represent different user equipment, although both are user equipment. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of the present disclosure.
When an element (e.g., a first element) is referred to as being "operably or communicatively coupled" or "connected" (operably or communicatively) to "another element (e.g., a second element) or" connected "to another element (e.g., a second element), it is understood that the element is directly connected to the other element or the element is indirectly connected to the other element via yet another element (e.g., a third element). In contrast, it is understood that when an element (e.g., a first element) is referred to as being "directly connected" or "directly coupled" to another element (a second element), no element (e.g., a third element) is interposed therebetween.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
Claims (10)
1. A method for identifying identity card information, the method comprising:
detecting the direction of characters in an identity card picture to be recognized through a character direction detection model so as to obtain character direction information of the identity card picture;
correcting the identity card picture based on the character direction information of the identity card picture to obtain the corrected identity card picture;
and identifying the characters in the corrected identity card picture to obtain the identity information in the identity card picture.
2. The method according to claim 1, wherein before detecting the direction of the text in the identification card picture to be recognized through the text direction detection model, the method further comprises:
detecting the direction of characters in the identity card picture sample through the character direction detection model to be trained so as to obtain character direction detection information of the identity card picture sample;
and training the character direction detection model to be trained on the basis of the character direction detection information and the character direction labeling information of the identity card picture sample so as to obtain the trained character direction detection model.
3. The method according to claim 1, wherein the recognizing the corrected characters in the identification card picture to obtain the identification information in the identification card picture comprises:
detecting a character area in the corrected identity card picture through a character area detection model to obtain character area information of the corrected identity card picture;
cutting the corrected identity card picture based on the corrected character region information of the identity card picture to obtain a character region picture corresponding to the corrected identity card picture;
and identifying the characters in the character area picture through a character identification model so as to obtain the identity information in the identity card picture.
4. The method according to claim 3, wherein before the detecting the text region in the corrected identification card picture through the text region detection model, the method further comprises:
detecting a character area in the corrected identity card picture sample through the character area detection model to be trained to obtain character area detection information of the identity card picture sample;
and training the character area detection model to be trained on the basis of the character area detection information and the character area labeling information of the identity card picture sample so as to obtain the trained character area detection model.
5. The method of claim 3, wherein the recognizing the text in the text region picture through a text recognition model to obtain the identity information in the identity card picture comprises:
identifying characters in each character area picture through the character identification model so as to obtain character information of each character area picture;
and analyzing the text information of each text area picture and the text area information corresponding to each text area picture to obtain the structured identity information in the identity card picture.
6. The method of claim 5, wherein before the recognizing the text in each text region picture by the text recognition model, the method further comprises:
identifying a character area in a character area picture sample through the character identification model to be trained to obtain character identification information of the character area picture sample;
and training the character recognition model to be trained based on the character recognition information and the character labeling information of the character region picture sample so as to obtain the trained character recognition model.
7. A system for identifying identification card information, the system comprising:
the system comprises terminal equipment and a server in communication connection with the terminal equipment;
the terminal equipment is used for sending an identity identification request carrying an identity card picture to be identified to the server;
the server is configured to receive the identity identification request sent by the terminal device, parse the identity identification request to obtain the to-be-identified identity card picture carried in the identity identification request, identify the to-be-identified identity card picture by using the identity card information identification method according to any one of claims 1 to 6 to obtain an identification result of the identity card picture, and return the identification result to the terminal device.
8. An apparatus for recognizing identification card information, the apparatus comprising:
the first detection module is used for detecting the direction of characters in the identity card picture to be recognized through a character direction detection model so as to obtain character direction information of the identity card picture;
the correction module is used for correcting the identity card picture based on the character direction information of the identity card picture so as to obtain the corrected identity card picture;
and the first identification module is used for identifying the characters in the corrected identity card picture so as to obtain the identity information in the identity card picture.
9. An electronic device, characterized in that the device comprises:
one or more processors;
a computer readable medium configured to store one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method for identifying identification card information according to any one of claims 1 to 6.
10. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out a method of identification card information according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911260281.3A CN111062374A (en) | 2019-12-10 | 2019-12-10 | Identification method, device, system, equipment and readable medium of identity card information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911260281.3A CN111062374A (en) | 2019-12-10 | 2019-12-10 | Identification method, device, system, equipment and readable medium of identity card information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111062374A true CN111062374A (en) | 2020-04-24 |
Family
ID=70300357
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911260281.3A Pending CN111062374A (en) | 2019-12-10 | 2019-12-10 | Identification method, device, system, equipment and readable medium of identity card information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111062374A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112101317A (en) * | 2020-11-17 | 2020-12-18 | 深圳壹账通智能科技有限公司 | Page direction identification method, device, equipment and computer readable storage medium |
| CN112464852A (en) * | 2020-12-09 | 2021-03-09 | 重庆大学 | Self-adaptive correction and identification method for vehicle driving license picture |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3151180A1 (en) * | 2015-09-29 | 2017-04-05 | STH Development & Design AB | Identification method and system |
| CN108427950A (en) * | 2018-02-01 | 2018-08-21 | 北京捷通华声科技股份有限公司 | A kind of literal line detection method and device |
| CN108549881A (en) * | 2018-05-02 | 2018-09-18 | 杭州创匠信息科技有限公司 | The recognition methods of certificate word and device |
| CN109583445A (en) * | 2018-11-26 | 2019-04-05 | 平安科技（深圳）有限公司 | Character image correction processing method, device, equipment and storage medium |
-
2019
- 2019-12-10 CN CN201911260281.3A patent/CN111062374A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3151180A1 (en) * | 2015-09-29 | 2017-04-05 | STH Development & Design AB | Identification method and system |
| CN108427950A (en) * | 2018-02-01 | 2018-08-21 | 北京捷通华声科技股份有限公司 | A kind of literal line detection method and device |
| CN108549881A (en) * | 2018-05-02 | 2018-09-18 | 杭州创匠信息科技有限公司 | The recognition methods of certificate word and device |
| CN109583445A (en) * | 2018-11-26 | 2019-04-05 | 平安科技（深圳）有限公司 | Character image correction processing method, device, equipment and storage medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112101317A (en) * | 2020-11-17 | 2020-12-18 | 深圳壹账通智能科技有限公司 | Page direction identification method, device, equipment and computer readable storage medium |
| CN112101317B (en) * | 2020-11-17 | 2021-02-19 | 深圳壹账通智能科技有限公司 | Page direction identification method, device, equipment and computer readable storage medium |
| CN112464852A (en) * | 2020-12-09 | 2021-03-09 | 重庆大学 | Self-adaptive correction and identification method for vehicle driving license picture |
| CN112464852B (en) * | 2020-12-09 | 2023-12-05 | 重庆大学 | Vehicle driving license picture self-adaptive correction and identification method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109117831B (en) | Training method and device of object detection network | |
| CN108830235B (en) | Method and apparatus for generating information | |
| CN108427939B (en) | Model generation method and device | |
| US11328401B2 (en) | Stationary object detecting method, apparatus and electronic device | |
| CN107945198B (en) | Method and device for marking point cloud data | |
| US20170111532A1 (en) | Real-time processing of video streams captured using mobile devices | |
| KR102002024B1 (en) | Method for processing labeling of object and object management server | |
| EP3893125A1 (en) | Method and apparatus for searching video segment, device, medium and computer program product | |
| TW202026948A (en) | Methods and devices for biological testing and storage medium thereof | |
| CN112954450B (en) | Video processing method and device, electronic equipment and storage medium | |
| CN108280422B (en) | Method and device for recognizing human face | |
| CN109377508B (en) | Image processing method and device | |
| CN110059623B (en) | Method and apparatus for generating information | |
| CN109583389B (en) | Drawing recognition method and device | |
| CN110941978B (en) | Face clustering method and device for unidentified personnel and storage medium | |
| CN113496208B (en) | Video scene classification method and device, storage medium and terminal | |
| CN111325798A (en) | Camera model correction method and device, AR implementation equipment and readable storage medium | |
| CN114723646A (en) | Image data generation method with label, device, storage medium and electronic equipment | |
| CN111563398A (en) | Method and device for determining information of target object | |
| CN111062374A (en) | Identification method, device, system, equipment and readable medium of identity card information | |
| CN112417947A (en) | Method and device for optimizing key point detection model and detecting face key points | |
| CN114663871A (en) | Image recognition method, training method, device, system and storage medium | |
| CN109064464B (en) | Method and device for detecting burrs of battery pole piece | |
| CN111126159A (en) | Method, apparatus, electronic device, and medium for tracking pedestrian in real time | |
| CN108805799B (en) | Panoramic image synthesis apparatus, panoramic image synthesis method, and computer-readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |