CN103824068A - Human face payment authentication system and method - Google Patents
Human face payment authentication system and method Download PDFInfo
- Publication number
- CN103824068A CN103824068A CN201410101181.7A CN201410101181A CN103824068A CN 103824068 A CN103824068 A CN 103824068A CN 201410101181 A CN201410101181 A CN 201410101181A CN 103824068 A CN103824068 A CN 103824068A
- Authority
- CN
- China
- Prior art keywords
- face
- data
- recognition
- information
- payment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000013441 quality evaluation Methods 0.000 claims abstract description 60
- 230000001815 facial effect Effects 0.000 claims description 91
- 238000000605 extraction Methods 0.000 claims description 19
- 230000008878 coupling Effects 0.000 claims description 17
- 238000010168 coupling process Methods 0.000 claims description 17
- 238000005859 coupling reaction Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 15
- 238000013459 approach Methods 0.000 claims description 10
- 239000000284 extract Substances 0.000 claims description 9
- 238000012550 audit Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 8
- 238000007726 management method Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 8
- 230000015572 biosynthetic process Effects 0.000 claims description 6
- 210000001747 pupil Anatomy 0.000 claims description 6
- 238000001303 quality assessment method Methods 0.000 claims description 6
- 238000003786 synthesis reaction Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 abstract description 3
- 230000036544 posture Effects 0.000 abstract 3
- 238000013480 data collection Methods 0.000 abstract 1
- 238000011156 evaluation Methods 0.000 abstract 1
- 238000012216 screening Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 11
- 238000011161 development Methods 0.000 description 4
- 239000000203 mixture Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000003672 processing method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
Images
Landscapes
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a human face payment authentication system and method. The human face payment authentication system comprises a human face original data binding module, a face quality evaluation module, a face posture correction module, a human face recognition module and a payment data intelligent treatment module, wherein the human face original data binding module uses standard user face information as original binding data; the face quality evaluation module is used for performing comprehensive quality evaluation of data collection faces and screening comparison data; the face posture correction module is used for correcting deviated postures on the premise that the face data is not lost; the human face recognition module is used for collecting information of human faces needing to be compared, extracting face feature information and comparing the face feature information with corresponding face feature information in a database so as to judge whether the feature information belongs to the same person; the payment data intelligent treatment module is used for performing comprehensive evaluation and judgment on human face information after human face payment authentication transaction is successful. The human face payment authentication system and method provided by the invention can be used for improving the safety and convenience of payment, and meanwhile, the recognition accuracy of the system is improved.
Description
Technical field
The invention belongs to payment authentication and face recognition technology field, relate to a kind of payment authentication system, relate in particular to a kind of face payment authentication system; Meanwhile, the invention still further relates to a kind of face payment authentication method.
Background technology
The face recognition technology of China, since the development of late nineteen nineties in last century, is experiencing the exploration of more than ten years, is studying, puts into practice, trying commercialization and commercialization, up to the present, and the continuous maturation of face recognition technology level,
Police field is widely used, carry out in registered permanent residence clean-up and rectification work the Ministry of Public Security in 2014 comprehensively, adopt face recognition technology, magnanimity comparison and retrieval are carried out in China second-generation identity card storehouse, find ' the multiple registered permanent residence ' or ' two registered permanent residence ', check and approve and nullify 790,000 repetition registereds permanent residence.
The more and more fields such as security protection, gate inhibition, building, welfare, ecommerce that are applied to of face recognition technology, especially in payment technical field development rapidly.Uniqul venture company of Finland in 2013, release is a payment platform based on face identification system, this system does not need wallet, credit card or mobile phone, only need to be in the face of the camera on POS machine screen when payment, system can be associated consumer's facial information automatically with personal account, whole process of exchange is very convenient.Meanwhile, the PayPal of payment company under Zoomlion eBay announces, releases the payment system of dependence " recognition of face " in 12 markets in the Richmond district of road by the Thames, London.In Japan, equally there is sub-fraction company to bring into use recognition of face software to carry out various transaction.This practice has allowed " swiping the card " consumption in nearly 10 years popular and has changed " brush face " consumption into, overturns traditional modes of payments, and brush face convenient, fast, simple, fashion becomes a kind of trend in the future.Existing face pays to be developed gradually, but various countries' development is all different, be mainly face biological characteristic because of population factor, facial characteristics can be had any different.In addition, facial quality evaluation, attitude rectify, face payment transaction data intelligent are because of mankind population reason facial characteristics feature, and the algorithm of processing is completely different, so there is standard and algorithm that face recognition technology is ununified.
The existing shopping modes of payments generally includes the modes such as cash, bank card, credit card, and along with scientific and technological development, mobile payment (as passed through mobile phone) also starts to be widely used for nearest 2 years.But the existing modes of payments has a lot of weak points; As: bank card, the easy stolen brush of credit card, mobile phone also has the risk of stolen fund after losing.Tracing it to its cause, is mainly that the existing modes of payments only has cipher authentication conventionally, and whether the holder that businessman cannot authenticate bank card, mobile phone is me.
Subsequently, there is the mobile-payment system that comprises face authentication function.In mobile-payment system, iOS, Android and Windows Phone that shopper utilizes third party to pay to be provided move application software, near the shop that can seeing on their mobile phone, support " recognition of face " pays.User walks close to behind shop, selects oneself and likes article, and businessman and client examine after personal information, and cashier, for client provides ' brush face ' service, completes process of purchase.User is unique, and what will do is exactly before use the bank account of oneself or credit card to be associated with mobile payment platform.
Mobile payment recognition of face authentication techniques become the major technique of following payment authentication, especially in mobile payment and third party's payment platform field.Also stage in the early stage of the at present domestic research in mobile payment field, run into a lot of problems, as image data quality evaluation in advance, the accuracy of recognition of face degree is low, error rate is high, every compartment time need bind face again, image data must standard prove attitude, the problems such as poor user experience, need to continue technical research, solve all kinds of problems that run into, could finally realize face and pay.
In view of this, nowadays in the urgent need to designing a kind of face payment authentication system, to overcome the above-mentioned defect of the existing modes of payments.
Summary of the invention
Technical matters to be solved by this invention is: a kind of face payment authentication system is provided, makes to gather and transaction data can intelligent processing method and self-teaching, improve the security, the convenience that pay, the degree of accuracy that Hoisting System is identified simultaneously.
In addition, the present invention also provides a kind of face payment authentication method, can improve the security of payment, improves the degree of accuracy of system identification simultaneously.
For solving the problems of the technologies described above, the present invention adopts following technical scheme:
A kind of face payment authentication system, described Verification System comprises:
Face raw data binding module, in order to gather user's human face photo, carrying out facial quality evaluation and facial pose corrects, as original binding data, user's face information and this user are bound, and the face features information of human face photo and extraction is stored in comparison database;
Face quality evaluation unit, in order to the quality that gathers photo is assessed, leading indicator comprises: pixel height, shape of face pixel size, part lack or block, shape of face angle; Shape of face angle refers to and upper and lower, the left and right deviation angle of positive criteria, and facial upward view angle is controlled within 10 °, depression angle is controlled within 15 °, and left and right angle is controlled within 15 °;
Facial pose is corrected unit, in order to gather face by quality evaluation after, the data shape of face angle of foundation, human face photo higher than minimum threshold values is carried out to attitude rectify to a certain degree, guaranteeing under facial raw data prerequisite, adjustment departs from attitude, makes shape of face more approach positive criteria photograph, significantly promotes the accuracy of recognition of face; Attitude rectify is take standard front face according to as benchmark, within automated intelligent is adjusted 5 ° of upward view angles, within 10 ° of depression angles, in 10 °, deflection angle;
Face recognition module, correct in order to human face photo is carried out to facial quality evaluation and facial pose, extract facial characteristics information, and the facial characteristics information extracting is compared with the described facial characteristics information of comparing the corresponding face information in database, determine whether same people;
Payment data intelligent processing module, in order to repeatedly to complete after the face information of face payment transaction, according to quality evaluation standard, comprise gather face light, sharpness, pixel height, hot-tempered point, whether standard front face, feature obvious, transaction data is carried out to quality evaluation, if the quality of the face information of comparison is better than comparing the face information of storing in database, additionally learn, optimize, make this transaction data participate in the self-teaching of face recognition algorithms, and participate in limited authentication comparison, participate in gradually the identification of face payment authentication; To participating in the transaction data of recognition of face, by facial quality evaluation, get involved according to low weights, middle weights, three kinds of ranks of high weight, high weight was got involved after a period of time, repeatedly be better than under original binding face data prerequisite, with raw data exchange weights ratio, then after transaction authentication repeatedly, replace original old data, principle circulation according to this, realizes the self-teaching of face data, optimization, intelligent management face data, optimize original binding data, promote the quality of data;
Wherein, described face recognition module comprises:
Face detecting unit, whether the authentication photo gathering in order to identification is containing complete face;
Face characteristic extraction unit, in order to extract face biological characteristic, record in a particular manner, generates skin detection, for face alignment and coupling provide raw data;
Face alignment and matching unit, according to face characteristic data template, carry out comparison one by one, the coupling of whole each biological characteristic point of face in order to recognition of face core algorithm, finally returns to similar value;
Recognition results unit, whether in order to according to face living things feature recognition algorithm rreturn value, judging and recognizing is same people;
Wherein, described face alignment and matching unit comprise comparer unit, one-to-many comparer unit one to one;
Described comparer one to one unit is in order to after client Real-time Collection human face photo, and the target photo that the human face photo of collection and payment account are bound in advance, carries out recognition of face and comparison, and whether identification is same people, then returns to recognition result;
Described one-to-many comparer unit is in order to carry out high degree of safety Intelligent Recognition, by client Real-time Collection upload pictures, compare with multiple target photos that payment account is bound in advance, traversal one by one, and with reference to the similarity after each comparison, arrange from high low strap successively, for the data of low ratio, adopt again Local Alignment algorithm to compare, comprise eyes, pupil, the bridge of the nose, mouth carries out Local Alignment, then according to all kinds of ratio, identify more accurately by algorithm synthesis, identification and sequence, multi-angle audit determines whether same people, then return to recognition result.
A kind of face payment authentication system, described Verification System comprises:
Face raw data binding module, in order to gather user's human face photo, as original binding data, binds user's face information and this user, and the face features information of human face photo and extraction is stored in comparison database;
Face recognition module, in order to extract the facial characteristics information of the human face photo that needs comparison, and compares the facial characteristics information extracting with the described facial characteristics information of comparing the corresponding face information in database, determine whether same people;
Payment data intelligent processing module, in order to after comparison face information, judges face information, if meet setting requirement, face information is added in described comparison database.
As a preferred embodiment of the present invention, described Verification System also comprises:
Face quality evaluation unit, in order to the quality that gathers photo is assessed, leading indicator comprises: pixel height, shape of face pixel size, part lack or block, shape of face angle; Shape of face angle refers to and upper and lower, the left and right deviation angle of positive criteria, and facial upward view angle is controlled within 10 °, depression angle is controlled within 15 °, and left and right angle is controlled within 15 °;
Facial pose is corrected unit, in order to gather face by quality evaluation after, the data shape of face angle of foundation, human face photo higher than minimum threshold values is carried out to attitude rectify to a certain degree, guaranteeing under facial raw data prerequisite, adjustment departs from attitude, makes shape of face more approach positive criteria photograph, significantly promotes the accuracy of recognition of face; Attitude rectify is take standard front face according to as benchmark, within automated intelligent is adjusted 5 ° of upward view angles, within 10 ° of depression angles, in 10 °, deflection angle.
As a preferred embodiment of the present invention, described payment data intelligent processing module, in order to repeatedly to complete after the face information of face payment transaction, according to quality evaluation standard, comprise and gather face light, sharpness, pixel height, hot-tempered point, whether standard front face, whether feature is obvious, transaction data is carried out to quality evaluation, if the quality of the face information of comparison is better than comparing the face information of storing in database, additionally learn, optimize, make this transaction data participate in the self-teaching of face recognition algorithms, and participate in limited authentication and compare, participate in gradually the identification of face payment authentication,
To participating in the transaction data of recognition of face, by facial quality evaluation, get involved according to low weights, middle weights, three kinds of ranks of high weight, high weight was got involved after a period of time, repeatedly be better than under original binding face data prerequisite, with raw data exchange weights ratio, then after transaction authentication repeatedly, replace original old data, principle circulation according to this, realizes the self-teaching of face data, optimization, intelligent management face data, optimize original binding data, promote the quality of data.
As a preferred embodiment of the present invention, described payment data intelligent processing module comprises:
Quality assessment unit, in order to the face information of described face recognition module identification is carried out to quality judgement, judges whether the quality of face information meets setting requirement;
Face information storage unit, in order to preserve satisfactory face information;
Weight setting unit, carries out weight setting in order to contrast to the face information in database, is high weight by face information setting high quality, in the time of comparison, preferentially compares.
As a preferred embodiment of the present invention, described face recognition module comprises:
Face detecting unit, whether the authentication photo gathering in order to identification is containing complete face;
Face characteristic extraction unit, in order to extract face biological characteristic, record in a particular manner, generates skin detection, for face alignment and coupling provide raw data;
Face alignment and matching unit, according to face characteristic data template, carry out comparison one by one, the coupling of whole each biological characteristic point of face in order to recognition of face core algorithm, finally returns to similar value;
Recognition results unit, whether in order to according to face living things feature recognition algorithm rreturn value, judging and recognizing is same people;
Described face alignment and matching unit comprise that comparer unit is or/and one-to-many comparer unit one to one;
Described comparer one to one unit is in order to after client Real-time Collection human face photo, and the target photo that the human face photo of collection and payment account are bound in advance, carries out recognition of face and comparison, and whether identification is same people, then returns to recognition result;
Described one-to-many comparer unit is in order to carry out high degree of safety Intelligent Recognition, by client Real-time Collection upload pictures, compare with multiple target photos that payment account is bound in advance, traversal one by one, and with reference to the similarity after each comparison, identify more accurately, recognize and sort according to certain algorithm, multi-angle audit determines whether same people then to return to recognition result.
A kind of face payment authentication method, described authentication method comprises the steps:
Face raw data binding step, collection user's face information, as original binding data, binds user's face information and this user, and face information is stored in comparison database;
Recognition of face step, gathers the face information that needs comparison, extracts facial characteristics information, and the facial characteristics information extracting is compared with the described facial characteristics information of comparing the corresponding face information in database, determines whether same people;
Payment data Intelligent treatment step, after comparison face information, judges face information, if meet setting requirement, face information is added in described comparison database.
As a preferred embodiment of the present invention, described authentication method also comprises:
Face quality evaluation step, assesses the quality that gathers photo, and leading indicator comprises: pixel height, shape of face pixel size, part lack or block, shape of face angle; Shape of face angle refers to and upper and lower, the left and right deviation angle of positive criteria, and facial upward view angle is controlled within 10 °, depression angle is controlled within 15 °, and left and right angle is controlled within 15 °;
Facial pose correct step, the face of collection by quality evaluation after, the data shape of face angle of foundation, carries out attitude rectify to a certain degree to the human face photo higher than minimum threshold values, makes shape of face more approach positive criteria photograph, lifting recognition of face accuracy; Attitude rectify is take standard front face according to as benchmark, within automated intelligent is adjusted 5 ° of upward view angles, within 10 ° of depression angles, in 10 °, deflection angle;
As a preferred embodiment of the present invention, in described payment data Intelligent treatment step, repeatedly complete after the face information of face payment transaction, according to quality evaluation standard, comprise and gather face light, sharpness, pixel height, hot-tempered point, whether standard front face, whether feature is obvious, transaction data is carried out to quality evaluation, if the quality of the face information of comparison is better than comparing the face information of storing in database, additionally learn, optimize, make this transaction data participate in the self-teaching of face recognition algorithms, and participate in limited authentication and compare, participate in gradually the identification of face payment authentication, to participating in the transaction data of recognition of face, by facial quality evaluation, get involved according to low weights, middle weights, three kinds of ranks of high weight, high weight was got involved after a period of time, repeatedly be better than under original binding face data prerequisite, with raw data exchange weights ratio, then after transaction authentication repeatedly, replace original old data, principle circulation according to this, realizes the self-teaching of face data, optimization, intelligent management face data, optimize original binding data, promote the quality of data.
As a preferred embodiment of the present invention, described recognition of face step specifically comprises the steps:
Face detecting step, whether the authentication photo that identification gathers is containing complete face;
Face characteristic extraction step, extracts face biological characteristic, and record in a particular manner generates skin detection, for face alignment and coupling provide raw data;
Face alignment with mate step, recognition of face core algorithm, according to face characteristic data template, carries out comparison one by one, the coupling of whole each biological characteristic point of face, finally returns to similar value;
Recognition results step, whether according to face living things feature recognition algorithm rreturn value, judging and recognizing is same people;
Described face alignment with mate step and comprise and compare step one to one or/and one-to-many comparer step;
Described comparison one to one in step, after client Real-time Collection human face photo, the target photo that the human face photo of collection and payment account are bound in advance, carries out recognition of face and comparison, and whether identification is same people, then returns to recognition result;
In described one-to-many comparison step, carry out high degree of safety Intelligent Recognition, by client Real-time Collection upload pictures, compare with multiple target photos that payment account is bound in advance, traversal one by one, and with reference to the similarity after each comparison, arrange from high low strap successively, for the data of low ratio, adopt again Local Alignment algorithm to compare, comprise eyes, pupil, the bridge of the nose, mouth carries out Local Alignment, then according to all kinds of ratio, identify more accurately by algorithm synthesis, identification and sequence, multi-angle audit determines whether same people, then return to recognition result.
Beneficial effect of the present invention is: face payment authentication system and method that the present invention proposes, make to gather and transaction data can intelligent processing method and self-teaching, and improve the security, the convenience that pay, the degree of accuracy that Hoisting System is identified simultaneously.
Accompanying drawing explanation
Fig. 1 is the composition schematic diagram of face payment authentication system of the present invention.
Fig. 2 is the composition schematic diagram figure of face recognition module in Verification System of the present invention.
Fig. 3 is the process flow diagram of face payment authentication method of the present invention.
Fig. 4 is the particular flow sheet of face payment authentication method of the present invention.
Fig. 5 is the particular flow sheet of payment data Intelligent treatment step in authentication method of the present invention.
Embodiment
Describe the preferred embodiments of the present invention in detail below in conjunction with accompanying drawing.
Embodiment mono-
Refer to Fig. 1, the present invention has disclosed a kind of face payment authentication system, and described Verification System comprises: face raw data binding module 1, comparison database 2, facial quality evaluation 3, facial pose are corrected module 4, face recognition module 5, payment data intelligent processing module 6, face acquisition module 7.
[face raw data binding module]
Face raw data binding module 1 is in order to gather user's human face photo, carrying out facial quality evaluation and facial pose corrects, as original binding data, user's face information and this user are bound, and the face features information of human face photo and extraction is stored in comparison database 2.。
[facial quality assessment modules]
Face quality evaluation unit 2, in order to gather human face photo by face acquisition module 7, is assessed the quality that gathers photo, and leading indicator comprises: pixel height, shape of face pixel size, part lack or block, shape of face angle; Shape of face angle refers to and upper and lower, the left and right deviation angle of positive criteria, and facial upward view angle is controlled within 10 °, depression angle is controlled within 15 °, and left and right angle is controlled within 15 °.
[facial pose correction module]
Facial pose correct module 3 in order to gather face by quality evaluation after, the data shape of face angle of foundation, carries out attitude rectify to a certain degree to the human face photo higher than minimum threshold values, makes shape of face more approach positive criteria photograph, lifting recognition of face accuracy; Attitude rectify is take standard front face according to as benchmark, within automated intelligent is adjusted 5 ° of upward view angles, within 10 ° of depression angles, in 10 °, deflection angle.
[face recognition module]
Face recognition module 3, in order to gather the face information that needs comparison, is extracted facial characteristics information, and the facial characteristics information extracting is compared with the described facial characteristics information of comparing the corresponding face information in database, determines whether same people.
Specifically refer to Fig. 2, described face recognition module 5 comprises: face detecting unit 51, face characteristic extraction unit 52, face alignment and matching unit 53, recognition results unit 54.
Whether the authentication photo that face detecting unit 51 gathers in order to identification is containing complete face.
Face characteristic extraction unit 52 is in order to extract face biological characteristic, and record in a particular manner generates skin detection, for face alignment and coupling provide raw data.
Face alignment and matching unit 53 according to face characteristic data template, carry out comparison one by one, the coupling of whole each biological characteristic point of face in order to recognition of face core algorithm, finally return to similar value.Described face alignment and matching unit 53 comprise that comparer unit is or/and one-to-many comparer unit one to one.Described comparer one to one unit is in order to after client Real-time Collection human face photo, and the target photo that the human face photo of collection and payment account are bound in advance, carries out recognition of face and comparison, and whether identification is same people, then returns to recognition result.Described one-to-many comparer unit is in order to carry out high degree of safety Intelligent Recognition, by client Real-time Collection upload pictures, compare with multiple target photos that payment account is bound in advance, traversal one by one, and with reference to the similarity after each comparison, arrange from high low strap successively, for the data of low ratio, adopt again Local Alignment algorithm to compare, comprise eyes, pupil, the bridge of the nose, mouth carries out Local Alignment, then according to all kinds of ratio, identify more accurately by algorithm synthesis, identification and sequence, multi-angle audit determines whether same people, then return to recognition result.
[payment data intelligent processing module]
Refer to Fig. 5, payment data intelligent processing module 6 is in order to repeatedly to complete after the face information of face payment transaction, according to quality evaluation standard, comprise and gather face light, sharpness, pixel height, hot-tempered point, whether standard front face, whether feature is obvious, transaction data is carried out to quality evaluation, if the quality of the face information of comparison is better than comparing the face information of storing in database, additionally learn, optimize, make this transaction data participate in the self-teaching of face recognition algorithms, and participate in limited authentication and compare, participate in gradually the identification of face payment authentication, to participating in the transaction data of recognition of face, by facial quality evaluation, get involved according to low weights, middle weights, three kinds of ranks of high weight, high weight was got involved after a period of time, repeatedly be better than under original binding face data prerequisite, with raw data exchange weights ratio, then after transaction authentication repeatedly, replace original old data, principle circulation according to this, realizes the self-teaching of face data, optimization, intelligent management face data, optimize original binding data, promote the quality of data.
More than introduced the composition of face payment authentication system of the present invention, the present invention, in disclosing said system composition, also discloses a kind of face payment authentication method; Refer to Fig. 3, Fig. 4, described authentication method comprises the steps:
[step S0] face raw data binding step, gather user's human face photo, carrying out facial quality evaluation and facial pose corrects, as original binding data, user's face information and this user are bound, and the face features information of human face photo and extraction is stored in comparison database.
[step S1] face acquisition step, gathers human face photo by camera head.After the binding of face raw data, can carry out follow-up recognition of face, payment process.
[step S2] facial quality evaluation step, assesses the quality that gathers photo, and leading indicator comprises: pixel height, shape of face pixel size, part lack or block, shape of face angle; Shape of face angle refers to and upper and lower, the left and right deviation angle of positive criteria, and facial upward view angle is controlled within 10 °, depression angle is controlled within 15 °, and left and right angle is controlled within 15 °.
[step S3] facial pose is corrected step, gather face by quality evaluation after, the data shape of face angle of foundation, carries out attitude rectify to a certain degree to the human face photo higher than minimum threshold values, make shape of face more approach positive criteria photograph, promote the accuracy of recognition of face; Attitude rectify is take standard front face according to as benchmark, within automated intelligent is adjusted 5 ° of upward view angles, within 10 ° of depression angles, in 10 °, deflection angle.
[step S4] recognition of face step, gathers the face information that needs comparison, extracts facial characteristics information, and the facial characteristics information extracting is compared with the described facial characteristics information of comparing the corresponding face information in database, determines whether same people.Described recognition of face step specifically comprises the steps:
Step S41, face detecting step, whether the authentication photo that identification gathers is containing complete face;
Step S42, face characteristic extraction step, extract face biological characteristic, and record in a particular manner generates skin detection, for face alignment and coupling provide raw data;
Step S43, face alignment and mate step, recognition of face core algorithm, according to face characteristic data template, carries out comparison one by one, the coupling of whole each biological characteristic point of face, finally returns to similar value;
Described step S43 face alignment with mate step and comprise and compare step one to one or/and one-to-many comparer step.Described comparison one to one in step, after client Real-time Collection human face photo, the target photo that the human face photo of collection and payment account are bound in advance, carries out recognition of face and comparison, and whether identification is same people, then returns to recognition result.In described one-to-many comparison step, carry out high degree of safety Intelligent Recognition, by client Real-time Collection upload pictures, compare with multiple target photos that payment account is bound in advance, traversal one by one, and with reference to the similarity after each comparison, arrange from high low strap successively, for the data of low ratio, adopt again Local Alignment algorithm to compare, comprise eyes, pupil, the bridge of the nose, mouth carries out Local Alignment, then according to all kinds of ratio, identify more accurately by algorithm synthesis, identification and sequence, multi-angle audit determines whether same people, then return to recognition result.
Step S44, recognition results step, whether according to face living things feature recognition algorithm rreturn value, judging and recognizing is same people.
[step S5] payment data Intelligent treatment step, after comparison face information, judges face information, if meet setting requirement, face information is added in described comparison database.
Refer to Fig. 5, particularly, repeatedly complete after the face information of face payment transaction, according to quality evaluation standard, comprise gather face light, sharpness, pixel height, hot-tempered point, whether standard front face, feature obvious, transaction data is carried out to quality evaluation, if the quality of the face information of comparison is better than comparing the face information of storing in database, additionally learn, optimize, make this transaction data participate in the self-teaching of face recognition algorithms, and participate in limited authentication comparison, participate in gradually the identification of face payment authentication; To participating in the transaction data of recognition of face, by facial quality evaluation, get involved according to low weights, middle weights, three kinds of ranks of high weight, high weight was got involved after a period of time, repeatedly be better than under original binding face data prerequisite, with raw data exchange weights ratio, then after transaction authentication repeatedly, replace original old data, principle circulation according to this, realizes the self-teaching of face data, optimization, intelligent management face data, optimize original binding data, promote the quality of data.
Embodiment bis-
In the present embodiment, face payment authentication system comprises: face raw data binding module, facial quality evaluation, facial pose are corrected module, face recognition module, payment data intelligent processing module.
Face raw data binding module is in order to gather user's human face photo, carrying out facial quality evaluation and facial pose corrects, as original binding data, user's face information and this user are bound, and the face features information of human face photo and extraction is stored in comparison database.
Face quality evaluation unit is in order to assess the quality that gathers photo, and leading indicator comprises: pixel height, shape of face pixel size, part lack or block, shape of face angle; Shape of face angle refers to and upper and lower, the left and right deviation angle of positive criteria, and facial upward view angle is controlled within 10 °, depression angle is controlled within 15 °, and left and right angle is controlled within 15 °.
Facial pose correct module in order to gather face by quality evaluation after, the data shape of face angle of foundation, carries out attitude rectify to a certain degree to the human face photo higher than minimum threshold values, makes shape of face more approach positive criteria photograph, lifting recognition of face accuracy; Attitude rectify is take standard front face according to as benchmark, within automated intelligent is adjusted 5 ° of upward view angles, within 10 ° of depression angles, in 10 °, deflection angle.
Face recognition module needs the facial characteristics information of the human face photo of comparison in order to extraction, and the facial characteristics information extracting is compared with the described facial characteristics information of comparing the corresponding face information in database, determines whether same people.
Payment data intelligent processing module in order to after comparison face information, judges face information, if meet setting requirement, face information is added in described comparison database.
Wherein, described payment data intelligent processing module comprises: quality assessment unit, face information storage unit, weight setting unit.
Quality assessment unit, in order to the face information of described face recognition module identification is carried out to quality judgement, judges whether the quality of face information meets setting requirement.
Face information storage unit is in order to preserve satisfactory face information.Certainly, can also delete the corresponding face information being replaced simultaneously.
Weight setting unit carries out weight setting in order to contrast to the face information in database, is high weight by face information setting high quality, in the time of comparison, preferentially compares.
The present invention also discloses a kind of face payment authentication method, and described authentication method comprises the steps:
Face raw data binding step, gather user's human face photo, carry out facial quality evaluation and facial pose and correct, as original binding data, user's face information and this user are bound, and the face features information of human face photo and extraction is stored in comparison database.
Face quality evaluation step, assesses the quality that gathers photo, and leading indicator comprises: pixel height, shape of face pixel size, part lack or block, shape of face angle; Shape of face angle refers to and upper and lower, the left and right deviation angle of positive criteria, and facial upward view angle is controlled within 10 °, depression angle is controlled within 15 °, and left and right angle is controlled within 15 °.
Facial pose correct step, the face of collection by quality evaluation after, the data shape of face angle of foundation, carries out attitude rectify to a certain degree to the human face photo higher than minimum threshold values, makes shape of face more approach positive criteria photograph, lifting recognition of face accuracy; Attitude rectify is take standard front face according to as benchmark, within automated intelligent is adjusted 5 ° of upward view angles, within 10 ° of depression angles, in 10 °, deflection angle.
Recognition of face step, extracts the facial characteristics information of the human face photo that needs comparison, and the facial characteristics information extracting is compared with the described facial characteristics information of comparing the corresponding face information in database, determines whether same people;
Payment data Intelligent treatment step, after comparison face information, judges face information, if meet setting requirement, face information is added in described comparison database.
Wherein, described payment data Intelligent treatment step comprises:
Quality assessment step, carries out quality judgement to the face information of described recognition of face step identification, judges whether the quality of face information meets setting requirement;
Face information is preserved step, preserves satisfactory face information;
Weight setting step, contrast is carried out weight setting to the face information in database, is high weight by face information setting high quality, in the time of comparison, preferentially compares.
In sum, face payment authentication system and method that the present invention proposes, can improve the security of payment, improves the degree of accuracy of system identification simultaneously.The present invention still with regard to data identification recognizes after can effectively avoiding user to use for a long time face to pay, along with the variation of shape of face outward appearance, can affect recognition effect and user's experience.
Face payment authentication system is based on mobile Internet medium, the payment authentication system that combines with face biological identification technology, and this system provides a set of full authentication system for payment authentication.
System of the present invention utilizes intelligent terminal (mobile phone, panel computer, handheld terminal etc.) to gather user's human face photo, by face detect, the technology such as facial quality evaluation, attitude rectify, facial feature extraction, face alignment and coupling, carry out users consistency checking with the original face data of user's binding, using this biological characteristic of face as identity ID, encrypt payment transaction.For consumer, businessman provide convenient, quick, safe payment technology.
Here description of the invention and application is illustrative, not wants scope of the present invention to limit in the above-described embodiments.Here the distortion of disclosed embodiment and change is possible, and for those those of ordinary skill in the art, the various parts of the replacement of embodiment and equivalence are known.Those skilled in the art are noted that in the situation that not departing from spirit of the present invention or essential characteristic, and the present invention can be with other form, structure, layout, ratio, and realize with other assembly, material and parts.In the situation that not departing from the scope of the invention and spirit, can carry out other distortion and change to disclosed embodiment here.
Claims (10)
1. a face payment authentication system, is characterized in that, described Verification System comprises:
Face raw data binding module, in order to gather user's human face photo, carrying out facial quality evaluation and facial pose corrects, as original binding data, user's face information and this user are bound, and the face features information of human face photo and extraction is stored in comparison database;
Face quality evaluation unit, in order to the quality that gathers photo is assessed, leading indicator comprises: pixel height, shape of face pixel size, part lack or block, shape of face angle; Shape of face angle refers to and upper and lower, the left and right deviation angle of positive criteria, and facial upward view angle is controlled within 10 °, depression angle is controlled within 15 °, and left and right angle is controlled within 15 °;
Facial pose is corrected unit, in order to gather face by quality evaluation after, the data shape of face angle of foundation, human face photo higher than minimum threshold values is carried out to attitude rectify to a certain degree, guaranteeing under facial raw data prerequisite, adjustment departs from attitude, makes shape of face more approach positive criteria photograph, significantly promotes the accuracy of recognition of face; Attitude rectify is take standard front face according to as benchmark, within automated intelligent is adjusted 5 ° of upward view angles, within 10 ° of depression angles, in 10 °, deflection angle;
Face recognition module, correct in order to human face photo is carried out to facial quality evaluation and facial pose, extract facial characteristics information, and the facial characteristics information extracting is compared with the described facial characteristics information of comparing the corresponding face information in database, determine whether same people;
Payment data intelligent processing module, in order to repeatedly to complete after the face information of face payment transaction, according to quality evaluation standard, comprise gather face light, sharpness, pixel height, hot-tempered point, whether standard front face, feature obvious, transaction data is carried out to quality evaluation, if the quality of the face information of comparison is better than comparing the face information of storing in database, additionally learn, optimize, make this transaction data participate in the self-teaching of face recognition algorithms, and participate in limited authentication comparison, participate in gradually the identification of face payment authentication; To participating in the transaction data of recognition of face, by facial quality evaluation, get involved according to low weights, middle weights, three kinds of ranks of high weight, high weight was got involved after a period of time, repeatedly be better than under original binding face data prerequisite, with raw data exchange weights ratio, then after transaction authentication repeatedly, replace original old data, principle circulation according to this, realizes the self-teaching of face data, optimization, intelligent management face data, optimize original binding data, promote the quality of data;
Wherein, described face recognition module comprises:
Face detecting unit, whether the authentication photo gathering in order to identification is containing complete face;
Face characteristic extraction unit, in order to extract face biological characteristic, record in a particular manner, generates skin detection, for face alignment and coupling provide raw data;
Face alignment and matching unit, according to face characteristic data template, carry out comparison one by one, the coupling of whole each biological characteristic point of face in order to recognition of face core algorithm, finally returns to similar value;
Recognition results unit, whether in order to according to face living things feature recognition algorithm rreturn value, judging and recognizing is same people;
Wherein, described face alignment and matching unit comprise comparer unit, one-to-many comparer unit one to one;
Described comparer one to one unit is in order to after client Real-time Collection human face photo, and the target photo that the human face photo of collection and payment account are bound in advance, carries out recognition of face and comparison, and whether identification is same people, then returns to recognition result;
Described one-to-many comparer unit is in order to carry out high degree of safety Intelligent Recognition, by client Real-time Collection upload pictures, compare with multiple target photos that payment account is bound in advance, traversal one by one, and with reference to the similarity after each comparison, arrange from high low strap successively, for the data of low ratio, adopt again Local Alignment algorithm to compare, comprise eyes, pupil, the bridge of the nose, mouth carries out Local Alignment, then according to all kinds of ratio, identify more accurately by algorithm synthesis, identification and sequence, multi-angle audit determines whether same people, then return to recognition result.
2. a face payment authentication system, is characterized in that, described Verification System comprises:
Face raw data binding module, in order to gather user's human face photo, as original binding data, binds user's face information and this user, and the face features information of human face photo and extraction is stored in comparison database;
Face recognition module, in order to extract the facial characteristics information of the human face photo that needs comparison, and compares the facial characteristics information extracting with the described facial characteristics information of comparing the corresponding face information in database, determine whether same people;
Payment data intelligent processing module, in order to after comparison face information, judges face information, if meet setting requirement, face information is added in described comparison database.
3. face payment authentication system according to claim 2, is characterized in that:
Described Verification System also comprises:
Face quality evaluation unit, in order to the quality that gathers photo is assessed, leading indicator comprises: pixel height, shape of face pixel size, part lack or block, shape of face angle; Shape of face angle refers to and upper and lower, the left and right deviation angle of positive criteria, and facial upward view angle is controlled within 10 °, depression angle is controlled within 15 °, and left and right angle is controlled within 15 °;
Facial pose is corrected unit, in order to gather face by quality evaluation after, the data shape of face angle of foundation, human face photo higher than minimum threshold values is carried out to attitude rectify to a certain degree, guaranteeing under facial raw data prerequisite, adjustment departs from attitude, makes shape of face more approach positive criteria photograph, significantly promotes the accuracy of recognition of face; Attitude rectify is take standard front face according to as benchmark, within automated intelligent is adjusted 5 ° of upward view angles, within 10 ° of depression angles, in 10 °, deflection angle.
4. face payment authentication system according to claim 2, is characterized in that:
Described payment data intelligent processing module, in order to repeatedly to complete after the face information of face payment transaction, according to quality evaluation standard, comprise gather face light, sharpness, pixel height, hot-tempered point, whether standard front face, feature obvious, transaction data is carried out to quality evaluation, if the quality of the face information of comparison is better than comparing the face information of storing in database, additionally learn, optimize, make this transaction data participate in the self-teaching of face recognition algorithms, and participate in limited authentication comparison, participate in gradually the identification of face payment authentication;
To participating in the transaction data of recognition of face, by facial quality evaluation, get involved according to low weights, middle weights, three kinds of ranks of high weight, high weight was got involved after a period of time, repeatedly be better than under original binding face data prerequisite, with raw data exchange weights ratio, then after transaction authentication repeatedly, replace original old data, principle circulation according to this, realizes the self-teaching of face data, optimization, intelligent management face data, optimize original binding data, promote the quality of data.
5. face payment authentication system according to claim 2, is characterized in that:
Described payment data intelligent processing module comprises:
Quality assessment unit, in order to the face information of described face recognition module identification is carried out to quality judgement, judges whether the quality of face information meets setting requirement;
Face information storage unit, in order to preserve satisfactory face information;
Weight setting unit, carries out weight setting in order to contrast to the face information in database, is high weight by face information setting high quality, in the time of comparison, preferentially compares.
6. face payment authentication system according to claim 2, is characterized in that:
Described face recognition module comprises:
Face detecting unit, whether the authentication photo gathering in order to identification is containing complete face;
Face characteristic extraction unit, in order to extract face biological characteristic, record in a particular manner, generates skin detection, for face alignment and coupling provide raw data;
Face alignment and matching unit, according to face characteristic data template, carry out comparison one by one, the coupling of whole each biological characteristic point of face in order to recognition of face core algorithm, finally returns to similar value;
Recognition results unit, whether in order to according to face living things feature recognition algorithm rreturn value, judging and recognizing is same people;
Described face alignment and matching unit comprise that comparer unit is or/and one-to-many comparer unit one to one;
Described comparer one to one unit is in order to after client Real-time Collection human face photo, and the target photo that the human face photo of collection and payment account are bound in advance, carries out recognition of face and comparison, and whether identification is same people, then returns to recognition result;
Described one-to-many comparer unit is in order to carry out high degree of safety Intelligent Recognition, by client Real-time Collection upload pictures, compare with multiple target photos that payment account is bound in advance, traversal one by one, and with reference to the similarity after each comparison, identify more accurately, recognize and sort according to certain algorithm, multi-angle audit determines whether same people then to return to recognition result.
7. a face payment authentication method, is characterized in that, described authentication method comprises the steps:
Face raw data binding step, collection user's face information, as original binding data, binds user's face information and this user, and face information is stored in comparison database;
Recognition of face step, gathers the face information that needs comparison, extracts facial characteristics information, and the facial characteristics information extracting is compared with the described facial characteristics information of comparing the corresponding face information in database, determines whether same people;
Payment data Intelligent treatment step, after comparison face information, judges face information, if meet setting requirement, face information is added in described comparison database.
8. face payment authentication method according to claim 7, is characterized in that:
Described authentication method also comprises:
Face quality evaluation step, assesses the quality that gathers photo, and leading indicator comprises: pixel height, shape of face pixel size, part lack or block, shape of face angle; Shape of face angle refers to and upper and lower, the left and right deviation angle of positive criteria, and facial upward view angle is controlled within 10 °, depression angle is controlled within 15 °, and left and right angle is controlled within 15 °;
Facial pose correct step, the face of collection by quality evaluation after, the data shape of face angle of foundation, carries out attitude rectify to a certain degree to the human face photo higher than minimum threshold values, makes shape of face more approach positive criteria photograph, lifting recognition of face accuracy; Attitude rectify is take standard front face according to as benchmark, within automated intelligent is adjusted 5 ° of upward view angles, within 10 ° of depression angles, in 10 °, deflection angle.
9. face payment authentication method according to claim 7, is characterized in that:
In described payment data Intelligent treatment step, repeatedly complete after the face information of face payment transaction, according to quality evaluation standard, comprise gather face light, sharpness, pixel height, hot-tempered point, whether standard front face, feature obvious, transaction data is carried out to quality evaluation, if the quality of the face information of comparison is better than comparing the face information of storing in database, additionally learn, optimize, make this transaction data participate in the self-teaching of face recognition algorithms, and participate in limited authentication comparison, participate in gradually the identification of face payment authentication; To participating in the transaction data of recognition of face, by facial quality evaluation, get involved according to low weights, middle weights, three kinds of ranks of high weight, high weight was got involved after a period of time, repeatedly be better than under original binding face data prerequisite, with raw data exchange weights ratio, then after transaction authentication repeatedly, replace original old data, principle circulation according to this, realizes the self-teaching of face data, optimization, intelligent management face data, optimize original binding data, promote the quality of data.
10. face payment authentication method according to claim 7, is characterized in that:
Described recognition of face step specifically comprises the steps:
Face detecting step, whether the authentication photo that identification gathers is containing complete face;
Face characteristic extraction step, extracts face biological characteristic, and record in a particular manner generates skin detection, for face alignment and coupling provide raw data;
Face alignment with mate step, recognition of face core algorithm, according to face characteristic data template, carries out comparison one by one, the coupling of whole each biological characteristic point of face, finally returns to similar value;
Recognition results step, whether according to face living things feature recognition algorithm rreturn value, judging and recognizing is same people;
Described face alignment with mate step and comprise and compare step one to one or/and one-to-many comparer step;
Described comparison one to one in step, after client Real-time Collection human face photo, the target photo that the human face photo of collection and payment account are bound in advance, carries out recognition of face and comparison, and whether identification is same people, then returns to recognition result;
In described one-to-many comparison step, carry out high degree of safety Intelligent Recognition, by client Real-time Collection upload pictures, compare with multiple target photos that payment account is bound in advance, traversal one by one, and with reference to the similarity after each comparison, arrange from high low strap successively, for the data of low ratio, adopt again Local Alignment algorithm to compare, comprise eyes, pupil, the bridge of the nose, mouth carries out Local Alignment, then according to all kinds of ratio, identify more accurately by algorithm synthesis, identification and sequence, multi-angle audit determines whether same people, then return to recognition result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410101181.7A CN103824068B (en) | 2014-03-19 | 2014-03-19 | Face payment authentication system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410101181.7A CN103824068B (en) | 2014-03-19 | 2014-03-19 | Face payment authentication system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103824068A true CN103824068A (en) | 2014-05-28 |
| CN103824068B CN103824068B (en) | 2018-06-01 |
Family
ID=50759120
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410101181.7A Active CN103824068B (en) | 2014-03-19 | 2014-03-19 | Face payment authentication system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103824068B (en) |
Cited By (41)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104143139A (en) * | 2014-08-07 | 2014-11-12 | 辽宁蓝卡医疗投资管理有限公司 | Payment method and system based on facial expressions |
| CN104392356A (en) * | 2014-11-28 | 2015-03-04 | 苏州福丰科技有限公司 | Mobile payment system and method based on three-dimensional human face recognition |
| CN104408343A (en) * | 2014-11-09 | 2015-03-11 | 河南华辰智控技术有限公司 | Threshold value calculating method for identifying biological features through authentication system |
| CN104408616A (en) * | 2014-11-25 | 2015-03-11 | 苏州福丰科技有限公司 | Supermarket prepayment method based on three-dimensional face recognition |
| 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 |
| CN104574087A (en) * | 2015-01-26 | 2015-04-29 | 深圳前海万融智能信息有限公司 | Canteen directional micropayment method and system |
| CN104715540A (en) * | 2015-02-10 | 2015-06-17 | 福建工程学院 | Dining room fee deduction system based on RFID and recognition technology |
| CN104766210A (en) * | 2015-04-09 | 2015-07-08 | 广东小天才科技有限公司 | transaction verification method and device |
| CN104935438A (en) * | 2015-05-28 | 2015-09-23 | 北京旷视科技有限公司 | Method and apparatus for identity verification |
| CN105354710A (en) * | 2015-12-22 | 2016-02-24 | 重庆智韬信息技术中心 | Auxiliary identity authentication method for face identification payment |
| CN105528703A (en) * | 2015-12-26 | 2016-04-27 | 上海孩子国科教设备有限公司 | Method and system for implementing payment verification via expression |
| WO2016062173A1 (en) * | 2014-10-22 | 2016-04-28 | 腾讯科技（深圳）有限公司 | User attribute value transfer method and terminal |
| CN105938552A (en) * | 2016-06-29 | 2016-09-14 | 北京旷视科技有限公司 | Face recognition method capable of realizing base image automatic update and face recognition device |
| CN106485221A (en) * | 2016-09-30 | 2017-03-08 | 江苏四五安全科技有限公司 | A kind of method that benchmark photograph is replaced automatically according to similar concentration degree |
| CN107004076A (en) * | 2014-09-05 | 2017-08-01 | Utc 消防及保安公司 | System and method for access registrar |
| WO2017128085A1 (en) * | 2016-01-26 | 2017-08-03 | 罗剑锋 | Method for displaying information of face and credit card matching technology, and verification system |
| WO2017128084A1 (en) * | 2016-01-26 | 2017-08-03 | 罗剑锋 | Statistical method for usage data of human face and credit card matching technology, and verification system |
| CN107438185A (en) * | 2016-08-31 | 2017-12-05 | 李军 | Barrage supplying system and method for pushing |
| CN107590807A (en) * | 2017-09-29 | 2018-01-16 | 百度在线网络技术（北京）有限公司 | Method and apparatus for detection image quality |
| CN107609508A (en) * | 2017-09-08 | 2018-01-19 | 深圳市金立通信设备有限公司 | A kind of face identification method, terminal and computer-readable recording medium |
| CN108090772A (en) * | 2018-01-29 | 2018-05-29 | 河北三川科技有限公司 | Hotel occupancy brush face payment system and method based on recognition of face |
| CN108230293A (en) * | 2017-05-31 | 2018-06-29 | 深圳市商汤科技有限公司 | Determine method and apparatus, electronic equipment and the computer storage media of quality of human face image |
| CN108875336A (en) * | 2017-11-24 | 2018-11-23 | 北京旷视科技有限公司 | The method of face authentication and typing face, authenticating device and system |
| CN108876351A (en) * | 2018-07-05 | 2018-11-23 | 周爱霞 | The instant amount of money payment system of bus |
| CN108985174A (en) * | 2018-06-19 | 2018-12-11 | 杭州创匠信息科技有限公司 | Member authentication method and apparatus |
| CN109840515A (en) * | 2019-03-06 | 2019-06-04 | 百度在线网络技术（北京）有限公司 | Facial pose method of adjustment, device and terminal |
| CN109977815A (en) * | 2019-03-13 | 2019-07-05 | 上海商汤智能科技有限公司 | Image quality evaluating method and device, electronic equipment, storage medium |
| WO2019179242A1 (en) * | 2018-03-18 | 2019-09-26 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Image processing method and electronic device |
| CN110570200A (en) * | 2019-08-16 | 2019-12-13 | 阿里巴巴集团控股有限公司 | payment method and device |
| CN110610117A (en) * | 2018-06-15 | 2019-12-24 | 中兴通讯股份有限公司 | Face recognition method, face recognition device and storage medium |
| CN110688930A (en) * | 2019-09-20 | 2020-01-14 | Oppo广东移动通信有限公司 | Face detection method, face detection device, mobile terminal and storage medium |
| CN110782241A (en) * | 2019-10-31 | 2020-02-11 | 郑州天迈科技股份有限公司 | Hybrid face recognition public transportation payment system and method |
| CN110998626A (en) * | 2017-05-31 | 2020-04-10 | 谷歌有限责任公司 | Providing hands-free data for interaction |
| CN111310512A (en) * | 2018-12-11 | 2020-06-19 | 杭州海康威视数字技术股份有限公司 | User identity authentication method and device |
| US10803444B2 (en) | 2018-11-29 | 2020-10-13 | Alibaba Group Holding Limited | Method, device and terminal for payment |
| WO2021025627A1 (en) | 2019-08-05 | 2021-02-11 | Pippa Consulting, Vanja Cas S.P. | A transaction processing system and a transaction method based on facial recognition |
| CN113011348A (en) * | 2019-12-12 | 2021-06-22 | 天目爱视（北京）科技有限公司 | Intelligent service processing equipment based on 3D information identification |
| US11263634B2 (en) | 2019-08-16 | 2022-03-01 | Advanced New Technologies Co., Ltd. | Payment method and device |
| CN115619410A (en) * | 2022-10-19 | 2023-01-17 | 闫雪 | Self-adaptive financial payment platform |
| TWI804988B (en) * | 2020-09-17 | 2023-06-11 | 大陸商中國銀聯股份有限公司 | Identification object determination method, device, equipment and storage medium |
| CN117495384A (en) * | 2023-11-07 | 2024-02-02 | 广州准捷电子科技有限公司 | KTV face brushing payment method based on AI face recognition technology |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103268551A (en) * | 2013-05-29 | 2013-08-28 | 苏州福丰科技有限公司 | Bank card payment system based on human face identification and method for bank card payment system |
| CN103268549A (en) * | 2013-04-24 | 2013-08-28 | 徐明亮 | Mobile payment verification system based on facial features |
| CN103634118A (en) * | 2013-12-12 | 2014-03-12 | 山东神思电子技术股份有限公司 | Survival authentication method on basis of identification cards and composite biological feature recognition |
-
2014
- 2014-03-19 CN CN201410101181.7A patent/CN103824068B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103268549A (en) * | 2013-04-24 | 2013-08-28 | 徐明亮 | Mobile payment verification system based on facial features |
| CN103268551A (en) * | 2013-05-29 | 2013-08-28 | 苏州福丰科技有限公司 | Bank card payment system based on human face identification and method for bank card payment system |
| CN103634118A (en) * | 2013-12-12 | 2014-03-12 | 山东神思电子技术股份有限公司 | Survival authentication method on basis of identification cards and composite biological feature recognition |
Non-Patent Citations (2)
| Title |
|---|
| 杨飞，苏剑波，戴景文: "人脸识别中的人脸图像质量快速评价", 《PROCEEDINGS OF THE 27TH CHINESE CONTROL CONFERENCE》 * |
| 赵丽红, 刘纪红, 徐心和: "人脸检测方法综述", 《计算机应用研究》 * |
Cited By (57)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104143139A (en) * | 2014-08-07 | 2014-11-12 | 辽宁蓝卡医疗投资管理有限公司 | Payment method and system based on facial expressions |
| CN107004076A (en) * | 2014-09-05 | 2017-08-01 | Utc 消防及保安公司 | System and method for access registrar |
| US10417620B2 (en) | 2014-10-22 | 2019-09-17 | Tencent Technology (Shenzhen) Company Limited | User attribute value transfer method and terminal |
| WO2016062173A1 (en) * | 2014-10-22 | 2016-04-28 | 腾讯科技（深圳）有限公司 | User attribute value transfer method and terminal |
| US10127529B2 (en) | 2014-10-22 | 2018-11-13 | Tencent Technology (Shenzhen) Company Limited | User attribute value transfer method and terminal |
| CN104408343A (en) * | 2014-11-09 | 2015-03-11 | 河南华辰智控技术有限公司 | Threshold value calculating method for identifying biological features through authentication system |
| CN104408343B (en) * | 2014-11-09 | 2017-03-29 | 河南华辰智控技术有限公司 | By a kind of threshold value calculation method of the Verification System to living things feature recognition |
| CN104408616A (en) * | 2014-11-25 | 2015-03-11 | 苏州福丰科技有限公司 | Supermarket prepayment method based on three-dimensional face recognition |
| CN104392356A (en) * | 2014-11-28 | 2015-03-04 | 苏州福丰科技有限公司 | Mobile payment system and method based on three-dimensional human face recognition |
| 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 |
| CN104574087A (en) * | 2015-01-26 | 2015-04-29 | 深圳前海万融智能信息有限公司 | Canteen directional micropayment method and system |
| CN104715540A (en) * | 2015-02-10 | 2015-06-17 | 福建工程学院 | Dining room fee deduction system based on RFID and recognition technology |
| CN104766210A (en) * | 2015-04-09 | 2015-07-08 | 广东小天才科技有限公司 | transaction verification method and device |
| CN104935438A (en) * | 2015-05-28 | 2015-09-23 | 北京旷视科技有限公司 | Method and apparatus for identity verification |
| CN104935438B (en) * | 2015-05-28 | 2018-09-07 | 北京旷视科技有限公司 | Method and apparatus for authentication |
| CN105354710A (en) * | 2015-12-22 | 2016-02-24 | 重庆智韬信息技术中心 | Auxiliary identity authentication method for face identification payment |
| CN105528703A (en) * | 2015-12-26 | 2016-04-27 | 上海孩子国科教设备有限公司 | Method and system for implementing payment verification via expression |
| WO2017128085A1 (en) * | 2016-01-26 | 2017-08-03 | 罗剑锋 | Method for displaying information of face and credit card matching technology, and verification system |
| WO2017128084A1 (en) * | 2016-01-26 | 2017-08-03 | 罗剑锋 | Statistical method for usage data of human face and credit card matching technology, and verification system |
| CN105938552A (en) * | 2016-06-29 | 2016-09-14 | 北京旷视科技有限公司 | Face recognition method capable of realizing base image automatic update and face recognition device |
| CN107438185A (en) * | 2016-08-31 | 2017-12-05 | 李军 | Barrage supplying system and method for pushing |
| CN106485221A (en) * | 2016-09-30 | 2017-03-08 | 江苏四五安全科技有限公司 | A kind of method that benchmark photograph is replaced automatically according to similar concentration degree |
| US11182589B2 (en) | 2017-05-31 | 2021-11-23 | Shenzhen Sensetime Technology Co., Ltd. | Methods and apparatuses for determining face image quality, electronic devices, and computer storage media |
| CN108230293A (en) * | 2017-05-31 | 2018-06-29 | 深圳市商汤科技有限公司 | Determine method and apparatus, electronic equipment and the computer storage media of quality of human face image |
| CN110998626B (en) * | 2017-05-31 | 2023-12-01 | 谷歌有限责任公司 | Providing hands-free data for interaction |
| WO2018219180A1 (en) * | 2017-05-31 | 2018-12-06 | 深圳市商汤科技有限公司 | Method and apparatus for determining facial image quality, as well as electronic device and computer storage medium |
| CN110998626A (en) * | 2017-05-31 | 2020-04-10 | 谷歌有限责任公司 | Providing hands-free data for interaction |
| CN107609508A (en) * | 2017-09-08 | 2018-01-19 | 深圳市金立通信设备有限公司 | A kind of face identification method, terminal and computer-readable recording medium |
| CN107590807A (en) * | 2017-09-29 | 2018-01-16 | 百度在线网络技术（北京）有限公司 | Method and apparatus for detection image quality |
| CN108875336A (en) * | 2017-11-24 | 2018-11-23 | 北京旷视科技有限公司 | The method of face authentication and typing face, authenticating device and system |
| CN108090772A (en) * | 2018-01-29 | 2018-05-29 | 河北三川科技有限公司 | Hotel occupancy brush face payment system and method based on recognition of face |
| US10769416B2 (en) | 2018-03-18 | 2020-09-08 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Image processing method, electronic device and storage medium |
| WO2019179242A1 (en) * | 2018-03-18 | 2019-09-26 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Image processing method and electronic device |
| CN110610117A (en) * | 2018-06-15 | 2019-12-24 | 中兴通讯股份有限公司 | Face recognition method, face recognition device and storage medium |
| CN108985174A (en) * | 2018-06-19 | 2018-12-11 | 杭州创匠信息科技有限公司 | Member authentication method and apparatus |
| CN108876351A (en) * | 2018-07-05 | 2018-11-23 | 周爱霞 | The instant amount of money payment system of bus |
| US10803444B2 (en) | 2018-11-29 | 2020-10-13 | Alibaba Group Holding Limited | Method, device and terminal for payment |
| US11132669B2 (en) | 2018-11-29 | 2021-09-28 | Advanced New Technologies Co., Ltd. | Method, device and terminal for payment |
| CN111310512B (en) * | 2018-12-11 | 2023-08-22 | 杭州海康威视数字技术股份有限公司 | User identity authentication method and device |
| CN111310512A (en) * | 2018-12-11 | 2020-06-19 | 杭州海康威视数字技术股份有限公司 | User identity authentication method and device |
| CN109840515A (en) * | 2019-03-06 | 2019-06-04 | 百度在线网络技术（北京）有限公司 | Facial pose method of adjustment, device and terminal |
| CN109977815A (en) * | 2019-03-13 | 2019-07-05 | 上海商汤智能科技有限公司 | Image quality evaluating method and device, electronic equipment, storage medium |
| WO2021025627A1 (en) | 2019-08-05 | 2021-02-11 | Pippa Consulting, Vanja Cas S.P. | A transaction processing system and a transaction method based on facial recognition |
| CN112258193B (en) * | 2019-08-16 | 2024-01-30 | 创新先进技术有限公司 | Payment method and device |
| US11263634B2 (en) | 2019-08-16 | 2022-03-01 | Advanced New Technologies Co., Ltd. | Payment method and device |
| CN112258193A (en) * | 2019-08-16 | 2021-01-22 | 创新先进技术有限公司 | Payment method and device |
| CN110570200A (en) * | 2019-08-16 | 2019-12-13 | 阿里巴巴集团控股有限公司 | payment method and device |
| CN110688930A (en) * | 2019-09-20 | 2020-01-14 | Oppo广东移动通信有限公司 | Face detection method, face detection device, mobile terminal and storage medium |
| CN110782241A (en) * | 2019-10-31 | 2020-02-11 | 郑州天迈科技股份有限公司 | Hybrid face recognition public transportation payment system and method |
| CN110782241B (en) * | 2019-10-31 | 2024-03-29 | 郑州天迈科技股份有限公司 | Hybrid face recognition public transportation payment system and method |
| CN113011348A (en) * | 2019-12-12 | 2021-06-22 | 天目爱视（北京）科技有限公司 | Intelligent service processing equipment based on 3D information identification |
| CN113011348B (en) * | 2019-12-12 | 2024-05-14 | 天目爱视（北京）科技有限公司 | Intelligent service processing equipment based on 3D information identification |
| TWI804988B (en) * | 2020-09-17 | 2023-06-11 | 大陸商中國銀聯股份有限公司 | Identification object determination method, device, equipment and storage medium |
| CN115619410B (en) * | 2022-10-19 | 2024-01-26 | 闫雪 | Self-adaptive financial payment platform |
| CN115619410A (en) * | 2022-10-19 | 2023-01-17 | 闫雪 | Self-adaptive financial payment platform |
| CN117495384A (en) * | 2023-11-07 | 2024-02-02 | 广州准捷电子科技有限公司 | KTV face brushing payment method based on AI face recognition technology |
| CN117495384B (en) * | 2023-11-07 | 2024-04-26 | 广州准捷电子科技有限公司 | KTV face brushing payment method based on AI face recognition technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103824068B (en) | 2018-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103824068A (en) | Human face payment authentication system and method | |
| US11151546B2 (en) | Trigger peer to peer payment with financial cards and phone camera | |
| CN105069622B (en) | A kind of face recognition payment system and method for facing moving terminal | |
| US9495586B1 (en) | Identity verification using biometric data | |
| WO2018028546A1 (en) | Key point positioning method, terminal, and computer storage medium | |
| CN103559485A (en) | Identity authentication method and device based on remote bank VTM | |
| US20140279516A1 (en) | Authenticating a physical device | |
| WO2018094584A1 (en) | Payment and identity authentication system based on biometric feature recognition | |
| CN105809447A (en) | Payment authentication method and system based on face recognition and HCE | |
| CN104462922A (en) | Method for verifying authorization on basis of biological recognition | |
| CN106779292A (en) | A kind of is the method and device of offering customers service based on recognition of face | |
| CN104167025A (en) | Mobile attendance system based on dynamic face recognition and WIFI positioning and method of attendance system | |
| CN111553312A (en) | Business handling method and device | |
| CN107230140A (en) | House lease and vending method and system | |
| CN104794386A (en) | Data processing method and device based on face recognition | |
| CN204680060U (en) | The identification of Network Based and biological characteristic and payment mechanism | |
| US20220277311A1 (en) | A transaction processing system and a transaction method based on facial recognition | |
| CN104778392A (en) | Privilege validation method and system on basis of biological identification | |
| CN105550928A (en) | System and method of network remote account opening for commercial bank | |
| CN109523271A (en) | Face payment system and method | |
| CN108446687A (en) | A kind of adaptive face vision authentication method based on mobile terminal and backstage interconnection | |
| TWM576696U (en) | Machine system with face recognition function | |
| CN108053218A (en) | A kind of safe method of mobile payment | |
| Wei | Video face recognition of virtual currency trading system based on deep learning algorithms | |
| Wei et al. | The impact of face recognition payment in the economic |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Facial payment authentication system and method Granted publication date: 20180601 Pledgee: China Construction Bank Corporation Shanghai Zhangjiang Branch Pledgor: SHANGHAI KANKAN INTELLIGENT TECHNOLOGY Co.,Ltd. Registration number: Y2024310000599 |