CN110334570B - Face recognition automatic library building method, device, equipment and storage medium - Google Patents

Face recognition automatic library building method, device, equipment and storage medium Download PDF

Info

Publication number
CN110334570B
CN110334570B CN201910253948.0A CN201910253948A CN110334570B CN 110334570 B CN110334570 B CN 110334570B CN 201910253948 A CN201910253948 A CN 201910253948A CN 110334570 B CN110334570 B CN 110334570B
Authority
CN
China
Prior art keywords
store
user data
entering
user
face image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910253948.0A
Other languages
Chinese (zh)
Other versions
CN110334570A (en
Inventor
丁晓刚
陈潘
卢崇志
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Xiaozhou Technology Co ltd
Original Assignee
Shenzhen Xiaozhou Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Xiaozhou Technology Co ltd filed Critical Shenzhen Xiaozhou Technology Co ltd
Priority to CN201910253948.0A priority Critical patent/CN110334570B/en
Publication of CN110334570A publication Critical patent/CN110334570A/en
Application granted granted Critical
Publication of CN110334570B publication Critical patent/CN110334570B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/51—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • G06V40/173—Classification, e.g. identification face re-identification, e.g. recognising unknown faces across different face tracks
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

The invention relates to the technical field of image recognition, in particular to a face recognition automatic library building method, a device, equipment and a storage medium, wherein the face recognition automatic library building method comprises the following steps: acquiring a face image of a person entering a store; acquiring a user identifier according to the face image, and acquiring corresponding user data from a database according to the user identifier; if the user identification cannot be obtained according to the face image, judging that the store entering personnel is a first store entering customer, and automatically establishing a user data table in a database according to the face image of the first store entering customer; marking a user data table by using the characteristic value of the facial image of the customer entering the store for the first time, and storing the facial image and the corresponding characteristic value into the user data table; and writing the consumption behavior information of the store-entering personnel into the corresponding user data table to obtain the user data. The invention has the effects of providing corresponding service for the personnel entering the store according to the face recognition result and improving the efficiency of customer management.

Description

Face recognition automatic library building method, device, equipment and storage medium
Technical Field
The invention relates to the technical field of image recognition, in particular to a face recognition automatic library building method, a face recognition automatic library building device, face recognition automatic library building equipment and a storage medium.
Background
At present, for the management of customers and staff in a store, the staff is generally arranged in the store to serve the customers in the store, wherein the customers are provided with corresponding member levels in order to enhance the consumption experience of the customers. However, when a customer enters a store or a mall, staff in the store can know whether the customer is a member or a member level of the customer only by inquiring the customer or checking out the customer, which results in inefficient management of the customer, and thus there is room for improvement.
The human face identification is to shoot an image containing a human face through a camera device, identify a face image of a human body in the image through an edge acquisition technology, perform gray level processing and binarization on the face image, and extract the face image.
Disclosure of Invention
The invention aims to provide a face recognition automatic database building method, a face recognition automatic database building device, face recognition automatic database building equipment and a storage medium, wherein the face recognition automatic database building method is used for recognizing store entering personnel and providing corresponding services for the store entering personnel according to recognition results, and the efficiency of customer management is improved.
The above object of the present invention is achieved by the following technical solutions:
a face recognition automatic database building method comprises the following steps:
s10: acquiring a face image of a person entering a store;
s20: acquiring a user identifier according to the face image, and acquiring corresponding user data from a database according to the user identifier;
s30: if the user identification cannot be obtained according to the face image, the person entering the store is judged to be a customer entering the store for the first time, and a user data table is automatically established in the database according to the face image of the customer entering the store for the first time;
s40: marking the user data table by using the characteristic value of the face image, and storing the face image and the corresponding characteristic value into the user data table;
s50: and writing the consumption behavior information of the store-entering personnel into the corresponding user data table to obtain the user data.
By adopting the technical scheme, after a customer enters a store, the customer is subjected to face recognition through the camera device in the store, so that a face image is obtained, for the customer who has registered a member and independent user data is established for the customer in the database, a user identification can be recognized according to the face image, the user data can be obtained according to the identification, and a worker can know the condition of the member of the customer in time; if the user identification cannot be obtained through face recognition, the fact that the customer enters the store for the first time can be judged, a user data table is automatically established for the customer entering the store for the first time, the user identification is set according to the face image of the customer, the newly established user data table is marked through the user identification, the consumption behavior of the customer in the store can be written into the user data table, a worker can conveniently provide corresponding services in time, and therefore the efficiency of customer management is improved through face recognition.
The invention is further configured to: the step S10 includes:
s11: setting a unique identifier for in-store camera devices according to the address information of the store, wherein the number of the in-store camera devices is at least 1;
s12: and acquiring the face image of the person entering the store through the in-store camera device.
Through adopting above-mentioned technical scheme, set up a plurality of camera devices in the shop, the consumption action of acquireing the user in the shop that can be better has promoted the richness of user data.
The invention is further configured to: the step S20 includes:
s21: setting a recognition score for the user identifier according to the user data;
s22: obtaining a characteristic value of the face image through a face recognition algorithm, and obtaining the user identification according to the characteristic value;
s23: and scoring the characteristic value, comparing the score with the identification score, and automatically acquiring the face image again if the score of the characteristic value of the face image does not reach the identification score of the user identification.
Through adopting above-mentioned technical scheme, set up the identification score according to user identification, can set up this identification score according to customer's member grade, can improve the precision to high-level member's customer identification, guaranteed the exactness of discernment, avoid the mistake to discern and lead to providing the unmatched service with customer member grade.
The invention is further configured to: the step S30 includes:
s31: if the user identification cannot be obtained according to the face image, automatically building a user data table in the database;
s32: and setting the user identification for the store entering personnel according to the characteristic value of the face recognition image, and marking the user data table by using the user identification.
By adopting the technical scheme, the user data table can be automatically established for the first-time customer entering the store, and the consumption behavior in the customer store can be recorded in the user data table.
The invention is further configured to: after the step S50, the automatic database building method for face recognition further includes:
s51: updating the acquired face image into corresponding user data according to the user identification, and recording the current storage time;
s52: sequencing the face images in the user data according to the storage time;
s53: and if the number of the face images in the user data exceeds a preset threshold value, deleting the face image with the earliest storage time from the user data.
By adopting the technical scheme, because the appearance of the face can be gradually changed according to the time lapse or the change of personal aesthetics, after the face image of the customer is obtained at every time, the face image added firstly is deleted, and the recognition precision can be improved while the memory space of the database is ensured.
The second aim of the invention is realized by the following technical scheme:
an automatic database establishment device for face recognition, comprising:
the image acquisition module is used for acquiring a face image of a person entering a store;
the data acquisition module is used for acquiring a user identifier according to the face image and acquiring corresponding user data from a database according to the user identifier;
the automatic table establishing module is used for judging that the store entering personnel is a first store entering customer if the user identification cannot be obtained according to the face image, and automatically establishing a user data table in the database according to the face image of the first store entering customer;
the storage module is used for marking the user data table by using the characteristic value of the facial image of the customer entering the store for the first time, and storing the facial image and the corresponding characteristic value into the user data table;
and the data updating module is used for writing the consumption behavior information of the store-entering personnel into the corresponding user data table to obtain the user data.
By adopting the technical scheme, after a customer enters a store, the customer is subjected to face recognition through the camera device in the store, so that a face image is obtained, for the customer who has registered a member and independent user data is established for the customer in the database, a user identification can be recognized according to the face image, the user data can be obtained according to the identification, and a worker can know the condition of the member of the customer in time; if the user identification cannot be obtained through face recognition, the customer can be judged to enter the store for the first time, a user data table is automatically established for the customer entering the store for the first time, the user identification is set according to the face image of the customer, the newly established user data table is marked through the user identification, the consumption behavior of the customer in the store can be written into the user data table, the corresponding service can be conveniently provided by staff in time, and therefore the efficiency of customer management is improved through face recognition.
The third object of the invention is realized by the following technical scheme:
a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the above-mentioned face recognition automatic library building method when executing the computer program.
The fourth object of the invention is realized by the following technical scheme:
a computer-readable storage medium, which stores a computer program that, when executed by a processor, implements the steps of the above-described face recognition automatic database building method.
In conclusion, the beneficial technical effects of the invention are as follows:
1. after a customer enters a store, carrying out face recognition on the customer through a camera device in the store to obtain a face image, for the customer who has registered a member and independent user data is established for the customer in a database, identifying a user identifier according to the face image, and acquiring user data according to the identifier to enable a worker to know the condition of the member of the customer in time;
2. if the user identification cannot be obtained through face recognition, the customer can be judged to enter the store for the first time, a user data table is automatically established for the customer entering the store for the first time, the user identification is set according to the face image of the customer, the newly established user data table is marked through the user identification, the consumption behavior of the customer in the store can be written into the user data table, the corresponding service can be conveniently provided by staff in time, and therefore the efficiency of customer management is improved through face recognition.
Drawings
FIG. 1 is a flow chart of an automatic database building method for face recognition according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating an implementation of step S10 in the automatic database creation method for face recognition according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating an implementation of step S20 in the automatic database creation method for face recognition according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating an implementation of step S30 in the automatic database creation method for face recognition according to an embodiment of the present invention;
FIG. 5 is a flow chart of another implementation of the automatic database building method for face recognition according to an embodiment of the present invention;
FIG. 6 is a schematic block diagram of an automatic face recognition library building apparatus according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a computer device according to an embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
The first embodiment is as follows:
in one embodiment, as shown in fig. 1, the present invention discloses an automatic database building method for face recognition, which specifically includes the following steps:
s10: and acquiring a face image of the person entering the store.
In this embodiment, the person entering the store refers to a person entering the store or the mall, including a customer and a staff in the store.
Specifically, an imaging device is installed in a shop or a mall so that the imaging device can capture the face area of a person entering the shop. The face image of the person entering the store is shot and acquired through the camera device.
S20: and acquiring a user identifier according to the face image, and acquiring corresponding user data from a database according to the user identifier.
In this embodiment, the user identifier refers to a unique identifier for distinguishing each user, which may be identity information of the user or a user id automatically generated by the server. The user data is a data set in which information such as a consumption record of a customer, a member level, and an attendance record for a worker is recorded. The database is used for storing user data of shops or shopping malls, wherein the database is an open source database and can be used by a certain shop alone or shared by all shops in a certain shopping mall.
In particular, for customers who have a store or store member registered therein or when staff members enter their jobs, a data set usable for storing the user data is automatically generated at the time of registration. The method comprises the steps of shooting a face photo for comparison on a customer or a staff who enters a job of a registered member, extracting a corresponding characteristic value through the existing face recognition method, automatically generating a unique user identification as a label of a data set according to the characteristic value, and binding and associating the user identification with identity information of the customer or the staff.
Further, after a customer or a staff member of a registered member enters a store, the corresponding user identifier is obtained through the obtained face image and the characteristic value, and the corresponding user data is obtained through the user identifier. The user data can be transmitted to a mobile terminal of an in-store worker, so that the in-store worker can know that the customer is a member of the storefront.
S30: and if the user identification cannot be obtained according to the face image, judging that the store entering personnel is a first store entering customer, and automatically establishing a user data table in the database according to the face image of the first store entering customer.
In the present embodiment, the user data table refers to a user data table for data of a customer who enters a store or a mall for the first time.
Specifically, if the user identifier is not obtained from the obtained face image, it is determined that the customer entering the store is the first customer entering the store. And automatically establishing a user data table for the customer according to the characteristic value corresponding to the acquired face image.
Preferably, after the user data table is established, a corresponding message is sent to the mobile terminal of the staff in the store, so that the staff knows that the customer entering the store is the first time to enter the store.
S40: and marking the user data table by using the characteristic value of the facial image of the customer entering the store for the first time, and storing the facial image and the corresponding characteristic value into the user data table.
Specifically, according to the feature value of the face image of the customer entering the store for the first time, the user identifier is set for the customer entering the store for the first time in the manner of step S20, and the user data table is marked by using the user identifier. Further, the face image and the corresponding feature value are stored in the user data table, so that subsequent identification is facilitated.
Preferably, when the first-time customer leaves the store and then enters the store again, the customer is known to be a revisited customer by recognizing a face image of the customer.
S50: and writing the consumption behavior information of the store-entering personnel into the corresponding user data table to obtain the user data.
In the present embodiment, the consumption behavior information refers to behavior information of store-entering personnel in a store or a store. Including records of purchases and browsing by the customer.
Specifically, after the customer enters the store, the consumption behavior information of the customer is written into the corresponding user data table to obtain the user data.
Preferably, for the staff, the identification record can be added into the attendance record of the staff by identifying the identity of the staff.
In the embodiment, after a customer enters a store, the customer is subjected to face recognition through a camera device in the store, so that a face image is obtained, for the customer who has registered a member and independent user data is established for the customer in a database, a user identifier can be recognized according to the face image, the user data can be obtained according to the identifier, and a worker can know the condition of the member of the customer in time; if the user identification cannot be obtained through face recognition, the fact that the customer enters the store for the first time can be judged, a user data table is automatically established for the customer entering the store for the first time, the user identification is set according to the face image of the customer, the newly established user data table is marked through the user identification, the consumption behavior of the customer in the store can be written into the user data table, a worker can conveniently provide corresponding services in time, and therefore the efficiency of customer management is improved through face recognition.
In an embodiment, as shown in fig. 2, in step S10, acquiring a face image of a person entering the store specifically includes the following steps:
s11: and setting a unique identifier for the in-store camera devices according to the address information of the store, wherein the number of the in-store camera devices is at least 1.
Specifically, 1 camera device is arranged at a door of a store, and a unique identifier is set for the camera device in the store according to address information of the store, so that a face image acquired by the camera device is bound with the store or a market.
Preferably, in order to make the data obtained about the behavior of the people in the storefront more abundant and accurate, 1-2 camera devices may be respectively arranged at the doorway, the cashier desk and the store, so that the data in the database may include the data about the people entering the store, and the behavior of the people in the store may be obtained by the camera devices arranged in the store and the cashier desk, for example, by obtaining the area where the customer walks and stays in the store, analyzing the area where the customer is relatively gathered in the store, and analyzing the types of the goods of interest of the customer according to the goods set in the area.
S12: and acquiring a human face image of the person entering the store through an in-store camera device.
Specifically, the in-store person is shot by the in-store camera device, so that the face image of the in-store person is acquired.
Further, as shown in fig. 3, in step S20, that is, acquiring a user identifier according to the face image, and acquiring corresponding user data from the database according to the user identifier, the method specifically includes the following steps:
s21: and setting a recognition score for the user identification according to the user data.
In the present embodiment, the recognition score refers to the accuracy of face recognition for setting for different users.
Specifically, for the user identification as a worker, the identification score can be set to 85% due to the attendance system; for user identification as families, identification scores may be set according to the rank of the member, such as 80%, 75%, 70%, etc., for different levels of member customers.
S22: and acquiring a characteristic value of the face image through a face recognition algorithm, and acquiring a user identifier according to the characteristic value.
Specifically, after gray processing and binarization are performed on the face image through a face recognition algorithm, the characteristic value of the face image is extracted. Further, a specific user identifier is obtained according to the characteristic value.
S23: and grading the characteristic values, comparing the grades with the identification scores, and automatically acquiring the face image again if the grades of the characteristic values of the face image do not reach the identification scores of the user identifications.
Specifically, after the feature value corresponding to the face image of the person entering the door is identified in step S22, the user identifier of the person entering the door is queried according to the feature value matching, and the identification score corresponding to the user identifier is obtained from the user identifier. Since the recognition score is a score which represents the accuracy of face recognition, the recognition accuracy of the characteristic value can be scored firstly, the score is compared with the recognition score, and if the score is lower than the recognition score, the face image is automatically obtained again.
Understandably, the recognition score is to further ensure that the recognition result corresponds to an authentic individual. That is, although 80% of the members who enter the house are identified by face recognition, the identification score is only 76%, and in order to ensure the authenticity of the identification, face recognition needs to be performed on the person who enters the house again until the identification score reaches 80% or more.
In an embodiment, as shown in fig. 4, in step S30, that is, if the user identifier is not obtained from the facial image, it is determined that the person entering the store is a first customer entering the store, and a user data table is automatically created in the database according to the facial image of the first customer entering the store, which specifically includes the following steps:
s31: and if the user identification cannot be obtained according to the face image, automatically creating a user data table in the database.
Specifically, if the user identification cannot be obtained according to the face image, it is determined that the person who enters the store is the first person who enters the store, and a user data table is automatically established in the database and used for storing data of the person who enters the store for the first time.
S32: and setting user identification for the store entering personnel according to the characteristic value of the face recognition image, and marking a user data table by using the user identification.
Specifically, by the method in step S22, the feature value of the person entering the store for the first time is obtained, a unique user identifier is generated for the person entering the store, and the user identifier is tagged with the user data table.
Preferably, the user data table may record the visit time of the customer entering the store for the first time, and the shelf area with the longest stay. If the customer is identified to enter the store again, the staff member may recommend similar or related products for the customer in the shelf area.
In an embodiment, as shown in fig. 5, after step S50, the method for automatically creating a database for face recognition further includes:
s51: and updating the acquired face image into corresponding user data according to the user identification, and recording the current storage time.
In this embodiment, the storage time refers to a specific time when each face image is stored in the corresponding user data.
Specifically, when the face image is updated and stored to the corresponding user data according to the user identifier each time, the current time is recorded as the storage time, and the storage time and the face image are used as a label. Note that the face image such as the user data is updated to the face image that has reached the corresponding recognition score.
S52: and sequencing the face images in the user data according to the storage time.
Specifically, the face images in the user data are sorted according to the storage time from the first time of storing the face images in the user data.
S53: and if the number of the face images in the user data exceeds a preset threshold value, deleting the face image with the earliest storage time from the user data.
Specifically, if the number of stored face images exceeds 10 in the user data, the face image with the earliest storage time is deleted from the user data.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Example two:
in an embodiment, a face recognition automatic database establishment device is provided, and the face recognition automatic database establishment device corresponds to the face recognition automatic database establishment method in the embodiment one to one. As shown in fig. 6, the automatic face recognition library establishing device includes an image obtaining module 10, a data obtaining module 20, an automatic table establishing module 30, a storage module 40 and a data updating module 50. The functional modules are explained in detail as follows:
the image acquisition module 10 is used for acquiring a face image of a person entering a store;
a data obtaining module 20, configured to obtain a user identifier according to the face image, and obtain corresponding user data from a database according to the user identifier;
a table automatic establishing module 30, configured to determine that the store entering person is a first store entering customer if the user identifier is not obtained according to the facial image, and automatically establish a user data table in the database according to the facial image of the first store entering customer;
a storage module 40, configured to mark the user data table with a feature value of the facial image of the customer entering the store for the first time, and store the facial image and the corresponding feature value in the user data table;
and the data updating module 50 is configured to write the consumption behavior information of the store entering personnel into the corresponding user data table to obtain the user data.
Preferably, the image acquisition module 10 comprises:
the identification setting submodule 11 is configured to set a unique identification for the in-store camera devices according to the store address information, where the number of the in-store camera devices is at least 1;
and the image acquisition sub-module 12 is configured to acquire the facial image of the person entering the store through the in-store camera device.
Preferably, the data acquisition module 20 comprises:
the score setting submodule 21 is configured to set an identification score for the user identifier according to the user data;
the identification generation submodule 22 is used for acquiring a characteristic value of the face image through a face recognition algorithm and acquiring the user identification according to the characteristic value;
and the data acquisition submodule 23 is configured to score the feature value, compare the score with the identification score, and automatically acquire the face image again if the score of the feature value of the face image does not reach the identification score of the user identifier.
Preferably, the table automatic creation module 30 includes:
a table automatic establishing submodule 31, configured to automatically establish a new user data table in the database if the user identifier is not obtained according to the face image;
and the marking submodule 32 is configured to set the user identifier for the store entering person according to the feature value of the face recognition image, and mark the user data table by using the user identifier.
Preferably, the automatic face recognition library creating device further comprises:
the time recording module 51 is configured to update the acquired face image into the corresponding user data according to the user identifier, and record current storage time;
a sorting module 52, configured to sort the facial images in the user data according to the storage time;
a data iteration module 53, configured to delete the facial image with the earliest storage time from the user data if the number of the facial images in the user data exceeds a preset threshold.
For specific limitations of the automatic face recognition library building device, reference may be made to the above limitations of the automatic face recognition library building method, which are not described herein again. All modules in the face recognition automatic library establishing device can be completely or partially realized through software, hardware and a combination of the software and the hardware. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
Example three:
in one embodiment, a computer device is provided, which may be a server, and the internal structure thereof may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for user data and consumption behavior information. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an automatic library building method for face recognition.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
s10: acquiring a face image of a person entering a store;
s20: acquiring a user identifier according to the face image, and acquiring corresponding user data from a database according to the user identifier;
s30: if the user identification cannot be obtained according to the face image, the person entering the store is judged to be a customer entering the store for the first time, and a user data table is automatically established in the database according to the face image of the customer entering the store for the first time;
s40: marking the user data table by using the characteristic value of the facial image of the customer entering the store for the first time, and storing the facial image and the corresponding characteristic value into the user data table;
s50: and writing the consumption behavior information of the store-entering personnel into the corresponding user data table to obtain the user data.
Example four:
in one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
s10: acquiring a face image of a person entering a store;
s20: acquiring a user identifier according to the face image, and acquiring corresponding user data from a database according to the user identifier;
s30: if the user identification cannot be obtained according to the face image, the person entering the store is judged to be a customer entering the store for the first time, and a user data table is automatically established in the database according to the face image of the customer entering the store for the first time;
s40: marking the user data table by using the characteristic value of the facial image of the customer entering the store for the first time, and storing the facial image and the corresponding characteristic value into the user data table;
s50: and writing the consumption behavior information of the store-entering personnel into the corresponding user data table to obtain the user data.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It should be clear to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional units and modules is only used for illustration, and in practical applications, the above function distribution may be performed by different functional units and modules as needed, that is, the internal structure of the apparatus may be divided into different functional units or modules to perform all or part of the above described functions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.

Claims (5)

1. A face recognition automatic database building method is characterized by comprising the following steps:
s10: acquiring a face image of a person entering the store, wherein the step S10 includes:
s11: setting a unique identifier for in-store camera devices according to the address information of the store, wherein the number of the in-store camera devices is at least 1;
s12: acquiring the face image of the person entering the store through the in-store camera device;
s20: acquiring a user identifier according to the face image, and acquiring corresponding user data from a database according to the user identifier, wherein step S20 includes:
s21: setting a recognition score for the user identification according to the user data, wherein the recognition score refers to the accuracy of face recognition for different users;
s22: obtaining a characteristic value of the face image through a face recognition algorithm, and obtaining the user identification according to the characteristic value;
s23: scoring the characteristic value, comparing the score with the identification score, and automatically acquiring the face image again if the score of the characteristic value of the face image does not reach the identification score of the user identification;
s30: if the user identifier is not obtained according to the facial image, it is determined that the person entering the store is a first customer entering the store, and a user data table is automatically established in the database according to the facial image of the first customer entering the store, and step S30 includes:
s31: if the user identification cannot be obtained according to the face image, automatically building a user data table in the database;
s32: setting the user identification for the store entering personnel according to the characteristic value of the face recognition image, and marking the user data table by using the user identification;
s40: marking the user data table by using the characteristic value of the facial image of the customer entering the store for the first time, and storing the facial image and the corresponding characteristic value into the user data table;
s50: and writing the consumption behavior information of the store-entering personnel into the corresponding user data table to obtain the user data.
2. The automatic library building method for face recognition according to claim 1, wherein after step S50, the automatic library building method for face recognition further comprises:
s51: updating the acquired face image into corresponding user data according to the user identification, and recording the current storage time;
s52: sequencing the face images in the user data according to the storage time;
s53: and if the number of the face images in the user data exceeds a preset threshold value, deleting the face image with the earliest storage time from the user data.
3. The automatic human face recognition library establishing device is characterized by comprising the following components:
the image acquisition module is used for acquiring the face image of the person entering the store, and comprises:
the identification setting submodule is used for setting unique identifications for the in-store camera devices according to the address information of the stores, wherein the number of the in-store camera devices is at least 1;
the image acquisition sub-module is used for acquiring the face image of the person entering the store through the in-store camera device;
a data obtaining module, configured to obtain a user identifier according to the face image, and obtain corresponding user data from a database according to the user identifier, where the data obtaining module includes:
the score setting submodule is used for setting a recognition score for the user identification according to the user data, wherein the recognition score is used for setting the accuracy of face recognition for different users;
the identification generation submodule is used for acquiring a characteristic value of the face image through a face recognition algorithm and acquiring the user identification according to the characteristic value;
the data acquisition sub-module is used for scoring the characteristic value, comparing the score with the identification score, and automatically acquiring the face image again if the score of the characteristic value of the face image does not reach the identification score of the user identifier;
the automatic table establishing module is used for judging that the store entering personnel is a first store entering customer if the user identification cannot be obtained according to the face image, and automatically establishing a user data table in the database according to the face image of the first store entering customer, and the automatic table establishing module comprises:
a table automatic establishing sub-module, configured to automatically establish the user data table in the database if the user identifier is not obtained according to the face image;
the marking sub-module is used for setting the user identification for the store entering personnel according to the characteristic value of the face recognition image and marking the user data table by using the user identification;
the storage module is used for marking the user data table by using the characteristic value of the facial image of the customer entering the store for the first time, and storing the facial image and the corresponding characteristic value into the user data table;
and the data updating module is used for writing the consumption behavior information of the store-entering personnel into the corresponding user data table to obtain the user data.
4. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the face recognition automatic library building method according to any one of claims 1 to 2.
5. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the automatic library construction method for face recognition according to any one of claims 1 to 2.
CN201910253948.0A 2019-03-30 2019-03-30 Face recognition automatic library building method, device, equipment and storage medium Active CN110334570B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910253948.0A CN110334570B (en) 2019-03-30 2019-03-30 Face recognition automatic library building method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910253948.0A CN110334570B (en) 2019-03-30 2019-03-30 Face recognition automatic library building method, device, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN110334570A CN110334570A (en) 2019-10-15
CN110334570B true CN110334570B (en) 2022-09-16

Family

ID=68139259

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910253948.0A Active CN110334570B (en) 2019-03-30 2019-03-30 Face recognition automatic library building method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN110334570B (en)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111178966A (en) * 2019-12-30 2020-05-19 武汉零客思唯科技有限公司 Latent customer behavior analysis method and system based on face recognition
CN111950364B (en) * 2020-07-07 2024-03-22 北京思特奇信息技术股份有限公司 System and method for identifying library-separating face of tens of millions of libraries
CN111898559B (en) * 2020-08-03 2024-04-26 南京奥拓电子科技有限公司 Method and device for improving face recognition speed and electronic equipment
CN112150203A (en) * 2020-09-23 2020-12-29 创新奇智(青岛)科技有限公司 Real estate client visit identification method and device, electronic equipment and storage medium
CN112215653A (en) * 2020-10-12 2021-01-12 珠海格力电器股份有限公司 Commodity recommendation method, commodity recommendation device, server and storage medium
CN112215657A (en) * 2020-10-14 2021-01-12 珠海格力电器股份有限公司 Recommended commodity determining method and device, electronic equipment and storage medium
CN112784784A (en) * 2021-01-29 2021-05-11 新疆爱华盈通信息技术有限公司 Personnel information statistical method and system based on face recognition
CN112651793A (en) * 2021-02-09 2021-04-13 广东天正计算机服务有限公司 Intelligent retail system based on face recognition
CN113177770A (en) * 2021-04-13 2021-07-27 Tcl华星光电技术有限公司 Electronic work card generation method and device, storage medium and electronic equipment

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108597065A (en) * 2018-03-12 2018-09-28 南京甄视智能科技有限公司 Passenger flow statistical method based on recognition of face
CN109345316A (en) * 2018-10-23 2019-02-15 出门问问信息科技有限公司 Information processing method, device, electronic equipment and computer readable storage medium

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080031741A1 (en) * 2006-08-02 2008-02-07 Torres Martin R Jet pump slip joint with axial grooves
KR100847136B1 (en) * 2006-08-14 2008-07-18 한국전자통신연구원 Method and Apparatus for Shoulder-line detection and Gesture spotting detection

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108597065A (en) * 2018-03-12 2018-09-28 南京甄视智能科技有限公司 Passenger flow statistical method based on recognition of face
CN109345316A (en) * 2018-10-23 2019-02-15 出门问问信息科技有限公司 Information processing method, device, electronic equipment and computer readable storage medium

Also Published As

Publication number Publication date
CN110334570A (en) 2019-10-15

Similar Documents

Publication Publication Date Title
CN110334570B (en) Face recognition automatic library building method, device, equipment and storage medium
US11023533B2 (en) Node task data display method and apparatus, storage medium and computer equipment
CN109729383B (en) Double-recording video quality detection method and device, computer equipment and storage medium
US10699168B1 (en) Computer-executed method and apparatus for assessing vehicle damage
CN108038176B (en) Method and device for establishing passerby library, electronic equipment and medium
CN109450771B (en) Method and device for adding friends, computer equipment and storage medium
CN109992601B (en) To-do information pushing method and device and computer equipment
CN109816200B (en) Task pushing method, device, computer equipment and storage medium
CN109636582B (en) Credit information management method, apparatus, device and storage medium
CN109191635B (en) Passenger judging method and device based on face recognition technology and storage medium
CN108764239A (en) Invoice tests fake method, device, computer equipment and storage medium
WO2007129474A1 (en) Object recognition device, object recognition program, and image search service providing method
CN117114514B (en) Talent information analysis management method, system and device based on big data
CN105095479A (en) Mobile terminal and method for achieving photo classification management
CN110689325A (en) Information processing method, device and computer readable storage medium
CN109840778A (en) The recognition methods of fraudulent user and device, readable storage medium storing program for executing
CN110675252A (en) Risk assessment method and device, electronic equipment and storage medium
CN110717509A (en) Data sample analysis method and device based on tree splitting algorithm
CN101286163A (en) Recognition method based on recognition knowledge base
CN113793174A (en) Data association method and device, computer equipment and storage medium
KR20220073295A (en) Apparatus for estimating market price of real estate and method thereof
CN111539390A (en) Small target image identification method, equipment and system based on Yolov3
CN115860315A (en) Enterprise customer relationship management system and data processing method
CN114781517A (en) Risk identification method and device and terminal equipment
CN109636578A (en) Risk checking method, device, equipment and the readable storage medium storing program for executing of credit information

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant