CN115063234A - Image quality inspection method, server and system for credit card application - Google Patents
Image quality inspection method, server and system for credit card application Download PDFInfo
- Publication number
- CN115063234A CN115063234A CN202210736851.7A CN202210736851A CN115063234A CN 115063234 A CN115063234 A CN 115063234A CN 202210736851 A CN202210736851 A CN 202210736851A CN 115063234 A CN115063234 A CN 115063234A
- Authority
- CN
- China
- Prior art keywords
- image
- quality inspection
- group photo
- head portrait
- client
- 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
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
-
- 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
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/197—Matching; Classification
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Artificial Intelligence (AREA)
- Ophthalmology & Optometry (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention provides an image quality inspection method for applying credit cards, which comprises the following steps: the method comprises the steps of responding to a login request of a user sent by a client to log in, obtaining a client identity card image sent by the client, obtaining an identity card image of a service worker from a database according to an account number of the service worker, obtaining quality inspection data by comparing the obtained identity card image of the client and the service worker with a group photo image of the client and the service worker, and comparing the quality inspection data with a preset threshold value to obtain a conclusion whether manual quality inspection needs to be intervened. In addition, the invention also provides a system and a server applying the image quality inspection method for the credit card.
Description
Technical Field
The invention relates to the technical field of internet, in particular to an image quality inspection method, a server and a system for applying for a credit card.
Background
In the background of rapid development of consumer financial market, a small credit payment instrument such as a credit card which is consumed first and then credited is popular with more and more people, but the credit card is stolen for various reasons, and the credit card is given a good name and is borrowed or handled, thereby causing problems such as poor personal credit investigation records.
Today, in order to help users to prevent fraud risks, protect client funds and fulfill enterprise responsibilities, various safety measures are adopted, wherein multiple face recognition is one means, but manual quality inspection is still required after the clients finish OCR, group photo of business personnel and other image information are uploaded to a platform, the error rate of manual participation is uncontrollable, the time efficiency is slow, and manpower is wasted.
Then can the image comparison technology be used to perform quality inspection on the images uploaded by customers and business personnel? How to compare and determine whether the result is accurate? If the quality inspection is passed, the quality inspection quality can be provided, and meanwhile, the quality inspection timeliness is ensured, and even if the quality inspection fails abnormally, manual quality inspection can be redistributed.
Therefore, finding a method for realizing image quality inspection to help a system to complete automatic quality inspection is an urgent problem to be solved.
Disclosure of Invention
The invention provides an image quality inspection method, a server and a system for applying for a credit card, which reduce the waste of human resources, improve the business efficiency of enterprises and ensure the quality inspection timeliness.
In a first aspect, an embodiment of the present invention provides an image quality inspection method for applying for a credit card, where the image quality inspection method for applying for a credit card includes:
responding a login request of a user sent by a client to log in, wherein the login request at least comprises an account number of a service person;
acquiring a customer identity card image sent by the client;
acquiring an identity card image of a service person from a database according to an account number of the service person;
acquiring a group photo image of a client and a service worker sent by the client;
matching the customer identity card image with the group photo image to obtain a first matching score;
matching the business person identification card image with the group photo image to obtain a second matching score;
determining a quality inspection result according to the first matching score and the second matching score, wherein the quality inspection result comprises quality inspection passing and quality inspection failing;
and when the quality inspection fails, prompting manual intervention quality inspection.
Optionally, the client identity card image and the service staff identity card image are grid images, and the pairing of the client identity card image and the group photo image to obtain a first matching score specifically includes:
grid removing processing is carried out on the customer identity card image to obtain a grid-removed customer identity card image;
performing head portrait cutout on the client identity card image subjected to grid removal to obtain a client head portrait;
inputting the client head portrait and the group photo image into a preset recognition model for operation to obtain a first matching score, wherein the preset recognition model is obtained by training an identity card head portrait training set and a character image training set, and each head portrait of the identity card head portrait training set corresponds to one image and a plurality of images in the character image training set.
Optionally, the client identification card image and the group photo image are grid images, and the pairing the client identification card image and the group photo image to obtain a first matching score specifically includes:
grid removing processing is carried out on the customer identity card image and the group photo image to obtain a grid-removed customer identity card image and a grid-removed group photo image;
performing head portrait cutout on the client identity card image subjected to grid removal to obtain a client head portrait;
and matching the customer head portrait with the customer image of the grid-removed group photo image to obtain the first matching score.
Optionally, the pairing the customer identification card image and the group photo image to obtain a first matching score further includes:
matting the grid-removed group photo image to form a first head portrait and a second head portrait;
comparing the head portrait of the client with the first head portrait and the second head portrait one by one;
and taking the score with the highest score as the first matching score.
Optionally, the pairing the service personnel identification card image and the group photo image to obtain a second matching score includes:
performing gridding removal processing on the service personnel identity card image to obtain a gridded service personnel identity card image;
performing head portrait cutout on the identity card image of the service personnel after grid removal to obtain a head portrait of the service personnel;
inputting the head portraits of the business personnel and the head portraits of the group photo into a preset recognition model for operation to obtain a second matching score, wherein the preset recognition model is obtained by training an identity card head portraits training set and a character image training set, and each head portraits of the identity card head portraits training set corresponds to one image and a plurality of images in the character image training set.
Optionally, the step of pairing the business person identification card image and the group photo image to obtain a second matching score specifically includes:
carrying out grid removing treatment on the service personnel identity card image and the group photo image to obtain a grid-removed service personnel identity card image and a grid-removed group photo image;
performing head portrait cutout on the identity card image of the service personnel after grid removal to obtain a head portrait of the service personnel;
and matching the head portrait of the business personnel with the customer image of the grid-removed group photo image to obtain the second matching score.
Optionally, the step of pairing the service personnel identification card image and the group photo image to obtain a second matching score further includes:
matting the group photo image to form a first head portrait and a second head portrait;
comparing the head portraits of the business personnel with the first head portraits and the second head portraits one by one;
and taking the score with the highest score as the second matching score.
Optionally, the customer identification card image and the group photo image are captured by the client.
In a second aspect, an embodiment of the present invention further provides an image quality inspection system for applying for a credit card, where the quality inspection system includes a client and a server. The server includes a memory and a processor. The client is used for receiving an input command of a service person and sending a service request to the server. A memory for storing computer program instructions; and the processor is used for executing the computer program instructions to realize the image quality inspection method for applying for the credit card.
In a third aspect, an embodiment of the present invention further provides a server, where the server includes a memory and a processor. The client is used for receiving an input command of a service person and sending a service request to the server. A memory for storing computer program instructions; and the processor is used for executing the computer program instructions to realize the image quality inspection method for applying for the credit card.
Above-mentioned, pair through the ID card image of acquireing customer and service personnel and customer and service personnel's group photo image and acquire the quality inspection data, compare the quality inspection data with predetermineeing the threshold value and acquire the conclusion that whether need intervene artifical quality inspection, this scheme greatly reduced bank handle the card cost, improved the business efficiency and also avoided the artificial possibility of making mistakes.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
Fig. 1 is a flowchart of an image quality inspection method for applying for a credit card according to an embodiment of the present invention.
Fig. 2 is a schematic view of a quality inspection result page of an image quality inspection method for applying for a credit card according to an embodiment of the present invention.
Fig. 3 is a flowchart illustrating sub-steps of step S109 in the method for applying for image quality inspection of a credit card according to the first embodiment of the present invention.
Fig. 4 is a flowchart illustrating sub-steps of step S109 in a method for applying for image quality inspection of a credit card according to a second embodiment of the present invention.
Fig. 5 is a flowchart illustrating sub-steps of step S106 in a method for applying for image quality inspection of a credit card according to a first embodiment of the present invention.
Fig. 6 is a flowchart illustrating sub-steps of the first embodiment provided in step S111 of the method for applying for image quality inspection of a credit card according to the embodiment of the present invention.
Fig. 7 is a flowchart illustrating sub-steps of the second embodiment provided in step S111 of the method for applying for image quality inspection of a credit card according to the embodiment of the present invention.
Fig. 8 is a flowchart illustrating sub-steps of step S21 in an image quality inspection method for applying for a credit card according to an embodiment of the present invention.
Fig. 9 is a schematic diagram of an internal structure of a server of an image quality inspection system for applying for a credit card according to an embodiment of the present invention.
Fig. 10 and 9 are schematic diagrams of an image quality inspection system for applying for a credit card 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
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, and in the above-described drawings, if any, are used for distinguishing between similar items and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances, in other words that the embodiments described are to be practiced in sequences other than those illustrated or described herein. Moreover, the terms "comprises," "comprising," and any other variation thereof, may also include other things, such as processes, methods, systems, articles, or apparatus that comprise a list of steps or elements is not necessarily limited to only those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such processes, methods, articles, or apparatus.
It should be noted that the description relating to "first", "second", etc. in the present invention is for descriptive purposes only and is not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature limited to "first" or "second" may explicitly or implicitly include one or more of that feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
Please refer to fig. 1, which is a flowchart illustrating an image quality inspection method for a credit card according to an embodiment of the present invention. The image quality inspection method for applying for a credit card is performed by an image quality inspection system for applying for a credit card, as shown in fig. 10. The image quality inspection system 100 includes a client 10 and a server 20. The client 10 is used for generating a corresponding request or acquiring corresponding data such as text information or images in response to a user operation, and sending the corresponding data and request to the server. And the server processes the image according to the request or the data of the client so as to realize quality inspection of the image of the credit card application. The method comprises steps S101-S115.
Step S101, a user logs in response to a login request sent by a client, wherein the login request information at least comprises account information of an operator.
The credit card transaction request received in step S101 may be a request for the user to apply for transaction of a credit card to any bank. In the embodiment of the present invention, the account information of the clerk included in the login request for credit card transaction may be information that can be used to uniquely identify the clerk, for example: the system comprises an identity card number, a mobile phone number and an operator account number.
And step S103, acquiring a customer identity card image sent by the client. Specifically, the customer identity card image is a grid image, and because the image stored in the computer is a bitmap, the customer identity card image received by the client needs to be subjected to grid removal before image processing, and then the client identity card image is subjected to head image matting by using a matting program to obtain a customer head image P1.
It should be noted that there are many existing technologies that can be implemented for the method of descreening and matting the image, for example, phothosp, american show, popcore, Play With Pictures, etc., and details thereof are not described herein.
And step S105, acquiring an identity card image of the operator from a database according to the account number of the operator. After the operator inputs the system account and the password, the client sends the account information to the server, and the server searches the information of the operator through the account information, sends the information to the client and displays the information on the client interface. Similarly, the acquired employee identity card image information is a grid image, after the acquired employee image is subjected to grid processing, the identity card image of the employee is subjected to head portrait matting by using a matting program, and an employee head portrait P2 is obtained.
And step S107, acquiring a group photo image of the client and the service staff, which is sent by the client. Understandably, the group image is a mesh image, and the received group image is subjected to meshing processing to obtain a group image head image P3. The identification card image and the group photo image may be received by a client during the process of examining whether the client is in accordance with the credit card transaction by a salesperson, and the client may be, but not limited to, an image captured by a personal computer, a notebook computer, a smart phone, a tablet computer, a portable wearable device or a camera arranged in front of an ATM counter.
Further, including but not limited to using an OCR recognition engine, based on OCR recognition capability, the information on the image of the identification card is output in a text form, as one data source of the present invention, and in an embodiment of the present invention, as another data source of the present invention, the image information is sent by the business staff through the PC.
In this embodiment, the image sent by the clerk is manually confirmed by the customer, thus preventing others from counterfeiting the transacted credit card.
Step S109, matching the customer identity card image with the group photo image to obtain a first matching score. In some possible embodiments, the image features of the customer id card image and the image features of the group image may be compared to obtain the first matching score n1, and in other possible embodiments, the customer id card image and the group image may also be input into a trained preset recognition model for operation, which will be described in detail in step S109 below.
And step S111, pairing the salesman identity card image and the group photo image to obtain a second matching score.
In some possible embodiments, the image features of the service person identification card image and the image features of the group photo image may be compared to obtain the second matching score n2, and in other possible embodiments, the service person identification card image and the group photo image may also be input into a trained preset recognition model for operation, which will be described in detail in step S109 below.
And S113, determining a quality inspection result according to the first matching score and the second matching score, wherein the quality inspection result comprises quality inspection passing and quality inspection failing. Specifically, when the first matching score n1 and the second matching score n2 are both greater than the preset threshold n, the quality check is passed, and if the first matching score n1 or the second matching score n2 is less than the preset threshold n, the quality check is not passed. Wherein each avatar of the identity card avatar training corresponds to one image and a plurality of images in the person image training set.
And step S115, when the quality inspection fails, prompting manual intervention processing.
In this step, when the quality inspection is passed, the flow is ended. Specifically, after the quality inspection data are compared, the server sends a result to the client, as shown in fig. 2, a result interface 1 can be added to the client 10, and when "quality inspection is successful and a next step is requested" is popped up on the result interface 1, the service staff can click "next step" 4 to enter the next process; when the result interface 1 pops up that "quality inspection fails, please take a picture again", the service personnel clicks "take a picture again" 3 to enter the interface of taking a picture again, at this moment, the image quality inspection system 100 carries out image quality inspection again.
Please refer to fig. 3, which is a flowchart illustrating sub-steps of step S109 of the method for applying for image quality inspection of a credit card according to the first embodiment of the present invention, including steps S10-S12.
And step S10, performing grid removing processing on the customer identity card image to obtain a grid-removed customer identity card image. Because the image acquired by the client is a mesh image, the image needs to be subjected to meshing processing for precise subsequent processing of the image. For example, after receiving the customer identification card image, the client performs meshing processing by using a PhothoPhop program in a manner of sequentially clicking ' view ', ' display ', ' grid ' on a PhothoPhop menu bar, and the shortcut key is CTRL + '.
Step S11 performs portrait matting on the customer identification card image after the grid is removed to obtain a customer portrait.
Step S12 inputs the client avatar and the group photo image into a preset recognition model for operation to obtain a first matching score.
In this step, the preset recognition model is obtained by training an identity card avatar training set and a character image training set, wherein each avatar in the identity card avatar training set corresponds to one image and a plurality of images in the character image training set. Understandably, based on the deep learning of the face recognition, the recognition model acquires preset values of face features, wherein the face features comprise facial feature proportion features, face contour features, iris features and the like, and the recognition model performs feature comparison on the acquired head portrait and the combined image head portrait to acquire first matching data n 1.
Please refer to fig. 4, which is a flowchart illustrating the sub-steps of step S109 in the method for applying for image quality inspection of a credit card according to the second embodiment of the present invention, including steps S102-S106.
And step S102, grid removing processing is carried out on the customer identity card image and the group photo image to obtain a grid-removed customer identity card image and a grid-removed group photo image.
And step S104, performing head portrait cutout on the customer identity card image subjected to grid removal to obtain a customer head portrait.
And step S106, pairing the customer head portrait with the customer image of the grid-removed group photo image to obtain the first matching score. In some possible embodiments, the client head image is compared with the client image in the group image based on facial features including facial scale features, facial contour features, iris features, etc., and the first matching score for comparison is labeled as n 1.
Please refer to fig. 5, which is a flowchart illustrating sub-steps of the first embodiment of step S106 in the method for applying for image quality inspection of a credit card according to the present invention, comprising steps S13-S15.
And step S13, matting the grid-removed group photo image to form a first head portrait and a second head portrait.
And step S14, comparing the client head portrait with the first head portrait and the second head portrait one by one. In this step, the acquired head portrait of the client is compared with the first head portrait and the second head portrait one by one. The comparison may be performed based on the face features, for example, if the face contour is used as the comparison condition, the face contour of the client avatar is compared with the face contour of the first avatar, and the face contour of the client avatar is compared with the face contour of the second avatar.
In step S15, the score with the highest score is used as the first matching score. In this step, based on step S14, the results of the one-to-one comparison are compared to obtain the highest score as the first matching score n 1.
Please refer to fig. 6, which is a flowchart illustrating sub-steps of the first embodiment provided in step S111 of a method for applying for image quality inspection of a credit card according to an embodiment of the present invention, including steps S16-S18.
And step S16, performing grid removing processing on the service personnel identification card image to obtain a grid-removed service personnel identification card image.
And step S17, performing head portrait matting on the gridded business person ID card image to obtain a business person head portrait.
And step S18, inputting the head portraits of the service personnel and the group photo head portraits into a preset recognition model for operation to obtain a second matching score. In this step, the preset recognition model is obtained by training an identity card avatar training set and a character image training set, wherein each avatar of the identity card avatar training set corresponds to one image and a plurality of images in the character image training set. Understandably, based on the deep learning of the face recognition, the recognition model acquires preset values of face features, wherein the face features comprise facial feature proportion features, face contour features, iris features and the like, and the recognition model performs feature comparison on the acquired head portrait and the combined image head portrait to acquire second matching data n 2.
Please refer to fig. 7, which is a flowchart illustrating sub-steps of the second embodiment provided in step S111 of the method for applying for image quality inspection of a credit card according to the embodiment of the present invention, including steps S19-S21.
And step S19, performing grid removing processing on the service personnel identification card image and the group photo image to obtain a grid-removed service personnel identification card image and a grid-removed group photo image.
And step S20, performing head portrait matting on the gridded business person ID card image to obtain a business person head portrait.
And step S21, pairing the head portrait of the service staff with the customer image of the grid-removed group photo image to obtain the second matching score. In some possible embodiments, the business person head portrait is compared with the business person head portrait in the group photo image based on human face features, wherein the human face features comprise facial scale features, human face contour features, iris features and the like, and the second matching score of the comparison is marked as n 2.
Please refer to fig. 8, which is a flowchart illustrating the sub-steps of step S21 in the method for applying for image quality inspection of a credit card according to the first embodiment of the present invention, including steps S22-S24.
And step 22, matting the group photo image to form a first head portrait and a second head portrait.
And step 23, comparing the head portraits of the business personnel with the first head portraits and the second head portraits one by one. In this step, the obtained head portraits of the service personnel are compared with the first head portraits and the second head portraits one by one. For example, the comparison may be performed based on the face features, and in some feasible embodiments, if the face contour is used as the comparison condition, the face contour of the business person avatar is compared with the face contour of the first avatar, and the face contour of the business person avatar is compared with the face contour of the second avatar.
And step 24, taking the score with the highest score as the second matching score. In this step, based on step S23, the results of the one-to-one comparison are compared to obtain the highest score as the first matching score n 1.
Please refer to fig. 9, which is a schematic diagram illustrating an internal structure of a server of an image quality inspection system for applying for a credit card according to an embodiment of the present invention. The server 20 includes a memory 201 for storing program instructions for a credit card image quality inspection method and a processor 202 for executing the program instructions to cause the quality inspection system 100 to implement the credit card image quality inspection method described above.
The server 20 includes a memory 201 and a processor. The memory 201 includes at least one type of readable storage medium, which includes flash memory, hard disk, multimedia card, card type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, and the like. The memory 201 may be used not only to store application software installed in the quality inspection system 100 and various types of data, for example, a control instruction of an image quality inspection system applying for a credit card, etc., but also to temporarily store data that has been output or is to be output.
The quality inspection data are obtained by obtaining the identity card images of the client and the business personnel and comparing the obtained identity card images with the group photo images of the client and the business personnel, and the conclusion whether manual quality inspection needs to be intervened is obtained by comparing the quality inspection data with the preset threshold value.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, insofar as these modifications and variations of the invention fall within the scope of the claims of the invention and their equivalents, the invention is intended to include these modifications and variations.
The above-mentioned embodiments are only examples of the present invention, which should not be construed as limiting the scope of the present invention, and therefore, the present invention is not limited by the claims.
Claims (10)
1. The image quality inspection method for applying for the credit card is characterized by comprising the following steps:
responding a login request of a user sent by a client to log in, wherein the login request at least comprises an account number of a service worker;
acquiring a customer identity card image sent by the client;
acquiring an identity card image of a service person from a database according to an account number of the service person;
acquiring a group photo image of a client and a service worker sent by the client;
matching the customer identity card image with the group photo image to obtain a first matching score;
matching the business person identification card image with the group photo image to obtain a second matching score;
determining a quality inspection result according to the first matching score and the second matching score, wherein the quality inspection result comprises quality inspection passing and quality inspection failing;
and when the quality inspection fails, prompting manual intervention quality inspection.
2. The image quality inspection method for applying for the credit card according to claim 1, wherein the customer identification card image and the business person identification card image are mesh images, and the pairing of the customer identification card image and the group photo image to obtain the first matching score specifically comprises:
grid removing processing is carried out on the customer identity card image to obtain a customer identity card image after grid removing;
performing head portrait cutout on the client identity card image subjected to grid removal to obtain a client head portrait;
inputting the client head portrait and the group photo image into a preset recognition model for operation to obtain a first matching score, wherein the preset recognition model is obtained by training an identity card head portrait training set and a character image training set, and each head portrait of the identity card head portrait training set corresponds to one image and a plurality of images in the character image training set.
3. The image quality inspection method for applying for the credit card according to claim 1, wherein the customer identification card image and the group photo image are mesh images, and the pairing of the customer identification card image and the group photo image to obtain the first matching score specifically comprises:
grid removing processing is carried out on the customer identity card image and the group photo image to obtain a grid-removed customer identity card image and a grid-removed group photo image;
performing head portrait cutout on the client identity card image subjected to grid removal to obtain a client head portrait;
and matching the customer head portrait with the customer image of the grid-removed group photo image to obtain the first matching score.
4. The method of claim 3, wherein matching the customer identification card image with the customer image of the group photo image to obtain a first matching score further comprises:
matting the grid-removed group photo image to form a first head portrait and a second head portrait;
comparing the head portrait of the client with the first head portrait and the second head portrait one by one;
and taking the score with the highest score as the first matching score.
5. The method of claim 1, wherein the step of matching the image of the business person identification card with the image of the group photo to obtain a second matching score comprises:
carrying out grid removing processing on the service personnel identity card image to obtain a grid-removed service personnel identity card image;
performing head portrait cutout on the identity card image of the service personnel after grid removal to obtain a head portrait of the service personnel;
inputting the head portraits of the business personnel and the head portraits of the group photo into a preset recognition model for operation to obtain a second matching score, wherein the preset recognition model is obtained by training an identity card head portraits training set and a character image training set, and each head portraits of the identity card head portraits training set corresponds to one image and a plurality of images in the character image training set.
6. The image quality inspection method for applying for the credit card according to claim 1, wherein the business person identification card image is a grid image, and the matching of the business person identification card image and the group photo image to obtain the second matching score specifically comprises:
carrying out grid removing treatment on the service personnel identity card image and the group photo image to obtain a grid-removed service personnel identity card image and a grid-removed group photo image;
performing head portrait cutout on the identity card image of the service personnel after grid removal to obtain a head portrait of the service personnel;
and matching the head portrait of the business personnel with the customer image of the grid-removed group photo image to obtain the second matching score.
7. The image quality inspection method of claim 6, wherein pairing the business person identification card image with the business person image of the group photo image to obtain a second matching score further comprises:
matting the group photo image to form a first head portrait and a second head portrait;
comparing the head portraits of the business personnel with the first head portraits and the second head portraits one by one;
and taking the score with the highest score as the second matching score.
8. The method of claim 1, wherein the customer identification card image and the group photo image are captured by the client.
9. An image quality inspection system for applying for a credit card, the image quality inspection system for applying for a credit card comprising:
the client is used for receiving an input command of a service worker and sending a service request to the server;
a server, comprising:
a memory for storing computer program instructions; and
a processor for executing the computer program instructions to implement the method of image quality inspection for credit cards according to any one of claims 1 to 8.
10. A server, characterized in that the server comprises:
a memory for storing computer program instructions; and
a processor for executing the computer program instructions to implement the method of applying for image quality inspection of credit cards according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210736851.7A CN115063234A (en) | 2022-06-27 | 2022-06-27 | Image quality inspection method, server and system for credit card application |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210736851.7A CN115063234A (en) | 2022-06-27 | 2022-06-27 | Image quality inspection method, server and system for credit card application |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115063234A true CN115063234A (en) | 2022-09-16 |
Family
ID=83202511
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210736851.7A Pending CN115063234A (en) | 2022-06-27 | 2022-06-27 | Image quality inspection method, server and system for credit card application |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115063234A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115273210A (en) * | 2022-09-30 | 2022-11-01 | 平安银行股份有限公司 | Anti-image-rotation group image recognition method, device, electronic device and medium |
-
2022
- 2022-06-27 CN CN202210736851.7A patent/CN115063234A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115273210A (en) * | 2022-09-30 | 2022-11-01 | 平安银行股份有限公司 | Anti-image-rotation group image recognition method, device, electronic device and medium |
| CN115273210B (en) * | 2022-09-30 | 2022-12-09 | 平安银行股份有限公司 | Method and device for identifying group image resisting image rotation, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9836726B2 (en) | Internet payment system using credit card imaging | |
| US8861861B2 (en) | System and method for processing receipts and other records of users | |
| CN112651841B (en) | Online business handling method, online business handling device, server and computer readable storage medium | |
| CN108667622A (en) | Electron underwriting authentication method, system, computer equipment and storage medium | |
| CN110322317B (en) | Transaction data processing method and device, electronic equipment and medium | |
| US20170103397A1 (en) | Video identification method and computer program product thereof | |
| CN108335196A (en) | Credit card turns on family service implementation method, equipment, system and storage medium | |
| WO2018235055A1 (en) | Facial biometrics card emulation for in-store payment authorization | |
| WO2018184548A1 (en) | Method and device for providing proposed quote for insurance policy, terminal apparatus, and medium | |
| CN108280642A (en) | Debit card Activiation method, equipment, system and computer readable storage medium | |
| US11521209B2 (en) | Systems and methods for automated identity verification | |
| CN112634017A (en) | Remote card opening activation method and device, electronic equipment and computer storage medium | |
| CN112487982A (en) | Merchant information auditing method, system and storage medium | |
| CN115063234A (en) | Image quality inspection method, server and system for credit card application | |
| CN112508621A (en) | Transaction analysis method and device | |
| CN108270789A (en) | Internetbank activating method, equipment, system and computer readable storage medium | |
| CN112633271A (en) | Financial transaction system authentication method based on OCR recognition | |
| US20180060379A1 (en) | Automated correlation and deduplication of identities | |
| US20220414193A1 (en) | Systems and methods for secure adaptive illustrations | |
| CN111461824B (en) | Interface display method, electronic device and computer readable storage medium | |
| US11823139B2 (en) | Image-based transaction processing | |
| CN111770080A (en) | Method and device for recovering device fingerprint | |
| CN115398461A (en) | Credit score management device, credit score management method, and computer-readable recording medium | |
| CN111681745B (en) | Data processing method and device | |
| WO2022065059A1 (en) | Authentication system |
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 |