CN112215614A - Catering settlement method based on face recognition technology - Google Patents
Catering settlement method based on face recognition technology Download PDFInfo
- Publication number
- CN112215614A CN112215614A CN202011104156.6A CN202011104156A CN112215614A CN 112215614 A CN112215614 A CN 112215614A CN 202011104156 A CN202011104156 A CN 202011104156A CN 112215614 A CN112215614 A CN 112215614A
- Authority
- CN
- China
- Prior art keywords
- face
- user
- order
- face recognition
- face data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000005516 engineering process Methods 0.000 title claims abstract description 18
- 238000001514 detection method Methods 0.000 claims abstract description 10
- 239000000284 extract Substances 0.000 claims abstract description 10
- 235000013305 food Nutrition 0.000 claims abstract description 8
- 239000013598 vector Substances 0.000 claims description 54
- 230000001815 facial effect Effects 0.000 claims description 38
- 210000005069 ears Anatomy 0.000 claims description 9
- 238000004519 manufacturing process Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 3
- 210000001747 pupil Anatomy 0.000 claims description 3
- 210000000056 organ Anatomy 0.000 claims description 2
- 238000013467 fragmentation Methods 0.000 abstract description 6
- 238000006062 fragmentation reaction Methods 0.000 abstract description 6
- 235000021186 dishes Nutrition 0.000 description 12
- 210000004709 eyebrow Anatomy 0.000 description 3
- 235000012054 meals Nutrition 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 210000001508 eye Anatomy 0.000 description 2
- 235000012046 side dish Nutrition 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 239000011324 bead Substances 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000004397 blinking Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 210000004373 mandible Anatomy 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 210000000697 sensory organ Anatomy 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
Images
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
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/12—Hotels or restaurants
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Marketing (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Development Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Computer Security & Cryptography (AREA)
- Collating Specific Patterns (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a catering settlement method based on a face recognition technology, which is characterized in that a user inputs face data in advance, initiates a food ordering request by utilizing fragmentation time, generates an order, extracts the face data by a settlement terminal, binds the face data with the order, places the face data in a queue to be settled, performs target detection on the face if the face is recognized at the settlement terminal, matches the face data bound in the queue to be settled, settles and checks, deletes the corresponding face data and the order, and finishes single-person receiving. The invention distributes the dish taking links to different time periods, allows users to order dishes and submit orders on line by using own fragmentation time, and inputs own face data in advance for matching of subsequent dish taking; the method has great convenience, the acquisition of the face is obviously quicker and more convenient, and the queuing time is greatly shortened. The invention meets the requirements of high efficiency, time saving, rapid accounting and fast circulation of dining in the restaurant, and carries out two-way guarantee on business and customer source experience of the merchant.
Description
Technical Field
The present invention relates to authorization, e.g., payer or payee identification, auditing customer or store credentials; the technical field of the examination and the approval of payers, such as the examination of credit lines or rejection lists, in particular to a catering settlement method based on a face recognition technology.
Background
With the acceleration of the rhythm of life and the enhancement of the degree of intelligent life, people need to struggle for minutes and seconds in various occasions, especially in the working environment.
Catering is an essential link in life of people, with the progress of socialization, cafeterias are more and more, but the current catering industry generally adopts the mode that diners take dishes and workers manually settle accounts for consumption conditions, so that the diners cannot efficiently utilize fragmentization time, congestion and queuing are involved in the process of taking dishes, and the workers need to manually calculate prices, input dishes and the like in the settlement process.
The more common situation is that diners arrive at a restaurant collectively in the peak period of dinning, the intention is to seek high efficiency and time saving for dinning, more rest time is strived for while supplementing energy, however, because the existing settlement system can not meet the requirements, especially in the peak time of people flow, the consumption of consumers can not be calculated in a short time, so that the waiting time of the consumers is longer, the error rate is high, and the bidirectional guarantee can not be carried out on merchants and customer sources.
Disclosure of Invention
The invention solves the problems that in the prior art, a settlement system can not meet requirements, particularly in the peak time of people flow, the consumption of a consumer can not be calculated in a short time, so that the waiting time of the consumer is long, the error rate is high, and the merchant and the customer source can not be guaranteed in two ways, and provides an optimized catering settlement method based on a face recognition technology.
The invention adopts the technical scheme that a catering settlement method based on a face recognition technology comprises the following steps:
step 1: initializing user face data;
step 2: waiting, and generating an order when any user initiates a food ordering request;
and step 3: the settlement terminal extracts face data corresponding to the current user, binds the face data with the order and places the face data in a queue to be settled;
and 4, step 4: if the face recognition equipment recognizes the face, the next step is carried out, otherwise, the step 2 is returned;
and 5: carrying out target detection on the face identified by the face identification equipment, if the target is detected, carrying out the next step, otherwise, detecting whether a newly generated order exists; if the order of new production exists, returning to the step 3, otherwise returning to the step 4;
step 6: if the detected target is matched with any bound face data in the queue to be settled, settling and checking, and carrying out the next step, otherwise, prompting no order; detecting whether a newly generated order exists; if the order of new production exists, returning to the step 3, otherwise returning to the step 4;
and 7: and deleting the bound face data and the order corresponding to the meal-taking user in the queue to be settled.
Preferably, in step 1, the user data initialization includes the following steps:
step 1.1: a user starts the intelligent terminal and starts a camera;
step 1.2: collecting a plurality of facial images for a current user;
step 1.3: if the current facial image meets the acquisition requirement, acquiring a facial contour curve of the user based on a plurality of facial images of the current user, otherwise, shooting the facial image again, and repeating the step 1.3;
step 1.4: acquiring a feature vector aiming at the current user based on the user face contour curve, binding the feature vector and user information, and storing the feature vector and the user information into a database of a settlement terminal;
step 1.5: and finishing the data initialization of the current user and returning to the step 1.2.
Preferably, said step 1.3 comprises the steps of:
step 1.3.1: acquiring a plurality of facial images of a current user;
step 1.3.2: taking a plurality of facial images for preprocessing, and correcting the facial images to be normal;
step 1.3.3: if the coincidence rate of any two facial images exceeds the threshold value Q and the face and the ears are completely exposed, the acquisition requirements are met, the next step is carried out, otherwise, the facial images are shot again, and the step 1.3.1 is returned;
step 1.3.4: a user face contour curve is obtained.
Preferably, in the step 1.3.2, a line a is obtained by connecting the two pupils, a line B is obtained by connecting the midpoint of the line a and the tip of the nose, and the line a is horizontal and the line B is located in the middle of the acquired face image, which is in the normal position.
Preferably, the user face contour curves include facial outer contours, binaural contours, facial feature contours.
Preferably, based on the user face contour curve, obtaining a feature vector for a current user comprises the steps of:
step 1.4.1: based on the user face contour curve, acquiring the five-point of the face outer contour, the top point and the bottom point of the double-ear contour, and all inflection points and/or end points of the facial contour except the double ears;
step 1.4.2: taking the center of the face in the normal position as the origin of a coordinate axis;
step 1.4.3: obtaining a vector of each collected point in step 1.4.1 in a preset sequence;
step 1.4.4: a feature vector for the current user is obtained.
Preferably, the step 3 comprises the steps of:
step 3.1: integrating the order and the user information of the user who initiates the ordering request, and sending the order and the user information to a settlement terminal;
step 3.2: and the settlement terminal extracts the face data corresponding to the current user, binds the face data with the order and places the face data in a queue to be settled.
Preferably, in the step 3.2, if the settlement terminal inquires that the current user has the face characteristics correspondingly, the next step is performed, otherwise, the user is prompted to perform face entry or execute ordinary settlement; and if the user performs face input, initializing the user data, and repeating the step 3.2.
Preferably, the step 5 comprises the steps of:
step 5.1: carrying out target detection on the face identified by the face identification equipment;
step 5.2: if the recognized face simultaneously meets the conditions that the staying time in the face recognition equipment exceeds a threshold value T, the display area of the face in the face recognition equipment exceeds a threshold value W and the face recognition equipment can acquire preset acquisition point information, determining that the target is detected, and performing step 6, otherwise, performing step 5.3;
step 5.3: and detecting whether a newly generated order exists currently, if so, returning to the step 3, otherwise, returning to the step 4.
Preferably, in the step 6, the matching between the detected target and any one of the face data bound in the queue to be settled includes the following steps:
step 6.1: obtaining vectors between any collection point and the center of the target in the detected target in a preset sequence, setting the vectors of non-collection points as 0 vectors, and obtaining feature vectors to be matched;
step 6.2: matching the eigenvectors to be matched with the eigenvectors in the queue to be settled, and calculating the vector included angles in a successive corresponding manner;
step 6.3: counting if any vector included angle is smaller than a preset angle alpha;
step 6.4: and if the ratio of the count value to the vector of non-0 is greater than the preset value P, the matching is performed, and the verification and the cancellation are settled.
The invention provides an optimized catering settlement method based on a face recognition technology, which is characterized in that face data of a user is initialized, the face data of the user is input in advance, then the user can initiate a food ordering request and generate an order by utilizing fragmentation time, in the process, the settlement terminal extracts the face data corresponding to the current user, binds the face data with the order and places the face data in a queue to be settled, the dishes can be properly placed in the settlement queue in advance by workers, and can also be picked up by the users, at the settlement terminal, as long as the face recognition device recognizes the face, the face can be subject to target detection, after confirming the existence of the target, and matching with any one bound face data in the queue to be settled, settling and checking, and finally deleting the bound face data and the order corresponding to the meal-taking user in the queue to be settled to finish single-person single-time getting.
According to the invention, the dish taking links which are easy to be jammed are distributed to different time periods, so that a user is allowed to use own fragmentation time to order dishes and submit orders on line, and face data of the user is pre-input to carry out follow-up dish taking matching; when arriving at a settlement window, the user can get his dishes and check and sell the dishes through face recognition, and then the whole meal taking process can be completed; compared with manual settlement in the prior art, the method has the advantages that great convenience is obviously achieved, a user does not need to vacate two hands to take cards or input passwords and the like for verification, the face collection is obviously faster and more convenient, the time for removing side dishes in the whole process can be finished within 5 seconds, and the queuing time is greatly shortened.
The invention meets the requirements of high efficiency, time saving, rapid accounting and fast circulation of dining in the restaurant, and carries out two-way guarantee on business and customer source experience of the merchant.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The present invention is described in further detail with reference to the following examples, but the scope of the present invention is not limited thereto.
The invention relates to a catering settlement method based on a face recognition technology.
Step 1: and initializing the face data of the user.
In step 1, the user data initialization includes the following steps:
step 1.1: a user starts the intelligent terminal and starts a camera;
step 1.2: collecting a plurality of facial images for a current user;
step 1.3: if the current facial image meets the acquisition requirement, acquiring a facial contour curve of the user based on a plurality of facial images of the current user, otherwise, shooting the facial image again, and repeating the step 1.3;
the step 1.3 comprises the following steps:
step 1.3.1: acquiring a plurality of facial images of a current user;
step 1.3.2: taking a plurality of facial images for preprocessing, and correcting the facial images to be normal;
in the step 1.3.2, a line a is obtained by connecting the double pupils, a line B is obtained by connecting the midpoint of the line a and the tip of the nose, and the line a is in the normal position when the line B is horizontal and the line B is located in the middle of the collected face image.
Step 1.3.3: if the coincidence rate of any two facial images exceeds the threshold value Q and the face and the ears are completely exposed, the acquisition requirements are met, the next step is carried out, otherwise, the facial images are shot again, and the step 1.3.1 is returned;
step 1.3.4: a user face contour curve is obtained.
Step 1.4: acquiring a feature vector aiming at the current user based on the user face contour curve, binding the feature vector and user information, and storing the feature vector and the user information into a database of a settlement terminal;
the user face contour curve comprises a face outer contour, a double-ear contour and a five-sense organ contour.
Based on the user face contour curve, obtaining a feature vector for a current user comprises the steps of:
step 1.4.1: based on the user face contour curve, acquiring the five-point of the face outer contour, the top point and the bottom point of the double-ear contour, and all inflection points and/or end points of the facial contour except the double ears;
step 1.4.2: taking the center of the face in the normal position as the origin of a coordinate axis;
step 1.4.3: obtaining a vector of each collected point in step 1.4.1 in a preset sequence;
step 1.4.4: a feature vector for the current user is obtained.
Step 1.5: and finishing the data initialization of the current user and returning to the step 1.2.
In the invention, the intelligent terminal comprises all terminals with the functions of a face acquisition camera and network communication, such as a mobile phone, a tablet personal computer, a PDA and the like.
In the invention, the acquisition requirements in the step 1.3 comprise that the image definition reaches a preset value, the faces including eyebrows, eyes, ears and mandibles are completely recorded, light spots which have obvious shielding effects such as reflection of spectacle lenses do not exist, and a person skilled in the art can set specific acquisition requirements according to actual requirements.
In the invention, after the photo is collected, all the face images are processed, mainly corrected to be in the right position, but not distorted or stretched, and when the coincidence rate of any two face images exceeds a threshold value Q, generally 95%, and the face and ears are completely exposed, the acquisition requirement is met.
In the present invention, since it is actually necessary to confirm that the image is input by the user, blinking and shaking may be required, and it may be simply estimated that, when all face images completely overlap, it is considered to be a false input and recognitions are required.
In the present invention, the user face contour curves include, but are not limited to, facial outer contour, binaural contour, and facial features contour, and can be set by those skilled in the art according to the needs.
In the invention, the obtained user face contour curve is subjected to feature point sampling, generally, the collected points should fall into the user face contour curve, such as the five-point of the face outer contour, the top points and the bottom points of the binaural contour, and all the inflection points and the end points of the facial feature contour, wherein the five-point of the face outer contour is used for defining the face shape, and the top points and the bottom points of the binaural contour can be used for determining the normal position of the face image relative to the step 1.3 besides the feature determination; all inflection points and endpoints of the outline of five sense organs include the two ends and the peak of the eyebrow of any eyebrow, the canthus and the tail of any eye, the top, bottom and wings of the nose, and the two ends of the mouth and/or the position of the labial bead.
In the invention, a vector is constructed between each collected point and the center of the face in the right position, the starting point of the vector is the center of the face in the right position, all the vectors are integrated together in a preset sequence to form the feature vector of the current user, namely, the subsequent comparison only needs to compare the angle of the feature vector.
Step 2: waiting, and generating an order when any user initiates a food ordering request.
In the invention, after the user records the head portrait information of the user, the user initiates a food ordering request, dishes are ordered by utilizing fragmented time to generate an order, and then only a calculation place is required to take food for calculation.
In the invention, in order to meet different requirements of different customers, the meal taking time can be confirmed while ordering, so that the dish is convenient for the staff to prepare dishes in advance.
And step 3: and the settlement terminal extracts the face data corresponding to the current user, binds the face data with the order and places the face data in a queue to be settled.
The step 3 comprises the following steps:
step 3.1: integrating the order and the user information of the user who initiates the ordering request, and sending the order and the user information to a settlement terminal;
step 3.2: and the settlement terminal extracts the face data corresponding to the current user, binds the face data with the order and places the face data in a queue to be settled.
In the step 3.2, if the settlement terminal inquires that the current user corresponds to the face characteristics, the next step is carried out, otherwise, the user is prompted to carry out face input or ordinary settlement is executed; and if the user performs face input, initializing the user data, and repeating the step 3.2.
In the invention, the order and the user information of the user who initiates the ordering request are integrated and sent to the settlement terminal, and the settlement terminal mainly extracts face data, namely, the characteristic vector is bound with the order.
The invention can provide a plurality of settlement modes, the process of face settlement is obviously faster, and certainly, a non-face settlement path can also be provided.
And 4, step 4: and if the face recognition equipment recognizes the face, performing the next step, otherwise, returning to the step 2.
And 5: carrying out target detection on the face identified by the face identification equipment, if the target is detected, carrying out the next step, otherwise, detecting whether a newly generated order exists; and if the order of the new production exists, returning to the step 3, otherwise, returning to the step 4.
The step 5 comprises the following steps:
step 5.1: carrying out target detection on the face identified by the face identification equipment;
step 5.2: if the recognized face simultaneously meets the conditions that the staying time in the face recognition equipment exceeds a threshold value T, the display area of the face in the face recognition equipment exceeds a threshold value W and the face recognition equipment can acquire preset acquisition point information, determining that the target is detected, and performing step 6, otherwise, performing step 5.3;
step 5.3: and detecting whether a newly generated order exists currently, if so, returning to the step 3, otherwise, returning to the step 4.
In the invention, because a plurality of users pass before the face recognition equipment, target detection is needed, and the accounting process is carried out only under the condition that the face is recognized and confirmed as the target, otherwise, different paths are executed according to whether a new order is available.
In the invention, when the recognized face is met as a target, the face should stay for a long enough time in front of the face recognition equipment, and the face should be close to the acquisition module of the equipment as far as possible, but the integrity of acquisition points, especially the data of the acquisition points of ears, is ensured.
Step 6: if the detected target is matched with any bound face data in the queue to be settled, settling and checking, and carrying out the next step, otherwise, prompting no order; detecting whether a newly generated order exists; and if the order of the new production exists, returning to the step 3, otherwise, returning to the step 4.
In the step 6, the step of matching the detected target with any one of the face data bound in the queue to be settled comprises the following steps:
step 6.1: obtaining vectors between any collection point and the center of the target in the detected target in a preset sequence, setting the vectors of non-collection points as 0 vectors, and obtaining feature vectors to be matched;
step 6.2: matching the eigenvectors to be matched with the eigenvectors in the queue to be settled, and calculating the vector included angles in a successive corresponding manner;
step 6.3: counting if any vector included angle is smaller than a preset angle alpha;
step 6.4: and if the ratio of the count value to the vector of non-0 is greater than the preset value P, the matching is performed, and the verification and the cancellation are settled.
In the invention, in the process of checking and canceling, all orders under the current user name are generally checked and cancelled integrally, so that unnecessary errors are avoided.
In the invention, the same work of extracting the characteristic vector is carried out on the detected target, when the non-collected collection point exists, the vector position in the characteristic vector corresponding to the current collection point is set as 0 vector, and certainly, the number of the 0 vectors should meet a certain lower limit requirement so as to ensure the accuracy of matching.
In the invention, vector included angles are calculated in a successive corresponding manner, when the matched included angle degree is met, counting is carried out, and finally, whether the vector included angles are matched or not is judged according to the ratio between the counting value and the non-0 vector, and the settlement and the verification are carried out if the vector included angles are matched.
And 7: and deleting the bound face data and the order corresponding to the meal-taking user in the queue to be settled.
In the invention, bound face data and orders corresponding to checked orders are deleted, and space is released.
The invention is initialized by the face data of the user, the user inputs the face data of the user in advance, then the user can initiate a food ordering request and generate an order by utilizing fragmentation time, in the process, a settlement terminal extracts the face data corresponding to the current user, binds the face data with the order and places the face data into a queue to be settled, the dish can be properly placed in the settlement queue by workers in advance and can be picked up by the user, at the settlement terminal, as long as the face recognition device recognizes the face, the face can be subjected to target detection, after the existence of the target is confirmed, the dish is matched with any face data bound in the queue to be settled, settlement and the settlement is checked, and finally the bound face data corresponding to the food-taking user and the order are deleted in the queue to be settled, so that the single picking up is completed.
According to the invention, the dish taking links which are easy to be jammed are distributed to different time periods, so that a user is allowed to use own fragmentation time to order dishes and submit orders on line, and face data of the user is pre-input to carry out follow-up dish taking matching; when arriving at a settlement window, the user can get his dishes and check and sell the dishes through face recognition, and then the whole meal taking process can be completed; compared with manual settlement in the prior art, the method has the advantages that great convenience is obviously achieved, a user does not need to vacate two hands to take cards or input passwords and the like for verification, the face collection is obviously faster and more convenient, the time for removing side dishes in the whole process can be finished within 5 seconds, and the queuing time is greatly shortened.
The invention meets the requirements of high efficiency, time saving, rapid accounting and fast circulation of dining in the restaurant, and carries out two-way guarantee on business and customer source experience of the merchant.
Claims (10)
1. A catering settlement method based on a face recognition technology is characterized in that: the method comprises the following steps:
step 1: initializing user face data;
step 2: waiting, and generating an order when any user initiates a food ordering request;
and step 3: the settlement terminal extracts face data corresponding to the current user, binds the face data with the order and places the face data in a queue to be settled;
and 4, step 4: if the face recognition equipment recognizes the face, the next step is carried out, otherwise, the step 2 is returned;
and 5: carrying out target detection on the face identified by the face identification equipment, if the target is detected, carrying out the next step, otherwise, detecting whether a newly generated order exists; if the order of new production exists, returning to the step 3, otherwise returning to the step 4;
step 6: if the detected target is matched with any bound face data in the queue to be settled, settling and checking, and carrying out the next step, otherwise, prompting no order; detecting whether a newly generated order exists; if the order of new production exists, returning to the step 3, otherwise returning to the step 4;
and 7: and deleting the bound face data and the order corresponding to the meal-taking user in the queue to be settled.
2. The catering settlement method based on the face recognition technology as claimed in claim 1, wherein: in step 1, the user data initialization includes the following steps:
step 1.1: a user starts the intelligent terminal and starts a camera;
step 1.2: collecting a plurality of facial images for a current user;
step 1.3: if the current facial image meets the acquisition requirement, acquiring a facial contour curve of the user based on a plurality of facial images of the current user, otherwise, shooting the facial image again, and repeating the step 1.3;
step 1.4: acquiring a feature vector aiming at the current user based on the user face contour curve, binding the feature vector and user information, and storing the feature vector and the user information into a database of a settlement terminal;
step 1.5: and finishing the data initialization of the current user and returning to the step 1.2.
3. The catering settlement method based on the face recognition technology as claimed in claim 2, wherein: the step 1.3 comprises the following steps:
step 1.3.1: acquiring a plurality of facial images of a current user;
step 1.3.2: taking a plurality of facial images for preprocessing, and correcting the facial images to be normal;
step 1.3.3: if the coincidence rate of any two facial images exceeds the threshold value Q and the face and the ears are completely exposed, the acquisition requirements are met, the next step is carried out, otherwise, the facial images are shot again, and the step 1.3.1 is returned;
step 1.3.4: a user face contour curve is obtained.
4. The catering settlement method based on the face recognition technology as claimed in claim 3, wherein: in the step 1.3.2, a line a is obtained by connecting the double pupils, a line B is obtained by connecting the midpoint of the line a and the tip of the nose, and the line a is in the normal position when the line B is horizontal and the line B is located in the middle of the collected face image.
5. The catering settlement method based on the face recognition technology as claimed in claim 2, wherein: the user face contour curve comprises a face outer contour, a double-ear contour and a five-sense organ contour.
6. The catering settlement method based on the face recognition technology as claimed in claim 5, wherein: based on the user face contour curve, obtaining a feature vector for a current user comprises the steps of:
step 1.4.1: based on the user face contour curve, acquiring the five-point of the face outer contour, the top point and the bottom point of the double-ear contour, and all inflection points and/or end points of the facial contour except the double ears;
step 1.4.2: taking the center of the face in the normal position as the origin of a coordinate axis;
step 1.4.3: obtaining a vector of each collected point in step 1.4.1 in a preset sequence;
step 1.4.4: a feature vector for the current user is obtained.
7. The catering settlement method based on the face recognition technology as claimed in claim 1, wherein: the step 3 comprises the following steps:
step 3.1: integrating the order and the user information of the user who initiates the ordering request, and sending the order and the user information to a settlement terminal;
step 3.2: and the settlement terminal extracts the face data corresponding to the current user, binds the face data with the order and places the face data in a queue to be settled.
8. The catering settlement method based on the face recognition technology as claimed in claim 7, wherein: in the step 3.2, if the settlement terminal inquires that the current user corresponds to the face characteristics, the next step is carried out, otherwise, the user is prompted to carry out face input or ordinary settlement is executed; and if the user performs face input, initializing the user data, and repeating the step 3.2.
9. The catering settlement method based on the face recognition technology as claimed in claim 1, wherein: the step 5 comprises the following steps:
step 5.1: carrying out target detection on the face identified by the face identification equipment;
step 5.2: if the recognized face simultaneously meets the conditions that the staying time in the face recognition equipment exceeds a threshold value T, the display area of the face in the face recognition equipment exceeds a threshold value W and the face recognition equipment can acquire preset acquisition point information, determining that the target is detected, and performing step 6, otherwise, performing step 5.3;
step 5.3: and detecting whether a newly generated order exists currently, if so, returning to the step 3, otherwise, returning to the step 4.
10. The catering settlement method based on the face recognition technology as claimed in claim 1, wherein: in the step 6, the step of matching the detected target with any one of the face data bound in the queue to be settled comprises the following steps:
step 6.1: obtaining vectors between any collection point and the center of the target in the detected target in a preset sequence, setting the vectors of non-collection points as 0 vectors, and obtaining feature vectors to be matched;
step 6.2: matching the eigenvectors to be matched with the eigenvectors in the queue to be settled, and calculating the vector included angles in a successive corresponding manner;
step 6.3: counting if any vector included angle is smaller than a preset angle alpha;
step 6.4: and if the ratio of the count value to the vector of non-0 is greater than the preset value P, the matching is performed, and the verification and the cancellation are settled.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011104156.6A CN112215614A (en) | 2020-10-15 | 2020-10-15 | Catering settlement method based on face recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011104156.6A CN112215614A (en) | 2020-10-15 | 2020-10-15 | Catering settlement method based on face recognition technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112215614A true CN112215614A (en) | 2021-01-12 |
Family
ID=74054614
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011104156.6A Pending CN112215614A (en) | 2020-10-15 | 2020-10-15 | Catering settlement method based on face recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112215614A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949495A (en) * | 2021-03-04 | 2021-06-11 | 安徽师范大学 | Intelligent identification system based on big data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109087217A (en) * | 2018-11-02 | 2018-12-25 | 四川长虹电器股份有限公司 | A kind of intelligence based on face recognition technology is ordered pick-up system and method |
| CN109086847A (en) * | 2018-08-17 | 2018-12-25 | 浙江口碑网络技术有限公司 | Pick-up processing method and processing device based on recognition of face |
| CN109935007A (en) * | 2019-04-10 | 2019-06-25 | 杭州雄伟科技开发股份有限公司 | A kind of recognition of face pick-up cabinet and food and drink are intelligently ordered pick-up system |
| CN111027953A (en) * | 2019-10-21 | 2020-04-17 | 深圳蚂里奥技术有限公司 | Restaurant ordering and payment method and system |
-
2020
- 2020-10-15 CN CN202011104156.6A patent/CN112215614A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086847A (en) * | 2018-08-17 | 2018-12-25 | 浙江口碑网络技术有限公司 | Pick-up processing method and processing device based on recognition of face |
| CN109087217A (en) * | 2018-11-02 | 2018-12-25 | 四川长虹电器股份有限公司 | A kind of intelligence based on face recognition technology is ordered pick-up system and method |
| CN109935007A (en) * | 2019-04-10 | 2019-06-25 | 杭州雄伟科技开发股份有限公司 | A kind of recognition of face pick-up cabinet and food and drink are intelligently ordered pick-up system |
| CN111027953A (en) * | 2019-10-21 | 2020-04-17 | 深圳蚂里奥技术有限公司 | Restaurant ordering and payment method and system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949495A (en) * | 2021-03-04 | 2021-06-11 | 安徽师范大学 | Intelligent identification system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108009465B (en) | Face recognition method and device | |
| CN105741451B (en) | Information processing system and information processing method | |
| CN109508974B (en) | Shopping checkout system and method based on feature fusion | |
| US10055734B2 (en) | Systems and methods for processing customer purchase transactions using biometric data | |
| CN106204033A (en) | A kind of based on recognition of face with the payment system of fingerprint recognition | |
| US20160048821A1 (en) | Simple in-store payments | |
| US20180089688A1 (en) | System and methods for authenticating a user using biometric data | |
| CN105809447A (en) | Payment authentication method and system based on face recognition and HCE | |
| EP3642776A1 (en) | Facial biometrics card emulation for in-store payment authorization | |
| WO2017007590A1 (en) | Simultaneous multi-factor authentication systems and methods for payment transactions | |
| US20150235217A1 (en) | Photos to detect fraud at point of sale method and apparatus | |
| US20180174149A1 (en) | Systems and Methods for Use in Authenticating Consumers in Connection With Payment Account Transactions | |
| KR102334095B1 (en) | Payment method and payment system using user terminal | |
| WO2020168134A1 (en) | Systems and methods for accurate image characteristic detection | |
| CN105913264B (en) | Face payment mechanism based on the identification of fingerprint secondary identities | |
| US20190057390A1 (en) | Biometric system for authenticating a biometric request | |
| CN112215614A (en) | Catering settlement method based on face recognition technology | |
| US11651371B2 (en) | Zero-step user recognition and biometric access control | |
| CN105913241A (en) | Application method of customer authentication system based on image identification | |
| CN105825384A (en) | Application method of face payment apparatus based on fingerprint auxiliary identify identification | |
| CN110599187A (en) | Payment method and device based on face recognition, computer equipment and storage medium | |
| US9646295B1 (en) | Handsfree point-of-sale | |
| WO2021025627A1 (en) | A transaction processing system and a transaction method based on facial recognition | |
| WO2015103970A1 (en) | Method, apparatus and system for authenticating user | |
| CN105913263A (en) | Application method of face payment platform based on image detection |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210112 |
|
| RJ01 | Rejection of invention patent application after publication |