CN115619410B - Self-adaptive financial payment platform - Google Patents
Self-adaptive financial payment platform Download PDFInfo
- Publication number
- CN115619410B CN115619410B CN202211279940.XA CN202211279940A CN115619410B CN 115619410 B CN115619410 B CN 115619410B CN 202211279940 A CN202211279940 A CN 202211279940A CN 115619410 B CN115619410 B CN 115619410B
- Authority
- CN
- China
- Prior art keywords
- mode
- human face
- image block
- payment
- picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000003044 adaptive effect Effects 0.000 claims abstract description 22
- 230000004069 differentiation Effects 0.000 claims abstract description 16
- 238000001914 filtration Methods 0.000 claims description 61
- 230000007246 mechanism Effects 0.000 claims description 50
- 238000003384 imaging method Methods 0.000 claims description 28
- 238000003062 neural network model Methods 0.000 claims description 16
- 238000000034 method Methods 0.000 claims description 13
- 230000003287 optical effect Effects 0.000 claims description 10
- 230000001960 triggered effect Effects 0.000 claims description 7
- 230000009471 action Effects 0.000 claims description 5
- 230000002146 bilateral effect Effects 0.000 claims description 5
- 210000004709 eyebrow Anatomy 0.000 claims description 5
- 210000004209 hair Anatomy 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000001680 brushing effect Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 210000003128 head Anatomy 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4014—Identity check for transactions
- G06Q20/40145—Biometric identity checks
-
- 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
Abstract
The invention relates to an adaptive financial payment platform, comprising: a differentiation processing part, which is arranged in the financial payment equipment and is used for adopting a face identification mode of a first mode with higher operation complexity when a mask target exists in the received reference image block, or adopting a face identification mode of a second mode; and the payment execution component is used for realizing automatic deduction processing of the corresponding user financial account analyzed by successful authentication based on the face authentication result. The self-adaptive financial payment platform has reliable logic and wide application. Because the face identification environment can be subjected to targeted picture identification when the financial payment is executed, the payment is completed by adopting a complex face identification mode when the face is identified to exist in the mask, and the payment is completed by adopting a traditional simple face identification mode when the face is identified to exist in the mask, so that the safety and the reliability of the financial payment are ensured.
Description
Technical Field
The invention relates to the field of financial payment, in particular to a self-adaptive financial payment platform.
Background
Currently, in addition to the conventional financial payment settlement methods, such as banking intermediate business, third party payment services are adapted to the development of the internet and are prominent in the foreign military, and become an important force in financial payment services.
With the gradual opening of the payment settlement business in the traditional financial field to the third party payment enterprises, the network payment service forms business patterns including the third party payment enterprises, the traditional banks, the huge head of the electronic commerce and the telecom operators, the service bodies and modes in the payment field are more diversified, and the third party payment organization starts to enter the traditional business of the banks and lays a dominant role in the network payment field.
With the coming out of the management method of the internet payment and the bank card order-receiving service field, the industry competition environment tends to be benign and stable, and the third party payment service range basically covers the internet payment, the prepaid card issuing and accepting, the bank card order-receiving, the digital television payment and the mobile phone payment, and the service subdivision industry is continuously expanded from the traditional payment fields of online shopping, aviation, telecommunication and the like to the traditional industry fields of clothing and logistics as representatives.
In the actual operation of financial payments, face-swipe payment is the safest and last authentication mode, which is a key procedure that determines whether payment is successful or whether user can be given payment convenience.
Some related technologies have been disclosed by a main-stream payment platform in China, for example, patent application with application publication number of CN114358792A of Payment treasure (Hangzhou) information technology limited company, an embodiment of the specification provides a face-brushing payment method, a device and face-brushing equipment, wherein in the face-brushing payment method, the face-brushing equipment performs face detection on a first frame image acquired by a camera, if a face is detected, a first face image with image quality larger than or equal to a first quality threshold is cached in an image acquired after the first frame image, and after a face-brushing instruction is detected, a second face image is acquired; if the image quality is smaller than the second quality threshold, the first face image is used for replacing the second face image, and the first face image is displayed in a stop-motion mode, so that when the image quality of the second face image acquired in the acquisition stage is poor, the first face image is used for replacing the second face image, the first face image is identified, further, payment operation is carried out according to the identification result of the first face image, and the image quality of the face image used for face brushing payment is improved.
Another patent application with publication number CN113887451a by the company, an embodiment of the specification provides a picture processing method and apparatus, where the picture processing method includes: selecting a target face based on the face pose and the face position of the candidate face; acquiring two-dimensional face information and face depth information of the target face, and determining three-dimensional depth information of the target face based on the two-dimensional face information and the face depth information; determining state information of the picture acquisition equipment, and adjusting parameters of the picture acquisition equipment based on the three-dimensional depth information of the target face and the state information; and performing follow-up shooting on the target face based on the parameters of the picture acquisition equipment so as to solve the problem that the face brushing machine cannot acquire face information of a user in time or the acquired face information is incomplete and cannot realize the purpose of face brushing payment.
Some science and technology companies have also developed face payment technologies successively, for example, in patent application publication number CN113255587a, and the embodiment of the specification provides a face payment system based on a depth camera, which includes a depth camera module and a mobile phone module: the depth camera module comprises an image acquisition module, a face detection module, a depth reconstruction module and a living body detection module; the image acquisition module is used for acquiring an RGB image, an IR image and an infrared light spot image of the target face; the depth reconstruction module is used for performing depth reconstruction on the target face according to the infrared speckle image and the RGB image to generate a depth face image; the living body detection module is used for carrying out living body detection on any one or more of the infrared light spot image, the IR image and the depth face image, and then outputting a living body face detection result; the mobile phone module is used for receiving the living body face detection result and the face area, identifying the face area when the living body face detection result is passing, and determining and displaying the corresponding payment account information of the face area.
However, in recent years, people need to wear a mask in dangerous payment places with high infection probability to ensure personal safety when brushing the face, and obviously, wearing the mask causes obstruction to face brushing payment, although the face recognition of wearing the mask can be completed by adopting a plurality of more complex authentication modes, if the more complex authentication modes are adopted for financial payment in all occasions, excessive waste of operation resources and excessive use of communication resources are caused.
Disclosure of Invention
In order to solve the technical problems in the related art, the invention provides a self-adaptive financial payment platform which can carry out targeted picture authentication on a face authentication environment when financial payment is carried out so as to complete payment by adopting a complex face authentication mode when a mask is used for authenticating a face, and complete payment by adopting a traditional simple face authentication mode when the mask is not used for authenticating the face, thereby achieving dynamic balance between resource consumption and effective payment.
According to an aspect of the present invention, there is provided an adaptive financial payment platform, the platform comprising:
the wide-angle acquisition mechanism is arranged on the financial payment equipment, and is used for entering a working mode from a dormant mode when receiving a payment request signal triggered manually or electronically by the financial payment equipment, and executing the acquisition action of a payment field picture in the working mode;
a content restoration mechanism, which is arranged in the financial payment equipment, is connected with the wide-angle acquisition mechanism, and is used for executing point image restoration processing on the payment scene based on the optical characteristics of the optical component of the wide-angle acquisition mechanism so as to acquire a corresponding restoration processing picture;
the double-layer quality improving mechanism is connected with the content restoring mechanism and is used for sequentially executing guide filtering operation and bilateral filtering operation on the received restored pictures so as to obtain corresponding customized filtering pictures;
the object selection component is connected with the double-layer quality improving mechanism and is used for identifying each human face image block in the received customized filtering picture and outputting the human face image block closest to the center position of the customized filtering picture in each human face image block as a reference image block;
the differentiation processing part is connected with the object selection part and is used for adopting a face identification mode of a first mode when a mask target exists in the received reference image block and adopting a face identification mode of a second mode when the mask target does not exist in the received reference image block, wherein the operation complexity of the face identification mode of the first mode is greater than that of the face identification mode of the second mode;
the payment execution component is connected with the differentiation processing component and is used for realizing automatic deduction processing of the corresponding user financial account analyzed successfully by the authentication based on the face authentication result of the differentiation processing component in the first mode or the second mode;
the face identification mode of the first mode realizes the face identification operation based on the face outline, the binocular distribution position, the eyebrow part distribution position and the hair distribution level of the human face in the reference image block, and the face identification mode of the second mode realizes the face identification operation based on the binocular distribution position, the nose distribution position and the mouth distribution position of the human face in the reference image block.
The self-adaptive financial payment platform has reliable logic and wide application. Because the face identification environment can be subjected to targeted picture identification when the financial payment is executed, the payment is completed by adopting a complex face identification mode when the face is identified to exist in the mask, and the payment is completed by adopting a traditional simple face identification mode when the face is identified to exist in the mask, so that the safety and the reliability of the financial payment are ensured.
Drawings
Embodiments of the present invention will be described below with reference to the accompanying drawings, in which:
fig. 1 is a block diagram illustrating the structure of an adaptive financial paymate according to an embodiment of the present invention.
Fig. 2 is a block diagram illustrating the structure of an adaptive financial paymate according to an embodiment B of the present invention.
Fig. 3 is a block diagram illustrating the structure of an adaptive financial paymate according to an embodiment of the present invention.
Detailed Description
Embodiments of the adaptive financial paymate of the present invention will be described in detail below with reference to the accompanying drawings.
Embodiment A
Fig. 1 is a block diagram illustrating the architecture of an adaptive financial payment platform according to an embodiment of the present invention, the platform comprising:
the wide-angle acquisition mechanism is arranged on the financial payment equipment, and is used for entering a working mode from a dormant mode when receiving a payment request signal triggered manually or electronically by the financial payment equipment, and executing an acquisition action of a payment scene in the working mode, wherein an imaging visual angle of the wide-angle acquisition mechanism is greater than 120 degrees;
a content restoration mechanism, which is arranged in the financial payment equipment, is connected with the wide-angle acquisition mechanism, and is used for executing point image restoration processing on the payment scene based on the optical characteristics of the optical component of the wide-angle acquisition mechanism so as to acquire a corresponding restoration processing picture;
the double-layer quality improving mechanism is connected with the content restoring mechanism and is used for sequentially executing guide filtering operation and bilateral filtering operation on the received restored pictures so as to obtain corresponding customized filtering pictures;
the object selection component is connected with the double-layer quality improving mechanism and is used for identifying each human face image block in the received customized filtering picture and outputting the human face image block closest to the center position of the customized filtering picture in each human face image block as a reference image block;
the differentiation processing part is connected with the object selection part and is used for adopting a face identification mode of a first mode when a mask target exists in the received reference image block and adopting a face identification mode of a second mode when the mask target does not exist in the received reference image block, wherein the operation complexity of the face identification mode of the first mode is greater than that of the face identification mode of the second mode;
the payment execution component is connected with the differentiation processing component and is used for realizing automatic deduction processing of the corresponding user financial account analyzed successfully by the authentication based on the face authentication result of the differentiation processing component in the first mode or the second mode;
the face identification mode of the first mode realizes face identification operation based on the face outline, the binocular distribution position, the eyebrow distribution position and the hair distribution level of the human face in the reference image block, and the face identification mode of the second mode realizes face identification operation based on the binocular distribution position, the nose distribution position and the mouth distribution position of the human face in the reference image block;
obviously, the operation complexity of the face identification operation based on the face contour, the binocular distribution position, the eyebrow part distribution position and the hair distribution level of the human face in the reference image block is higher than the operation complexity of the face identification operation based on the binocular distribution position, the nose distribution position and the mouth distribution position of the human face in the reference image block.
B embodiment
Fig. 2 is a block diagram illustrating the structure of an adaptive financial paymate according to an embodiment B of the present invention. Unlike fig. 1, the adaptive financial paymate shown in embodiment B of the present invention may include:
the wide-angle acquisition mechanism is arranged on the financial payment equipment, and is used for entering a working mode from a dormant mode when receiving a payment request signal triggered manually or electronically by the financial payment equipment, and executing an acquisition action of a payment scene in the working mode, wherein an imaging visual angle of the wide-angle acquisition mechanism is greater than 120 degrees;
a content restoration mechanism, which is arranged in the financial payment equipment, is connected with the wide-angle acquisition mechanism, and is used for executing point image restoration processing on the payment scene based on the optical characteristics of the optical component of the wide-angle acquisition mechanism so as to acquire a corresponding restoration processing picture;
the double-layer quality improving mechanism is connected with the content restoring mechanism and is used for sequentially executing guide filtering operation and bilateral filtering operation on the received restored pictures so as to obtain corresponding customized filtering pictures;
the object selection component is connected with the double-layer quality improving mechanism and is used for identifying each human face image block in the received customized filtering picture and outputting the human face image block closest to the center position of the customized filtering picture in each human face image block as a reference image block;
the differentiation processing part is connected with the object selection part and is used for adopting a face identification mode of a first mode when a mask target exists in the received reference image block and adopting a face identification mode of a second mode when the mask target does not exist in the received reference image block, wherein the operation complexity of the face identification mode of the first mode is greater than that of the face identification mode of the second mode;
the payment execution component is connected with the differentiation processing component and is used for realizing automatic deduction processing of the corresponding user financial account analyzed successfully by the authentication based on the face authentication result of the differentiation processing component in the first mode or the second mode;
a manual input device, which is arranged on the financial payment equipment and is used for manually triggering the payment request signal based on manual operation of the financial payment equipment;
the manual input device is connected with the wide-angle acquisition mechanism and is used for sending the manually input payment request signal to the wide-angle acquisition mechanism;
wherein the manually entered payment request signal may be transmitted to the wide-angle acquisition mechanism via a wireless communication link.
C embodiment
Fig. 3 is a block diagram illustrating the structure of an adaptive financial paymate according to an embodiment of the present invention. Unlike fig. 1, the adaptive financial paymate shown in the C embodiment of the present invention may include:
the wide-angle acquisition mechanism is arranged on the financial payment equipment, and is used for entering a working mode from a dormant mode when receiving a payment request signal triggered manually or electronically by the financial payment equipment, and executing an acquisition action of a payment scene in the working mode, wherein an imaging visual angle of the wide-angle acquisition mechanism is greater than 120 degrees;
a content restoration mechanism, which is arranged in the financial payment equipment, is connected with the wide-angle acquisition mechanism, and is used for executing point image restoration processing on the payment scene based on the optical characteristics of the optical component of the wide-angle acquisition mechanism so as to acquire a corresponding restoration processing picture;
the double-layer quality improving mechanism is connected with the content restoring mechanism and is used for sequentially executing guide filtering operation and bilateral filtering operation on the received restored pictures so as to obtain corresponding customized filtering pictures;
the object selection component is connected with the double-layer quality improving mechanism and is used for identifying each human face image block in the received customized filtering picture and outputting the human face image block closest to the center position of the customized filtering picture in each human face image block as a reference image block;
the differentiation processing part is connected with the object selection part and is used for adopting a face identification mode of a first mode when a mask target exists in the received reference image block and adopting a face identification mode of a second mode when the mask target does not exist in the received reference image block, wherein the operation complexity of the face identification mode of the first mode is greater than that of the face identification mode of the second mode;
the payment execution component is connected with the differentiation processing component and is used for realizing automatic deduction processing of the corresponding user financial account analyzed successfully by the authentication based on the face authentication result of the differentiation processing component in the first mode or the second mode;
the network transmission device is arranged on the financial payment equipment and is used for electronically triggering the payment request signal based on the network data packet received by the financial payment equipment;
the network transmission device is connected with the wide-angle acquisition mechanism and is used for sending the payment request signal electronically triggered by the network data packet to the wide-angle acquisition mechanism;
wherein electronically triggering the payment request signal based on the network data packet received by the financial payment device includes: the network data packet comprises payment request data, and the payment request signal comprises the payment request data.
Next, a further explanation of the specific structure of the adaptive financial payment platform of the present invention will be continued.
In an adaptive financial paymate according to various embodiments of the present invention:
identifying each human face image block in the received customized filtering picture, and outputting the human face image block closest to the center position of the customized filtering picture in each human face image block as a reference image block comprises the following steps: acquiring the central position of each human face block, and taking the human face block with the central position closest to the central position of the customized filtering picture as the human face image block closest to the central position of the customized filtering picture in the human face image blocks;
the method for obtaining the center position of each human face block, taking the human face block with the center position closest to the center position of the customized filtering picture as the human face image block closest to the center position of the customized filtering picture in the human face image blocks comprises the following steps: taking a pixel point where a centroid of an edge shape of each human face block is located as a first pixel point, taking a pixel point where a center position of the customized filtering picture is located as a second pixel point, and taking the number of the pixel points distributed between the first pixel point and the second pixel point as reference data for judging the distance from the human face block to the center position of the customized filtering picture;
the method for determining the distance from the human face block to the center of the customized filtering picture based on the number of the pixels distributed between the first pixel point and the second pixel point comprises the following steps: the smaller the number of the pixel points distributed between the first pixel point and the second pixel point, the closer the distance from the human face block to the center of the customized filtering picture.
And in an adaptive financial paymate according to various embodiments of the present invention:
identifying each human face image block in the received customized filtering picture, and outputting the human face image block closest to the center position of the customized filtering picture in each human face image block as a reference image block comprises the following steps: performing object type identification on each foreground imaging area in the customized filtering picture by adopting a neural network model, and taking the foreground imaging area identified as a human face image block;
the method for identifying the object type of each foreground imaging area in the customized filtering picture by adopting the neural network model comprises the following steps of: inputting the shape of the region edge of each foreground imaging region into the neural network model and executing the neural network model to obtain the object type of the foreground imaging region output by the neural network model;
the method for identifying the object type of each foreground imaging area in the customized filtering picture by adopting the neural network model, taking the foreground imaging area identified as the human face image block further comprises the following steps: when the object type to which the foreground imaging area output by the neural network model belongs is a human face, identifying the foreground imaging area as the human face;
the method for identifying the object type of each foreground imaging area in the customized filtering picture by adopting the neural network model, taking the foreground imaging area identified as the human face image block further comprises the following steps: and detecting a background sub-picture in the customized filtering picture, taking the customized filtering picture after the background sub-picture is stripped as a front Jing Zi picture, wherein the front Jing Zi picture is composed of a plurality of foreground imaging areas.
In addition, in the adaptive financial payment platform, when the mask target exists in the received reference image block, the face identification mode adopting the first mode is further used for adopting the face identification mode adopting the second mode when the mask target does not exist in the received reference image block, and the face identification mode adopting the second mode comprises: detecting whether a mask target exists in the received reference image block based on the standard outline of the mask, adopting a face identification mode of a first mode when the mask target exists, and adopting a face identification mode of a second mode when the mask target does not exist.
From the above embodiments, the present invention has key technical points in three aspects:
(1) In the process of executing financial payment based on a face identification result, taking a face image block at the middle position as an image block to be identified, switching to a face identification mode of a first mode with higher complexity when a mask object is detected in the image block to be identified, otherwise switching to a face identification mode of a second mode with lower complexity;
(2) The face identification mode of the first mode realizes the face identification operation based on the face outline, the two-eye distribution position, the eyebrow part distribution position and the hair distribution level of the human face in the image block to be identified, and the face identification mode of the second mode realizes the face identification operation based on the two-eye distribution position, the nose distribution position and the mouth distribution position of the human face in the image block to be identified;
(3) The picture content optimization processing before face identification is realized by adopting a targeted picture content optimization mechanism comprising a content restoration mechanism, a double-layer quality improvement mechanism and an object selection component.
The foregoing is merely a specific implementation of the embodiments of the present application, but the protection scope of the embodiments of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the embodiments of the present application should be covered by the protection scope of the embodiments of the present application. Therefore, the protection scope of the embodiments of the present application shall be subject to the protection scope of the claims.
Claims (7)
1. An adaptive financial payment platform, the platform comprising:
the wide-angle acquisition mechanism is arranged on the financial payment equipment, and is used for entering a working mode from a dormant mode when receiving a payment request signal triggered manually or electronically by the financial payment equipment, and executing the acquisition action of a payment field picture in the working mode;
a content restoration mechanism, which is arranged in the financial payment equipment, is connected with the wide-angle acquisition mechanism, and is used for executing point image restoration processing on the payment scene based on the optical characteristics of the optical component of the wide-angle acquisition mechanism so as to acquire a corresponding restoration processing picture;
the double-layer quality improving mechanism is connected with the content restoring mechanism and is used for sequentially executing guide filtering operation and bilateral filtering operation on the received restored pictures so as to obtain corresponding customized filtering pictures;
the object selection component is connected with the double-layer quality improving mechanism and is used for identifying each human face image block in the received customized filtering picture and outputting the human face image block closest to the center position of the customized filtering picture in each human face image block as a reference image block;
the method for identifying each human face image block in the received customized filtering picture, and outputting the human face image block closest to the center position of the customized filtering picture in each human face image block as a reference image block comprises the following steps: acquiring the central position of each human face block, and taking the human face block with the central position closest to the central position of the customized filtering picture as the human face image block closest to the central position of the customized filtering picture in the human face image blocks;
the method for obtaining the center position of each human face block, taking the human face block with the center position closest to the center position of the customized filtering picture as the human face image block closest to the center position of the customized filtering picture in the human face image blocks comprises the following steps: taking a pixel point where a centroid of an edge shape of each human face block is located as a first pixel point, taking a pixel point where a center position of the customized filtering picture is located as a second pixel point, and taking the number of the pixel points distributed between the first pixel point and the second pixel point as reference data for judging the distance from the human face block to the center position of the customized filtering picture;
the method for determining the distance from the human face block to the center of the customized filtering picture based on the number of the pixels distributed between the first pixel point and the second pixel point comprises the following steps: the smaller the number of the pixel points distributed between the first pixel points and the second pixel points, the closer the distance from the human face block to the center of the customized filtering picture;
the differentiation processing part is connected with the object selection part and is used for adopting a face identification mode of a first mode when a mask target exists in the received reference image block and adopting a face identification mode of a second mode when the mask target does not exist in the received reference image block, wherein the operation complexity of the face identification mode of the first mode is greater than that of the face identification mode of the second mode;
when the mask target exists in the received reference image block, the face identification mode adopting the first mode is further used for adopting the face identification mode adopting the second mode when the mask target does not exist in the received reference image block, and the face identification mode adopting the second mode comprises the following steps: detecting whether a mask target exists in the received reference image block based on the standard outline of the mask, adopting a face identification mode of a first mode when the mask target exists, and adopting a face identification mode of a second mode when the mask target does not exist;
the payment execution component is connected with the differentiation processing component and is used for realizing automatic deduction processing of the corresponding user financial account analyzed successfully by the authentication based on the face authentication result of the differentiation processing component in the first mode or the second mode;
the face identification mode of the first mode realizes the face identification operation based on the face outline, the binocular distribution position, the eyebrow part distribution position and the hair distribution level of the human face in the reference image block, and the face identification mode of the second mode realizes the face identification operation based on the binocular distribution position, the nose distribution position and the mouth distribution position of the human face in the reference image block.
2. The adaptive financial payment platform of claim 1, wherein the platform further comprises:
a manual input device, which is arranged on the financial payment equipment and is used for manually triggering the payment request signal based on manual operation of the financial payment equipment;
the manual input device is connected with the wide-angle acquisition mechanism and is used for sending the manually input payment request signal to the wide-angle acquisition mechanism.
3. The adaptive financial payment platform of claim 1, wherein the platform further comprises:
the network transmission device is arranged on the financial payment equipment and is used for electronically triggering the payment request signal based on the network data packet received by the financial payment equipment;
the network transmission device is connected with the wide-angle acquisition mechanism and is used for sending the payment request signal electronically triggered by the network data packet to the wide-angle acquisition mechanism;
wherein electronically triggering the payment request signal based on the network data packet received by the financial payment device includes: the network data packet comprises payment request data, and the payment request signal comprises the payment request data.
4. An adaptive financial payment platform as recited in any one of claims 1 to 3, wherein:
identifying each human face image block in the received customized filtering picture, and outputting the human face image block closest to the center position of the customized filtering picture in each human face image block as a reference image block comprises the following steps: and carrying out object type identification on each foreground imaging area in the customized filtering picture by adopting a neural network model, and taking the foreground imaging area identified as a human face image block.
5. An adaptive financial payment platform as recited in claim 4, wherein:
performing object type identification on each foreground imaging area in the customized filtering picture by adopting a neural network model, and taking the foreground imaging area identified as a human face image block comprises the following steps: the region edge shape of each foreground imaging region is input to the neural network model and the neural network model is executed to obtain the object type to which the foreground imaging region output by the neural network model belongs.
6. An adaptive financial payment platform as recited in claim 5, wherein:
performing object type identification on each foreground imaging area in the customized filtering picture by adopting a neural network model, and taking the foreground imaging area identified as a human face image block further comprises: and when the object type to which the foreground imaging area output by the neural network model belongs is a human face, identifying the foreground imaging area as the human face.
7. An adaptive financial payment platform as recited in claim 6, wherein:
performing object type identification on each foreground imaging area in the customized filtering picture by adopting a neural network model, and taking the foreground imaging area identified as a human face image block further comprises: and detecting a background sub-picture in the customized filtering picture, taking the customized filtering picture after the background sub-picture is stripped as a front Jing Zi picture, wherein the front Jing Zi picture is composed of a plurality of foreground imaging areas.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211279940.XA CN115619410B (en) | 2022-10-19 | 2022-10-19 | Self-adaptive financial payment platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211279940.XA CN115619410B (en) | 2022-10-19 | 2022-10-19 | Self-adaptive financial payment platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115619410A CN115619410A (en) | 2023-01-17 |
| CN115619410B true CN115619410B (en) | 2024-01-26 |
Family
ID=84864407
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211279940.XA Active CN115619410B (en) | 2022-10-19 | 2022-10-19 | Self-adaptive financial payment platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115619410B (en) |
Citations (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006309714A (en) * | 2005-03-31 | 2006-11-09 | Fuji Photo Film Co Ltd | Face discrimination method and device, and program |
| CN101246543A (en) * | 2008-03-18 | 2008-08-20 | 苏州纳米技术与纳米仿生研究所 | Examiner identity appraising system based on bionic and biological characteristic recognition |
| JP2009140423A (en) * | 2007-12-10 | 2009-06-25 | Panasonic Electric Works Co Ltd | Face centerline detecting device |
| CN103824068A (en) * | 2014-03-19 | 2014-05-28 | 上海看看智能科技有限公司 | Human face payment authentication system and method |
| CN104537534A (en) * | 2015-01-20 | 2015-04-22 | 武汉邮电科学研究院 | Facial recognition based mobile phone secure payment system and payment method thereof |
| CN107016370A (en) * | 2017-04-10 | 2017-08-04 | 电子科技大学 | One kind is based on the enhanced partial occlusion face identification method of data |
| CN108305366A (en) * | 2018-02-08 | 2018-07-20 | 深圳汇通智能化科技有限公司 | A kind of intelligent access control system with face identification functions |
| CN108564019A (en) * | 2018-04-08 | 2018-09-21 | 深浅度视觉科技（大连）有限公司 | A kind of face identification method and system |
| CN108664782A (en) * | 2017-03-28 | 2018-10-16 | 三星电子株式会社 | Face verification method and apparatus |
| CN108805040A (en) * | 2018-05-24 | 2018-11-13 | 复旦大学 | It is a kind of that face recognition algorithms are blocked based on piecemeal |
| CN109359618A (en) * | 2018-10-30 | 2019-02-19 | 北京市商汤科技开发有限公司 | A kind of image processing method and its device, equipment and storage medium |
| CN109472579A (en) * | 2018-11-01 | 2019-03-15 | 广东粤迪厚创科技发展有限公司 | A kind of face recognition payment platform |
| CN110942311A (en) * | 2019-11-28 | 2020-03-31 | 中国建设银行股份有限公司 | Payment method, device, equipment and medium |
| CN111241870A (en) * | 2018-11-28 | 2020-06-05 | 深圳市帝迈生物技术有限公司 | Terminal device and face image recognition method and system thereof |
| CN210776998U (en) * | 2020-01-08 | 2020-06-16 | 林希鹏 | Support multiple terminal equipment's polymerization face payment device that brushes |
| CN111444862A (en) * | 2020-03-30 | 2020-07-24 | 深圳信可通讯技术有限公司 | Face recognition method and device |
| CN111539912A (en) * | 2020-03-23 | 2020-08-14 | 中国科学院自动化研究所 | Health index evaluation method and equipment based on face structure positioning and storage medium |
| CN111539386A (en) * | 2020-06-03 | 2020-08-14 | 黑龙江大学 | Identity authentication system integrating fingerprint and face living body detection |
| CN111582090A (en) * | 2020-04-27 | 2020-08-25 | 杭州宇泛智能科技有限公司 | Face recognition method and device and electronic equipment |
| CN111582199A (en) * | 2020-05-12 | 2020-08-25 | 佛山市玖章智能科技有限公司 | Face recognition model training method and face recognition method |
| CN111598047A (en) * | 2020-05-28 | 2020-08-28 | 重庆康普达科技有限公司 | Face recognition method |
| CN111915307A (en) * | 2020-07-02 | 2020-11-10 | 浙江恒科实业有限公司 | Contactless mobile payment system and method |
| CN112115866A (en) * | 2020-09-18 | 2020-12-22 | 北京澎思科技有限公司 | Face recognition method and device, electronic equipment and computer readable storage medium |
| CN112560683A (en) * | 2020-12-16 | 2021-03-26 | 平安科技（深圳）有限公司 | Method and device for identifying copied image, computer equipment and storage medium |
| CN112912893A (en) * | 2021-01-28 | 2021-06-04 | 深圳市锐明技术股份有限公司 | Detection method and device for wearing mask, terminal equipment and readable storage medium |
| CN113095256A (en) * | 2021-04-20 | 2021-07-09 | 北京汽车集团越野车有限公司 | Face recognition method and device |
| CN113095148A (en) * | 2021-03-16 | 2021-07-09 | 深圳市雄帝科技股份有限公司 | Method and system for detecting occlusion of eyebrow area, photographing device and storage medium |
| CN114078270A (en) * | 2020-08-19 | 2022-02-22 | 上海新氦类脑智能科技有限公司 | Human face identity verification method, device, equipment and medium based on shielding environment |
| CN114120426A (en) * | 2021-12-09 | 2022-03-01 | 长讯通信服务有限公司 | Mask face recognition method based on local blocking attention double-branch optimization |
| CN114187644A (en) * | 2021-12-17 | 2022-03-15 | 长讯通信服务有限公司 | Mask face living body detection method based on support vector machine |
| CN114220143A (en) * | 2021-11-26 | 2022-03-22 | 华南理工大学 | Face recognition method for wearing mask |
| CN114241542A (en) * | 2021-09-23 | 2022-03-25 | 广东科学技术职业学院 | Face recognition method based on image stitching |
| CN114359998A (en) * | 2021-12-06 | 2022-04-15 | 江苏理工学院 | Recognition method for face mask in wearing state |
| CN114693987A (en) * | 2020-12-25 | 2022-07-01 | 广州慧睿思通人工智能技术有限公司 | Model generation method, model generation device, storage medium, face recognition method and face recognition device |
| CN114943703A (en) * | 2022-05-24 | 2022-08-26 | 闫雪 | Multi-component P map region analysis system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7860280B2 (en) * | 2006-06-09 | 2010-12-28 | Samsung Electronics Co., Ltd. | Facial feature detection method and device |
| JPWO2016203536A1 (en) * | 2015-06-16 | 2018-03-29 | オリンパス株式会社 | Arithmetic method, arithmetic program, and imaging apparatus |
-
2022
- 2022-10-19 CN CN202211279940.XA patent/CN115619410B/en active Active
Patent Citations (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006309714A (en) * | 2005-03-31 | 2006-11-09 | Fuji Photo Film Co Ltd | Face discrimination method and device, and program |
| JP2009140423A (en) * | 2007-12-10 | 2009-06-25 | Panasonic Electric Works Co Ltd | Face centerline detecting device |
| CN101246543A (en) * | 2008-03-18 | 2008-08-20 | 苏州纳米技术与纳米仿生研究所 | Examiner identity appraising system based on bionic and biological characteristic recognition |
| CN103824068A (en) * | 2014-03-19 | 2014-05-28 | 上海看看智能科技有限公司 | Human face payment authentication system and method |
| CN104537534A (en) * | 2015-01-20 | 2015-04-22 | 武汉邮电科学研究院 | Facial recognition based mobile phone secure payment system and payment method thereof |
| CN108664782A (en) * | 2017-03-28 | 2018-10-16 | 三星电子株式会社 | Face verification method and apparatus |
| CN107016370A (en) * | 2017-04-10 | 2017-08-04 | 电子科技大学 | One kind is based on the enhanced partial occlusion face identification method of data |
| CN108305366A (en) * | 2018-02-08 | 2018-07-20 | 深圳汇通智能化科技有限公司 | A kind of intelligent access control system with face identification functions |
| CN108564019A (en) * | 2018-04-08 | 2018-09-21 | 深浅度视觉科技（大连）有限公司 | A kind of face identification method and system |
| CN108805040A (en) * | 2018-05-24 | 2018-11-13 | 复旦大学 | It is a kind of that face recognition algorithms are blocked based on piecemeal |
| CN109359618A (en) * | 2018-10-30 | 2019-02-19 | 北京市商汤科技开发有限公司 | A kind of image processing method and its device, equipment and storage medium |
| CN109472579A (en) * | 2018-11-01 | 2019-03-15 | 广东粤迪厚创科技发展有限公司 | A kind of face recognition payment platform |
| CN111241870A (en) * | 2018-11-28 | 2020-06-05 | 深圳市帝迈生物技术有限公司 | Terminal device and face image recognition method and system thereof |
| CN110942311A (en) * | 2019-11-28 | 2020-03-31 | 中国建设银行股份有限公司 | Payment method, device, equipment and medium |
| CN210776998U (en) * | 2020-01-08 | 2020-06-16 | 林希鹏 | Support multiple terminal equipment's polymerization face payment device that brushes |
| CN111539912A (en) * | 2020-03-23 | 2020-08-14 | 中国科学院自动化研究所 | Health index evaluation method and equipment based on face structure positioning and storage medium |
| CN111444862A (en) * | 2020-03-30 | 2020-07-24 | 深圳信可通讯技术有限公司 | Face recognition method and device |
| CN111582090A (en) * | 2020-04-27 | 2020-08-25 | 杭州宇泛智能科技有限公司 | Face recognition method and device and electronic equipment |
| CN111582199A (en) * | 2020-05-12 | 2020-08-25 | 佛山市玖章智能科技有限公司 | Face recognition model training method and face recognition method |
| CN111598047A (en) * | 2020-05-28 | 2020-08-28 | 重庆康普达科技有限公司 | Face recognition method |
| CN111539386A (en) * | 2020-06-03 | 2020-08-14 | 黑龙江大学 | Identity authentication system integrating fingerprint and face living body detection |
| CN111915307A (en) * | 2020-07-02 | 2020-11-10 | 浙江恒科实业有限公司 | Contactless mobile payment system and method |
| CN114078270A (en) * | 2020-08-19 | 2022-02-22 | 上海新氦类脑智能科技有限公司 | Human face identity verification method, device, equipment and medium based on shielding environment |
| CN112115866A (en) * | 2020-09-18 | 2020-12-22 | 北京澎思科技有限公司 | Face recognition method and device, electronic equipment and computer readable storage medium |
| CN112560683A (en) * | 2020-12-16 | 2021-03-26 | 平安科技（深圳）有限公司 | Method and device for identifying copied image, computer equipment and storage medium |
| CN114693987A (en) * | 2020-12-25 | 2022-07-01 | 广州慧睿思通人工智能技术有限公司 | Model generation method, model generation device, storage medium, face recognition method and face recognition device |
| CN112912893A (en) * | 2021-01-28 | 2021-06-04 | 深圳市锐明技术股份有限公司 | Detection method and device for wearing mask, terminal equipment and readable storage medium |
| CN113095148A (en) * | 2021-03-16 | 2021-07-09 | 深圳市雄帝科技股份有限公司 | Method and system for detecting occlusion of eyebrow area, photographing device and storage medium |
| CN113095256A (en) * | 2021-04-20 | 2021-07-09 | 北京汽车集团越野车有限公司 | Face recognition method and device |
| CN114241542A (en) * | 2021-09-23 | 2022-03-25 | 广东科学技术职业学院 | Face recognition method based on image stitching |
| CN114220143A (en) * | 2021-11-26 | 2022-03-22 | 华南理工大学 | Face recognition method for wearing mask |
| CN114359998A (en) * | 2021-12-06 | 2022-04-15 | 江苏理工学院 | Recognition method for face mask in wearing state |
| CN114120426A (en) * | 2021-12-09 | 2022-03-01 | 长讯通信服务有限公司 | Mask face recognition method based on local blocking attention double-branch optimization |
| CN114187644A (en) * | 2021-12-17 | 2022-03-15 | 长讯通信服务有限公司 | Mask face living body detection method based on support vector machine |
| CN114943703A (en) * | 2022-05-24 | 2022-08-26 | 闫雪 | Multi-component P map region analysis system |
Non-Patent Citations (1)
| Title |
|---|
| 分块LBP的素描人脸识别;周汐 等;中国图象图形学报;第20卷(第01期);50-58 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115619410A (en) | 2023-01-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102663444B (en) | Method for preventing account number from being stolen and system thereof | |
| US7486806B2 (en) | Iris encoding method, individual authentication method, iris code registration device, iris authentication device, and iris authentication program | |
| CN103383723B (en) | Method and system for spoof detection for biometric authentication | |
| CN108470169A (en) | Face identification system and method | |
| CN113361349B (en) | Face living body detection method, device, electronic equipment and storage medium | |
| CN107463818B (en) | Unlocking control method and related product | |
| CN107292150A (en) | Save user identification confirmation method and apparatus in information processing from damage | |
| CN111160202B (en) | Identity verification method, device, equipment and storage medium based on AR equipment | |
| CN103577801A (en) | Quality metrics method and system for biometric authentication | |
| EP3061023A1 (en) | A method and a system for performing 3d-based identity verification of individuals with mobile devices | |
| CN107506708B (en) | Unlocking control method and related product | |
| WO2023202400A1 (en) | Training method and apparatus for segmentation model, and image recognition method and apparatus | |
| EP4131061A1 (en) | Vehicle loss assessment method, vehicle loss assessment apparatus, and electronic device using same | |
| CN111444830A (en) | Imaging method and device based on ultrasonic echo signal, storage medium and electronic device | |
| CN115619410B (en) | Self-adaptive financial payment platform | |
| CN113221767A (en) | Method for training living body face recognition model and method for recognizing living body face and related device | |
| CN103634557A (en) | Image processing method and apparatus for personal protection in video call | |
| EP3872753B1 (en) | Wrinkle detection method and terminal device | |
| CN115984973A (en) | Human body abnormal behavior monitoring method for peeping-proof screen | |
| CN115937938A (en) | Training method of face identity recognition model, face identity recognition method and device | |
| JP2005149145A (en) | Object detecting device and method, and computer program | |
| CN106845407A (en) | The many fingerprint sync extracting methods of mobile phone camera and system | |
| KR102151851B1 (en) | Face recognition method based on infrared image and learning method for the same | |
| WO2020232889A1 (en) | Check encashment method, apparatus and device, and computer-readable storage medium | |
| CN105139254A (en) | Earprint recognition-based bank remote identity authentication method and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |