[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN112668575A - Key information extraction method and device, electronic equipment and storage medium - Google Patents

Key information extraction method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN112668575A
CN112668575A CN202011581164.XA CN202011581164A CN112668575A CN 112668575 A CN112668575 A CN 112668575A CN 202011581164 A CN202011581164 A CN 202011581164A CN 112668575 A CN112668575 A CN 112668575A
Authority
CN
China
Prior art keywords
certificate
image
preset
key information
target
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.)
Granted
Application number
CN202011581164.XA
Other languages
Chinese (zh)
Other versions
CN112668575B (en
Inventor
熊军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Life Insurance Company of China Ltd
Original Assignee
Ping An Life Insurance Company of China Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ping An Life Insurance Company of China Ltd filed Critical Ping An Life Insurance Company of China Ltd
Priority to CN202011581164.XA priority Critical patent/CN112668575B/en
Publication of CN112668575A publication Critical patent/CN112668575A/en
Application granted granted Critical
Publication of CN112668575B publication Critical patent/CN112668575B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Image Analysis (AREA)
  • Character Input (AREA)

Abstract

The invention relates to an intelligent decision technology, and discloses a key information extraction method, which comprises the following steps: carrying out data amplification processing on the original certificate image to obtain an initial training image; training a preset light weight detection model by using an initial training image to obtain a trained light weight detection model; acquiring a certificate image to be identified, and performing target area screening processing on the certificate image to be identified to obtain a certificate area map; carrying out angle correction processing on the certificate area image to obtain a standard area image; carrying out target detection processing on the standard area graph to obtain a target rectangular graph; and performing text recognition processing on the target rectangular graph to obtain key information. In addition, the invention also relates to a block chain technology, and the certificate area graph can be stored in the nodes of the block chain. The invention also provides a key information extraction device, electronic equipment and a computer readable storage medium. The invention can solve the problem of low accuracy of extracting the key information.

Description

Key information extraction method and device, electronic equipment and storage medium
Technical Field
The invention relates to the technical field of intelligent decision, in particular to a key information extraction method and device, electronic equipment and a computer readable storage medium.
Background
With the development of information technology, online services (e.g., online transactions of hydropower services and online transactions of banking services) are increasing, and when online services are transacted, verification of user identities is usually required. When identity verification is performed, it is usually necessary to identify a certificate of a user first, and then determine the identity of the user according to the content of the certificate. Identifying a user's credentials typically requires extracting key information from the credentials, such as: certificate number, name, gender and other information, and further, the identity of the user is confirmed by checking the key information.
The existing key information extraction method is generally to match the intercepted certificate picture with the existing template to obtain the key information fragment of the certificate. The method is easily influenced by the template, and the accuracy of extracting the key information is not high.
Disclosure of Invention
The invention provides a method and a device for extracting key information and a computer readable storage medium, and mainly aims to solve the problem of low accuracy of extracting the key information.
In order to achieve the above object, the present invention provides a method for extracting key information, comprising:
acquiring an original certificate image, and performing data amplification processing on the original certificate image to obtain an initial training image;
training a preset light weight detection model by using the initial training image to obtain a trained light weight detection model;
acquiring a certificate image to be identified, and performing target area screening processing on the certificate image to be identified by using the trained lightweight detection model to obtain a certificate area map;
carrying out angle correction processing on the certificate area map to obtain a standard area map;
carrying out target detection processing on the standard area graph by using a preset target detection model in any direction to obtain a target rectangular graph;
and performing text recognition processing on the target rectangular graph to obtain key information.
Optionally, the performing angle correction processing on the certificate area map to obtain a standard area map includes:
carrying out angle prediction processing on the certificate area map by using a preset four-classification model to obtain angle information of the certificate area map;
judging whether the angle information meets a preset angle standard or not;
if the angle information meets the preset angle standard, judging that the certificate area map is a standard area map;
and if the angle information does not accord with the preset angle standard, performing angle correction on the certificate area map to obtain a standard area map.
Optionally, the performing target detection processing on the standard area map by using a preset target detection model in any direction to obtain a target rectangular map includes:
carrying out rectangular frame marking on the key information related area in the standard area graph by using a preset target detection model in any direction;
acquiring a twiddle factor corresponding to the marked rectangular frame;
judging whether the twiddle factor is a twiddle factor threshold value;
if the twiddle factor is a twiddle factor threshold value, intercepting a picture corresponding to the rectangular frame from the standard area image to obtain a target rectangular image;
if the rotation factor is not the rotation factor threshold, performing affine transformation on the rectangular frame, and intercepting a picture corresponding to the rectangular frame after affine transformation from the standard area image to obtain a target rectangular image.
Optionally, the performing affine transformation on the rectangular frame includes:
mapping the rectangular frame to a preset two-dimensional rectangular coordinate system, and extracting a coordinate value of the rectangular frame;
carrying out transformation processing on the coordinate values according to a preset affine transformation formula to obtain transformed coordinate values;
and mapping the transformation coordinate values on the two-dimensional rectangular coordinate system to obtain a rectangular frame after affine transformation.
Optionally, the performing text recognition processing on the target rectangular chart to obtain key information includes:
performing feature extraction processing on the target rectangular graph to obtain a feature sequence, wherein the feature sequence comprises a plurality of components;
performing probability calculation on the components by using a preset activation function to obtain probability values of the components;
and determining the component corresponding to the maximum probability value as key information.
Optionally, the training a preset lightweight detection model by using the initial training image to obtain a trained lightweight detection model includes:
performing framing processing on the initial training image by using a preset prior frame to obtain a prediction region image;
calculating a coincidence value between the prediction area map and a preset real area map according to a coincidence value formula;
and when the coincidence value is smaller than a preset threshold value, adjusting the internal parameters of the preset light weight detection model until the coincidence value is larger than or equal to the preset threshold value, and obtaining the trained light weight detection model.
Optionally, the coincidence value formula includes:
Figure BDA0002865069010000031
wherein IOU is the coincidence value, DetectionResult is the prediction region map, groudtuth is the real region map, DetectionResult $ groudtuth is an intersection between the prediction region map and the real region map, DetectionResult $ groudtuth is a union between the prediction region map and the real region map.
In order to solve the above problem, the present invention also provides a key information extraction device, including:
the data amplification module is used for acquiring an original certificate image and performing data amplification processing on the original certificate image to obtain an initial training image;
the model training module is used for training a preset light weight detection model by using the initial training image to obtain a trained light weight detection model;
the area screening module is used for acquiring a certificate image to be identified, and performing target area screening processing on the certificate image to be identified by using the trained lightweight detection model to obtain a certificate area map;
the angle correction module is used for carrying out angle correction processing on the certificate area map to obtain a standard area map;
the target detection module is used for carrying out target detection processing on the standard area graph by using a preset target detection model in any direction to obtain a target rectangular graph;
and the text recognition module is used for performing text recognition processing on the target rectangular graph to obtain key information.
In order to solve the above problem, the present invention also provides an electronic device, including:
a memory storing at least one instruction; and
and the processor executes the instructions stored in the memory to realize the key information extraction method.
In order to solve the above problem, the present invention further provides a computer-readable storage medium, in which at least one instruction is stored, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned key information extraction method.
According to the method, the initial training image is obtained by performing data amplification processing on the original certificate image, the number of model training data can be increased by the data amplification processing, and the robustness and the accuracy of the trained lightweight detection model are improved; after the certificate image to be recognized is acquired, the certificate area map can be accurately and quickly acquired by using the trained light weight detection model, the angle correction processing is carried out on the certificate area map, the target rectangular frame can be acquired quickly and accurately, the text recognition processing is carried out on the rectangular frame, the key information is obtained, the accuracy of extracting the key information is improved, and meanwhile, the efficiency of extracting the key information can also be improved. Therefore, the key information extraction method, the key information extraction device, the electronic equipment and the computer readable storage medium provided by the invention can solve the problem of low accuracy in extracting the key information.
Drawings
Fig. 1 is a schematic flow chart of a key information extraction method according to an embodiment of the present invention;
FIG. 2 is a functional block diagram of a key information extraction apparatus according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device for implementing the key information extraction method according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the application provides a key information extraction method. The execution subject of the key information extraction method includes, but is not limited to, at least one of electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the key information extraction method may be performed by software or hardware installed in the terminal device or the server device, and the software may be a block chain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Fig. 1 is a schematic flow chart of a key information extraction method according to an embodiment of the present invention. In this embodiment, the key information extraction method includes:
and S1, acquiring the original certificate image, and performing data amplification processing on the original certificate image to obtain an initial training image.
In the embodiment of the invention, the certificate image is an image of the certificate shot by the camera. For example, images of documents taken by a camera on a mobile electronic device (e.g., a cell phone).
In particular, document images include, but are not limited to: an image of an identification card, an image of a social security card, an image of a passport.
Wherein the data amplification process includes random color dithering, random brightness dithering, random saturation dithering, and random contrast dithering.
Specifically, the random color dithering is a color cross effect that a hue of a formed image is displaced to cause an adjacent dot difference; the random brightness dithering is an effect of causing a bright-dark cross on an image; the random saturation dithering is a cross effect that produces saturation difference shapes; the random contrast dithering is a cross effect that creates contrast differences.
In detail, in the embodiment of the invention, the original certificate image is subjected to data amplification processing, so that the number of model training data can be increased, and the robustness of the model can be improved.
And S2, training a preset light weight detection model by using the initial training image to obtain the trained light weight detection model.
In an embodiment of the present invention, the training of a preset lightweight detection model by using the initial training image to obtain a trained lightweight detection model includes:
performing framing processing on the initial training image by using a preset prior frame to obtain a prediction region image;
calculating a coincidence value between the prediction area map and a preset real area map according to a coincidence value formula;
and when the coincidence value is smaller than a preset threshold value, adjusting the internal parameters of the preset light weight detection model until the coincidence value is larger than or equal to the preset threshold value, and obtaining the trained light weight detection model.
In detail, the preset prior frame is placed on the initial training image for frame selection, a picture selected by the frame is a predicted region map, a preset coincidence value formula is used for calculating a coincidence value between the predicted region map and the real region map, the coincidence value is used for judging the similarity degree between the predicted region map and the real region map, when the coincidence value is smaller than a preset threshold value, it is indicated that the similarity degree between the predicted region map and the real region map does not reach a preset standard, internal parameters of a preset lightweight detection model need to be adjusted, wherein the internal parameters may be model weights or model gradients, and when the coincidence value is larger than or equal to the preset threshold value, the trained lightweight detection model is obtained.
Wherein the preset threshold may be 0.5.
Specifically, the coincidence value formula includes:
Figure BDA0002865069010000061
wherein IOU is the coincidence value, DetectionResult is the prediction region map, groudtuth is the real region map, DetectionResult $ groudtuth is an intersection between the prediction region map and the real region map, DetectionResult $ groudtuth is a union between the prediction region map and the real region map.
In detail, the intersection between the prediction region image and the real region image and the union between the prediction region image and the real region image are respectively solved, and a preset coincidence value formula is combined to calculate a coincidence value, wherein in the embodiment of the invention, the prediction region image is a predicted certificate region image, and the real region image is an existing standard certificate region image.
And S3, acquiring a certificate image to be recognized, and performing target area screening processing on the certificate image to be recognized by using the trained lightweight detection model to obtain a certificate area map.
The target area refers to an area of certificate information in the certificate image to be identified.
For example, if the to-be-identified certificate image includes a background image (such as a wood grain background) and a certificate image, the to-be-identified certificate image is subjected to target region screening processing by using a trained lightweight detection model to obtain the certificate image, namely the certificate region image.
In the embodiment of the invention, the trained lightweight detection model is used for intercepting the target area from the certificate image to be identified and taking the target area as the certificate area image, so that irrelevant information interference of the background in the certificate image to be identified is removed, the occupation ratio of the information in the certificate area image in the certificate image to be identified is increased, the information redundancy is favorably reduced, and the identification efficiency is improved.
And S4, performing angle correction processing on the certificate area map to obtain a standard area map.
In the embodiment of the present invention, the performing angle correction processing on the certificate area map to obtain a standard area map includes:
carrying out angle prediction processing on the certificate area map by using a preset four-classification model to obtain angle information of the certificate area map;
judging whether the angle information meets a preset angle standard or not;
if the angle information meets the preset angle standard, judging that the certificate area map is a standard area map;
and if the angle information does not accord with the preset angle standard, performing angle correction on the certificate area map to obtain a standard area map.
In detail, angle prediction processing is carried out on the certificate area map by using a preset four-classification model to obtain angle information of the certificate area map, wherein the angle information is a deviation angle of the certificate area map on the original certificate image, the placing direction of the certificate area map can be judged according to the angle information, different placing directions can influence subsequent certificate identification results, whether the angle information meets a preset angle standard or not is judged, the preset angle standard is a deviation angle of 0 degree, certificate identification is facilitated, and if the angle information meets the preset angle standard, the certificate area map is judged to be a standard area map;
and if the angle information does not accord with the preset angle standard, performing angle correction on the certificate area diagram, and correcting the angle of the certificate area diagram to be 0 degree deviation to obtain a standard area diagram.
Specifically, in the embodiment of the present invention, the angle information includes a deviation angle of the certificate area map on the original certificate image, for example, the certificate area map deviates from 0 degree, the certificate area map deviates from 90 degrees, or the certificate area map deviates from 180 degrees.
The preset angle standard means that the deviation angle of the certificate area image on the original certificate image is 0 degree.
Further, the angle correction of the certificate area map according to the angle information is to perform rotation correction of the certificate area map to meet an angle standard, for example, to rotate the certificate area map to a direction close to 0 degree.
And S5, carrying out target detection processing on the standard area graph by using a preset target detection model in any direction to obtain a target rectangular graph.
In the embodiment of the present invention, the performing target detection processing on the standard area map by using a preset target detection model in any direction to obtain a target rectangular map includes:
carrying out rectangular frame marking on the key information related area in the standard area graph by using a preset target detection model in any direction;
acquiring a twiddle factor corresponding to the marked rectangular frame;
judging whether the twiddle factor is a twiddle factor threshold value;
if the twiddle factor is a twiddle factor threshold value, intercepting a picture corresponding to the rectangular frame from the standard area image to obtain a target rectangular image;
if the rotation factor is not the rotation factor threshold, performing affine transformation on the rectangular frame, and intercepting a picture corresponding to the rectangular frame after affine transformation from the standard area image to obtain a target rectangular image.
Wherein the target detection model in any direction may be a model having a fast-rcnn structure.
In detail, rectangular labeling is performed on a key information related area in the standard area map according to a preset arbitrary direction target detection model, for example, the standard area map is a processed identity card picture, various key information including but not limited to name, gender, identification number, home address and the like exists on the identity card picture, rectangular frame labeling is performed on the key information, a twiddle factor corresponding to the rectangular frame is obtained, whether the twiddle factor is a twiddle factor threshold value is judged, the twiddle factor threshold value is a standard for judging whether the rectangular frame is horizontal, if the twiddle factor is the twiddle factor threshold value, the picture corresponding to the rectangular frame is intercepted from the standard area map to obtain a target rectangular map, and if the twiddle factor is not the twiddle factor threshold value, affine transformation is performed on the rectangular frame, and intercepting a picture corresponding to the rectangular frame after affine transformation from the standard area graph to obtain a target rectangular graph.
Further, the affine transforming the rectangular frame includes:
mapping the rectangular frame to a preset two-dimensional rectangular coordinate system, and extracting a coordinate value of the rectangular frame;
carrying out transformation processing on the coordinate values according to a preset affine transformation formula to obtain transformed coordinate values;
and mapping the transformation coordinate values on the two-dimensional rectangular coordinate system to obtain a rectangular frame after affine transformation.
In detail, the affine transformation of the rectangular frame is mainly implemented by transforming according to coordinate values of the rectangular frame, obtaining a preset two-dimensional rectangular coordinate system and mapping the rectangular frame to the two-dimensional rectangular coordinate system to obtain coordinate values of the rectangular frame, the affine transformation having a corresponding affine transformation formula, and transforming the coordinate values according to the preset affine transformation formula to obtain transformed coordinate values; and mapping the transformation coordinate values on the two-dimensional rectangular coordinate system to obtain a rectangular frame after affine transformation.
Wherein the preset affine transformation formula is
Figure BDA0002865069010000091
Wherein (x ', y') are transformed coordinate values, and (x, y) are coordinate values,
Figure BDA0002865069010000092
is a preset affine change matrix.
And S6, performing text recognition processing on the target rectangular graph to obtain key information.
When a plurality of target rectangular graphs are obtained through the key information extraction method, text recognition processing is carried out on the plurality of target rectangular graphs, and a plurality of pieces of key information can be obtained. For example, a name and an identification number are obtained, or a name, an identification number and a residential address are obtained.
In the embodiment of the invention, a preset text recognition model is used for carrying out text recognition processing on the target rectangular chart to obtain key information.
In the embodiment of the present invention, the text recognition model may be a CRNN model.
Specifically, the performing text recognition processing on the target rectangular chart to obtain key information includes:
performing feature extraction processing on the target rectangular graph to obtain a feature sequence, wherein the feature sequence comprises a plurality of components;
performing probability calculation on the components by using a preset activation function to obtain probability values of the components;
and determining the component corresponding to the maximum probability value as key information.
In detail, in the embodiment of the present invention, feature extraction processing is performed on the target histogram to obtain a feature sequence, that is, the feature sequence in the certificate picture subjected to the screening, the angle correction, and the target detection processing is extracted, and probability calculation is performed on the plurality of components by using a preset activation function to obtain probability values of the plurality of components; the preset activation function may be a softmax function, and the component corresponding to the maximum probability value is determined as key information.
Specifically, the target histogram may be converted into a feature map with feature information by using a convolutional layer in the text recognition model, so as to obtain a feature sequence, where the feature sequence includes multiple components, and the probability calculation is performed on each component by using a preset activation function, so as to obtain a probability value of each component, and a component with the maximum corresponding probability in each component is used as the key information.
Further, in the embodiment of the present invention, after the obtaining the key information, the method further includes: and identifying the identity of the key information.
Specifically, the identification of the key information may include: and matching the key information with data in an identity information base to determine the identity of the user corresponding to the certificate image to be identified, and further determining whether to open a certain authority for the user.
According to the method, the initial training image is obtained by performing data amplification processing on the original certificate image, the number of model training data can be increased by the data amplification processing, and the robustness and the accuracy of the trained lightweight detection model are improved; after the certificate image to be recognized is acquired, the certificate area map can be accurately and quickly acquired by using the trained light weight detection model, the angle correction processing is carried out on the certificate area map, the target rectangular frame can be acquired quickly and accurately, the text recognition processing is carried out on the rectangular frame, the key information is obtained, the accuracy of extracting the key information is improved, and meanwhile, the efficiency of extracting the key information can also be improved. Therefore, the method for extracting the key information can solve the problem of low accuracy of extracting the key information.
Fig. 2 is a functional block diagram of a key information extraction apparatus according to an embodiment of the present invention.
The key information extraction apparatus 100 of the present invention may be installed in an electronic device. According to the implemented functions, the key information extraction apparatus 100 may include a data amplification module 101, a model training module 102, a region screening module 103, an angle correction module 104, an object detection module 105, and a text recognition module 106. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the data amplification module 101 is configured to acquire an original certificate image, and perform data amplification processing on the original certificate image to obtain an initial training image;
the model training module 102 is configured to train a preset light-weight detection model by using the initial training image to obtain a trained light-weight detection model;
the area screening module 103 is configured to acquire a certificate image to be identified, and perform target area screening processing on the certificate image to be identified by using the trained lightweight detection model to obtain a certificate area map;
the angle correction module 104 is configured to perform angle correction processing on the certificate area map to obtain a standard area map;
the target detection module 105 is configured to perform target detection processing on the standard area map by using a preset target detection model in any direction to obtain a target rectangular map;
the text recognition module 106 is configured to perform text recognition processing on the target rectangular chart to obtain key information.
The data amplification module 101 is configured to acquire an original certificate image, and perform data amplification processing on the original certificate image to obtain an initial training image.
In the embodiment of the invention, the certificate image is an image of the certificate shot by the camera. For example, images of documents taken by a camera on a mobile electronic device (e.g., a cell phone).
In particular, document images include, but are not limited to: an image of an identification card, an image of a social security card, an image of a passport.
Wherein the data amplification process includes random color dithering, random brightness dithering, random saturation dithering, and random contrast dithering.
Specifically, the random color dithering is a color cross effect that a hue of a formed image is displaced to cause an adjacent dot difference; the random brightness dithering is an effect of causing a bright-dark cross on an image; the random saturation dithering is a cross effect that produces saturation difference shapes; the random contrast dithering is a cross effect that creates contrast differences.
In detail, in the embodiment of the invention, the original certificate image is subjected to data amplification processing, so that the number of model training data can be increased, and the robustness of the model can be improved.
The model training module 102 is configured to train a preset light-weight detection model by using the initial training image to obtain a trained light-weight detection model.
In an embodiment of the present invention, the model training module 102 is specifically configured to:
performing framing processing on the initial training image by using a preset prior frame to obtain a prediction region image;
calculating a coincidence value between the prediction area map and a preset real area map according to a coincidence value formula;
and when the coincidence value is smaller than a preset threshold value, adjusting the internal parameters of the preset light weight detection model until the coincidence value is larger than or equal to the preset threshold value, and obtaining the trained light weight detection model.
In detail, the preset prior frame is placed on the initial training image for frame selection, a picture selected by the frame is a predicted region map, a preset coincidence value formula is used for calculating a coincidence value between the predicted region map and the real region map, the coincidence value is used for judging the similarity degree between the predicted region map and the real region map, when the coincidence value is smaller than a preset threshold value, it is indicated that the similarity degree between the predicted region map and the real region map does not reach a preset standard, internal parameters of a preset lightweight detection model need to be adjusted, wherein the internal parameters may be model weights or model gradients, and when the coincidence value is larger than or equal to the preset threshold value, the trained lightweight detection model is obtained.
Wherein the preset threshold may be 0.5.
Specifically, the coincidence value formula includes:
Figure BDA0002865069010000121
wherein IOU is the coincidence value, DetectionResult is the prediction region map, groudtuth is the real region map, DetectionResult $ groudtuth is an intersection between the prediction region map and the real region map, DetectionResult $ groudtuth is a union between the prediction region map and the real region map.
In detail, the intersection between the prediction region image and the real region image and the union between the prediction region image and the real region image are respectively solved, and a preset coincidence value formula is combined to calculate a coincidence value, wherein in the embodiment of the invention, the prediction region image is a predicted certificate region image, and the real region image is an existing standard certificate region image.
The area screening module 103 is configured to acquire a certificate image to be identified, and perform target area screening processing on the certificate image to be identified by using the trained lightweight detection model to obtain a certificate area map.
The target area refers to an area of certificate information in the certificate image to be identified.
For example, if the to-be-identified certificate image includes a background image (such as a wood grain background) and a certificate image, the to-be-identified certificate image is subjected to target region screening processing by using a trained lightweight detection model to obtain the certificate image, namely the certificate region image.
In the embodiment of the invention, the trained lightweight detection model is used for intercepting the target area from the certificate image to be identified and taking the target area as the certificate area image, so that irrelevant information interference of the background in the certificate image to be identified is removed, the occupation ratio of the information in the certificate area image in the certificate image to be identified is increased, the information redundancy is favorably reduced, and the identification efficiency is improved.
The angle correction module 104 is configured to perform angle correction processing on the certificate area map to obtain a standard area map.
In an embodiment of the present invention, the angle correction module 104 is specifically configured to:
carrying out angle prediction processing on the certificate area map by using a preset four-classification model to obtain angle information of the certificate area map;
judging whether the angle information meets a preset angle standard or not;
if the angle information meets the preset angle standard, judging that the certificate area map is a standard area map;
and if the angle information does not accord with the preset angle standard, performing angle correction on the certificate area map to obtain a standard area map.
In detail, angle prediction processing is carried out on the certificate area map by using a preset four-classification model to obtain angle information of the certificate area map, wherein the angle information is a deviation angle of the certificate area map on the original certificate image, the placing direction of the certificate area map can be judged according to the angle information, different placing directions can influence subsequent certificate identification results, whether the angle information meets a preset angle standard or not is judged, the preset angle standard is a deviation angle of 0 degree, certificate identification is facilitated, and if the angle information meets the preset angle standard, the certificate area map is judged to be a standard area map;
and if the angle information does not accord with the preset angle standard, performing angle correction on the certificate area diagram, and correcting the angle of the certificate area diagram to be 0 degree deviation to obtain a standard area diagram.
Specifically, in the embodiment of the present invention, the angle information includes a deviation angle of the certificate area map on the original certificate image, for example, the certificate area map deviates from 0 degree, the certificate area map deviates from 90 degrees, or the certificate area map deviates from 180 degrees.
The preset angle standard means that the deviation angle of the certificate area image on the original certificate image is 0 degree.
Further, the angle correction of the certificate area map according to the angle information is to perform rotation correction of the certificate area map to meet an angle standard, for example, to rotate the certificate area map to a direction close to 0 degree.
The target detection module 105 is configured to perform target detection processing on the standard area map by using a preset target detection model in any direction to obtain a target rectangular map.
In this embodiment of the present invention, the target detection module 105 is specifically configured to:
carrying out rectangular frame marking on the key information related area in the standard area graph by using a preset target detection model in any direction;
acquiring a twiddle factor corresponding to the marked rectangular frame;
judging whether the twiddle factor is a twiddle factor threshold value;
if the twiddle factor is a twiddle factor threshold value, intercepting a picture corresponding to the rectangular frame from the standard area image to obtain a target rectangular image;
if the rotation factor is not the rotation factor threshold, performing affine transformation on the rectangular frame, and intercepting a picture corresponding to the rectangular frame after affine transformation from the standard area image to obtain a target rectangular image.
Wherein the target detection model in any direction may be a model having a fast-rcnn structure.
In detail, rectangular labeling is performed on a key information related area in the standard area map according to a preset arbitrary direction target detection model, for example, the standard area map is a processed identity card picture, various key information including but not limited to name, gender, identification number, home address and the like exists on the identity card picture, rectangular frame labeling is performed on the key information, a twiddle factor corresponding to the rectangular frame is obtained, whether the twiddle factor is a twiddle factor threshold value is judged, the twiddle factor threshold value is a standard for judging whether the rectangular frame is horizontal, if the twiddle factor is the twiddle factor threshold value, the picture corresponding to the rectangular frame is intercepted from the standard area map to obtain a target rectangular map, and if the twiddle factor is not the twiddle factor threshold value, affine transformation is performed on the rectangular frame, and intercepting a picture corresponding to the rectangular frame after affine transformation from the standard area graph to obtain a target rectangular graph.
Further, the affine transforming the rectangular frame includes:
mapping the rectangular frame to a preset two-dimensional rectangular coordinate system, and extracting a coordinate value of the rectangular frame;
carrying out transformation processing on the coordinate values according to a preset affine transformation formula to obtain transformed coordinate values;
and mapping the transformation coordinate values on the two-dimensional rectangular coordinate system to obtain a rectangular frame after affine transformation.
In detail, the affine transformation of the rectangular frame is mainly implemented by transforming according to coordinate values of the rectangular frame, obtaining a preset two-dimensional rectangular coordinate system and mapping the rectangular frame to the two-dimensional rectangular coordinate system to obtain coordinate values of the rectangular frame, the affine transformation having a corresponding affine transformation formula, and transforming the coordinate values according to the preset affine transformation formula to obtain transformed coordinate values; and mapping the transformation coordinate values on the two-dimensional rectangular coordinate system to obtain a rectangular frame after affine transformation.
Wherein the preset affine transformation formula is
Figure BDA0002865069010000151
Wherein (x ', y') are transformed coordinate values, and (x, y) are coordinate values,
Figure BDA0002865069010000152
is a preset affine change matrix.
The text recognition module 106 is configured to perform text recognition processing on the target rectangular chart to obtain key information.
When a plurality of target rectangular graphs are obtained through the key information extraction method, text recognition processing is carried out on the plurality of target rectangular graphs, and a plurality of pieces of key information can be obtained. For example, a name and an identification number are obtained, or a name, an identification number and a residential address are obtained.
In the embodiment of the invention, a preset text recognition model is used for carrying out text recognition processing on the target rectangular chart to obtain key information.
In the embodiment of the present invention, the text recognition model may be a CRNN model.
Specifically, the performing text recognition processing on the target rectangular chart to obtain key information includes:
performing feature extraction processing on the target rectangular graph to obtain a feature sequence, wherein the feature sequence comprises a plurality of components;
performing probability calculation on the components by using a preset activation function to obtain probability values of the components;
and determining the component corresponding to the maximum probability value as key information.
In detail, in the embodiment of the present invention, feature extraction processing is performed on the target histogram to obtain a feature sequence, that is, the feature sequence in the certificate picture subjected to the screening, the angle correction, and the target detection processing is extracted, and probability calculation is performed on the plurality of components by using a preset activation function to obtain probability values of the plurality of components; the preset activation function may be a softmax function, and the component corresponding to the maximum probability value is determined as key information.
Specifically, the target histogram may be converted into a feature map with feature information by using a convolutional layer in the text recognition model, so as to obtain a feature sequence, where the feature sequence includes multiple components, and the probability calculation is performed on each component by using a preset activation function, so as to obtain a probability value of each component, and a component with the maximum corresponding probability in each component is used as the key information.
Further, in the embodiment of the present invention, the apparatus further includes an identity module, where the identity module is configured to: and after obtaining the key information, carrying out identity recognition on the key information.
Specifically, the identification of the key information may include: and matching the key information with data in an identity information base to determine the identity of the user corresponding to the certificate image to be identified, and further determining whether to open a certain authority for the user.
According to the method, the initial training image is obtained by performing data amplification processing on the original certificate image, the number of model training data can be increased by the data amplification processing, and the robustness and the accuracy of the trained lightweight detection model are improved; after the certificate image to be recognized is acquired, the certificate area map can be accurately and quickly acquired by using the trained light weight detection model, the angle correction processing is carried out on the certificate area map, the target rectangular frame can be acquired quickly and accurately, the text recognition processing is carried out on the rectangular frame, the key information is obtained, the accuracy of extracting the key information is improved, and meanwhile, the efficiency of extracting the key information can also be improved. Therefore, the key information extraction device provided by the invention can solve the problem of low accuracy in extracting the key information.
Fig. 3 is a schematic structural diagram of an electronic device implementing a key information extraction method according to an embodiment of the present invention.
The electronic device 1 may comprise a processor 10, a memory 11 and a bus, and may further comprise a computer program, such as a key information extraction program 12, stored in the memory 11 and executable on the processor 10.
The memory 11 includes at least one type of readable storage medium, which includes flash memory, removable hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only to store application software installed in the electronic device 1 and various types of data, such as codes of the key information extraction program 12, but also to temporarily store data that has been output or is to be output.
The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device 1 by running or executing programs or modules (e.g., key information extraction programs, etc.) stored in the memory 11 and calling data stored in the memory 11.
The bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
Fig. 3 shows only an electronic device with components, and it will be understood by those skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than those shown, or some components may be combined, or a different arrangement of components.
For example, although not shown, the electronic device 1 may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so as to implement functions of charge management, discharge management, power consumption management, and the like through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 1 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
Further, the electronic device 1 may further include a network interface, and optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a bluetooth interface, etc.), which are generally used for establishing a communication connection between the electronic device 1 and other electronic devices.
Optionally, the electronic device 1 may further comprise a user interface, which may be a Display (Display), an input unit (such as a Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the electronic device 1 and for displaying a visualized user interface, among other things.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The key information extraction program 12 stored in the memory 11 of the electronic device 1 is a combination of instructions that, when executed in the processor 10, enable:
acquiring an original certificate image, and performing data amplification processing on the original certificate image to obtain an initial training image;
training a preset light weight detection model by using the initial training image to obtain a trained light weight detection model;
acquiring a certificate image to be identified, and performing target area screening processing on the certificate image to be identified by using the trained lightweight detection model to obtain a certificate area map;
carrying out angle correction processing on the certificate area map to obtain a standard area map;
carrying out target detection processing on the standard area graph by using a preset target detection model in any direction to obtain a target rectangular graph;
and performing text recognition processing on the target rectangular graph to obtain key information.
Specifically, the specific implementation method of the processor 10 for the instruction may refer to the description of the relevant steps in the embodiments corresponding to fig. 1 to fig. 3, which is not repeated herein.
Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
The present invention also provides a computer-readable storage medium, storing a computer program which, when executed by a processor of an electronic device, may implement:
acquiring an original certificate image, and performing data amplification processing on the original certificate image to obtain an initial training image;
training a preset light weight detection model by using the initial training image to obtain a trained light weight detection model;
acquiring a certificate image to be identified, and performing target area screening processing on the certificate image to be identified by using the trained lightweight detection model to obtain a certificate area map;
carrying out angle correction processing on the certificate area map to obtain a standard area map;
carrying out target detection processing on the standard area graph by using a preset target detection model in any direction to obtain a target rectangular graph;
and performing text recognition processing on the target rectangular graph to obtain key information.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims (10)

1. A method for extracting key information, the method comprising:
acquiring an original certificate image, and performing data amplification processing on the original certificate image to obtain an initial training image;
training a preset light weight detection model by using the initial training image to obtain a trained light weight detection model;
acquiring a certificate image to be identified, and performing target area screening processing on the certificate image to be identified by using the trained lightweight detection model to obtain a certificate area map;
carrying out angle correction processing on the certificate area map to obtain a standard area map;
carrying out target detection processing on the standard area graph by using a preset target detection model in any direction to obtain a target rectangular graph;
and performing text recognition processing on the target rectangular graph to obtain key information.
2. The method for extracting key information according to claim 1, wherein the performing angle correction processing on the certificate area map to obtain a standard area map comprises:
carrying out angle prediction processing on the certificate area map by using a preset four-classification model to obtain angle information of the certificate area map;
judging whether the angle information meets a preset angle standard or not;
if the angle information meets the preset angle standard, judging that the certificate area map is a standard area map;
and if the angle information does not accord with the preset angle standard, performing angle correction on the certificate area map to obtain a standard area map.
3. The method for extracting key information according to claim 1, wherein the performing the target detection processing on the standard area map by using a preset target detection model in any direction to obtain a target rectangular map comprises:
carrying out rectangular frame marking on the key information related area in the standard area graph by using a preset target detection model in any direction;
acquiring a twiddle factor corresponding to the marked rectangular frame;
judging whether the twiddle factor is a twiddle factor threshold value;
if the twiddle factor is a twiddle factor threshold value, intercepting a picture corresponding to the rectangular frame from the standard area image to obtain a target rectangular image;
if the rotation factor is not the rotation factor threshold, performing affine transformation on the rectangular frame, and intercepting a picture corresponding to the rectangular frame after affine transformation from the standard area image to obtain a target rectangular image.
4. The method of extracting key information according to claim 3, wherein said affine transforming the rectangular frame includes:
mapping the rectangular frame to a preset two-dimensional rectangular coordinate system, and extracting a coordinate value of the rectangular frame;
carrying out transformation processing on the coordinate values according to a preset affine transformation formula to obtain transformed coordinate values;
and mapping the transformation coordinate values on the two-dimensional rectangular coordinate system to obtain a rectangular frame after affine transformation.
5. The method for extracting key information according to claim 1, wherein the performing text recognition processing on the target histogram to obtain key information includes:
performing feature extraction processing on the target rectangular graph to obtain a feature sequence, wherein the feature sequence comprises a plurality of components;
performing probability calculation on the components by using a preset activation function to obtain probability values of the components;
and determining the component corresponding to the maximum probability value as key information.
6. The method for extracting key information according to any one of claims 1 to 5, wherein the training a preset lightweight detection model by using the initial training image to obtain a trained lightweight detection model comprises:
performing framing processing on the initial training image by using a preset prior frame to obtain a prediction region image;
calculating a coincidence value between the prediction area map and a preset real area map according to a coincidence value formula;
and when the coincidence value is smaller than a preset threshold value, adjusting the internal parameters of the preset light weight detection model until the coincidence value is larger than or equal to the preset threshold value, and obtaining the trained light weight detection model.
7. The key information extraction method according to claim 6, wherein the coincidence value formula includes:
Figure FDA0002865067000000021
wherein IOU is the coincidence value, DetectionResult is the prediction region map, groudtuth is the real region map, DetectionResult $ groudtuth is an intersection between the prediction region map and the real region map, DetectionResult $ groudtuth is a union between the prediction region map and the real region map.
8. A key information extraction apparatus, characterized in that the apparatus comprises:
the data amplification module is used for acquiring an original certificate image and performing data amplification processing on the original certificate image to obtain an initial training image;
the model training module is used for training a preset light weight detection model by using the initial training image to obtain a trained light weight detection model;
the area screening module is used for acquiring a certificate image to be identified, and performing target area screening processing on the certificate image to be identified by using the trained lightweight detection model to obtain a certificate area map;
the angle correction module is used for carrying out angle correction processing on the certificate area map to obtain a standard area map;
the target detection module is used for carrying out target detection processing on the standard area graph by using a preset target detection model in any direction to obtain a target rectangular graph;
and the text recognition module is used for performing text recognition processing on the target rectangular graph to obtain key information.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a key information extraction method as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the key information extraction method according to any one of claims 1 to 7.
CN202011581164.XA 2020-12-28 2020-12-28 Key information extraction method and device, electronic equipment and storage medium Active CN112668575B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011581164.XA CN112668575B (en) 2020-12-28 2020-12-28 Key information extraction method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011581164.XA CN112668575B (en) 2020-12-28 2020-12-28 Key information extraction method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN112668575A true CN112668575A (en) 2021-04-16
CN112668575B CN112668575B (en) 2024-05-21

Family

ID=75411003

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011581164.XA Active CN112668575B (en) 2020-12-28 2020-12-28 Key information extraction method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112668575B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113706422A (en) * 2021-10-28 2021-11-26 深圳市亚略特生物识别科技有限公司 Image correction method, device, equipment and medium based on key point acquisition
CN114596573A (en) * 2022-03-22 2022-06-07 中国平安人寿保险股份有限公司 Birth certificate identification method and device, computer equipment and storage medium
CN115375998A (en) * 2022-10-24 2022-11-22 成都新希望金融信息有限公司 Certificate identification method and device, electronic equipment and storage medium

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106909888A (en) * 2017-01-22 2017-06-30 南京开为网络科技有限公司 It is applied to the face key point tracking system and method for mobile device end
CN109697440A (en) * 2018-12-10 2019-04-30 浙江工业大学 A kind of ID card information extracting method
CN109859101A (en) * 2019-01-18 2019-06-07 黑龙江八一农垦大学 The recognition methods of corps canopy thermal infrared images and system
US20190246110A1 (en) * 2018-02-05 2019-08-08 Tencent America LLC Method and apparatus for video coding
CN110363199A (en) * 2019-07-16 2019-10-22 济南浪潮高新科技投资发展有限公司 Certificate image text recognition method and system based on deep learning
CN111027450A (en) * 2019-12-04 2020-04-17 深圳市新国都金服技术有限公司 Bank card information identification method and device, computer equipment and storage medium
CN111767859A (en) * 2020-06-30 2020-10-13 北京百度网讯科技有限公司 Image correction method and device, electronic equipment and computer-readable storage medium
CN112016547A (en) * 2020-08-20 2020-12-01 上海天壤智能科技有限公司 Image character recognition method, system and medium based on deep learning

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106909888A (en) * 2017-01-22 2017-06-30 南京开为网络科技有限公司 It is applied to the face key point tracking system and method for mobile device end
US20190246110A1 (en) * 2018-02-05 2019-08-08 Tencent America LLC Method and apparatus for video coding
CN109697440A (en) * 2018-12-10 2019-04-30 浙江工业大学 A kind of ID card information extracting method
CN109859101A (en) * 2019-01-18 2019-06-07 黑龙江八一农垦大学 The recognition methods of corps canopy thermal infrared images and system
CN110363199A (en) * 2019-07-16 2019-10-22 济南浪潮高新科技投资发展有限公司 Certificate image text recognition method and system based on deep learning
CN111027450A (en) * 2019-12-04 2020-04-17 深圳市新国都金服技术有限公司 Bank card information identification method and device, computer equipment and storage medium
CN111767859A (en) * 2020-06-30 2020-10-13 北京百度网讯科技有限公司 Image correction method and device, electronic equipment and computer-readable storage medium
CN112016547A (en) * 2020-08-20 2020-12-01 上海天壤智能科技有限公司 Image character recognition method, system and medium based on deep learning

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113706422A (en) * 2021-10-28 2021-11-26 深圳市亚略特生物识别科技有限公司 Image correction method, device, equipment and medium based on key point acquisition
CN113706422B (en) * 2021-10-28 2022-03-18 深圳市亚略特科技股份有限公司 Image correction method, device, equipment and medium based on key point acquisition
CN114596573A (en) * 2022-03-22 2022-06-07 中国平安人寿保险股份有限公司 Birth certificate identification method and device, computer equipment and storage medium
CN115375998A (en) * 2022-10-24 2022-11-22 成都新希望金融信息有限公司 Certificate identification method and device, electronic equipment and storage medium
CN115375998B (en) * 2022-10-24 2023-03-17 成都新希望金融信息有限公司 Certificate identification method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN112668575B (en) 2024-05-21

Similar Documents

Publication Publication Date Title
CN111932562B (en) Image identification method and device based on CT sequence, electronic equipment and medium
CN112699775B (en) Certificate identification method, device, equipment and storage medium based on deep learning
CN112396005A (en) Biological characteristic image recognition method and device, electronic equipment and readable storage medium
CN112052850A (en) License plate recognition method and device, electronic equipment and storage medium
CN112668575B (en) Key information extraction method and device, electronic equipment and storage medium
CN113705462B (en) Face recognition method, device, electronic equipment and computer readable storage medium
CN113283446A (en) Method and device for identifying target object in image, electronic equipment and storage medium
CN112541443B (en) Invoice information extraction method, invoice information extraction device, computer equipment and storage medium
CN112507934A (en) Living body detection method, living body detection device, electronic apparatus, and storage medium
CN112508145B (en) Electronic seal generation and verification method and device, electronic equipment and storage medium
CN113887408B (en) Method, device, equipment and storage medium for detecting activated face video
CN113887438B (en) Watermark detection method, device, equipment and medium for face image
CN114708461A (en) Multi-modal learning model-based classification method, device, equipment and storage medium
CN114049568A (en) Object shape change detection method, device, equipment and medium based on image comparison
CN112862703B (en) Image correction method and device based on mobile photographing, electronic equipment and medium
CN113627394A (en) Face extraction method and device, electronic equipment and readable storage medium
CN112560855B (en) Image information extraction method and device, electronic equipment and storage medium
CN113420684A (en) Report recognition method and device based on feature extraction, electronic equipment and medium
CN112528984A (en) Image information extraction method, device, electronic equipment and storage medium
CN113888086B (en) Article signing method, device, equipment and storage medium based on image recognition
CN114913518A (en) License plate recognition method, device, equipment and medium based on image processing
CN113869385A (en) Poster comparison method, device and equipment based on target detection and storage medium
CN115082736A (en) Garbage identification and classification method and device, electronic equipment and storage medium
CN114463685A (en) Behavior recognition method and device, electronic equipment and storage medium
CN113255456A (en) Non-active living body detection method, device, electronic equipment and 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
GR01 Patent grant
GR01 Patent grant