CN113516814B - Intelligent supply method and terminal based on face recognition - Google Patents
Intelligent supply method and terminal based on face recognition Download PDFInfo
- Publication number
- CN113516814B CN113516814B CN202110422007.2A CN202110422007A CN113516814B CN 113516814 B CN113516814 B CN 113516814B CN 202110422007 A CN202110422007 A CN 202110422007A CN 113516814 B CN113516814 B CN 113516814B
- Authority
- CN
- China
- Prior art keywords
- goods
- image
- taking
- face
- similarity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000008569 process Effects 0.000 claims abstract description 16
- 238000007726 management method Methods 0.000 claims description 32
- 238000007781 pre-processing Methods 0.000 claims description 27
- 238000011156 evaluation Methods 0.000 claims description 16
- 238000013527 convolutional neural network Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 7
- 235000008645 Chenopodium bonus henricus Nutrition 0.000 claims description 4
- 238000002716 delivery method Methods 0.000 claims description 4
- 241000531116 Blitum bonus-henricus Species 0.000 claims 1
- 230000006870 function Effects 0.000 description 22
- 230000001681 protective effect Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 238000004659 sterilization and disinfection Methods 0.000 description 4
- 244000138502 Chenopodium bonus henricus Species 0.000 description 3
- 238000007599 discharging Methods 0.000 description 3
- 235000013305 food Nutrition 0.000 description 3
- 230000005802 health problem Effects 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001954 sterilising effect Effects 0.000 description 2
- 244000000231 Sesamum indicum Species 0.000 description 1
- 235000003434 Sesamum indicum Nutrition 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000249 desinfective effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F17/00—Coin-freed apparatus for hiring articles; Coin-freed facilities or services
- G07F17/10—Coin-freed apparatus for hiring articles; Coin-freed facilities or services for means for safe-keeping of property, left temporarily, e.g. by fastening the property
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
Abstract
The application discloses intelligent supply method and terminal based on face identification, wherein the intelligent supply terminal can collect registered face images, a preset registered image library is used for storage, when the intelligent supply terminal supplies goods, a shooting module can be controlled to shoot faces of goods-taking users located in a goods-taking area so as to obtain goods-taking face images, the first image similarity of each registered face image in the registered image library and the goods-taking face images is identified, when the first image similarity is detected to be larger than or equal to a first similarity threshold value, a goods-taking module is controlled to execute goods-out operation, and goods supply is carried out in time, the supply process is effectively simplified, the supply efficiency is improved, labor cost is saved, and goods-taking experience is improved.
Description
Technical Field
The application relates to the technical field of face recognition, in particular to an intelligent goods supply method and terminal based on face recognition.
Background
In many organizations such as companies, supply of articles such as office supplies, daily supplies, and daily foods requires management by a dedicated person, and it is difficult for the person who manages the articles to be on duty all day long, and the supply efficiency is unstable due to factors such as experience and environment. With the rise of the self-service supply terminals, some organization groups introduce the self-service supply terminals provided by external merchants, and the self-service supply terminals are not limited by time and can respond to the taking requirements of users to a certain extent by responding to the advantages of the goods taking requirements of the users all day long.
However, the self-service goods supply terminal provided by the external merchant usually needs means such as coin and/or mobile phone electronic payment to realize fee payment to obtain the required goods, so that it is difficult to respond to the user's demand for use under the condition that no coin or mobile phone is powered off, and the payment method using coin and/or mobile phone electronic payment is relatively complicated, which easily affects the shipment efficiency.
Disclosure of Invention
In view of this, the present application provides an intelligent supply method and terminal based on face recognition, so as to simplify the supply process and improve the supply efficiency.
One aspect of the present application provides an intelligent supply method based on face recognition, which is applied to an intelligent supply terminal, where the intelligent supply terminal includes a shipment module, and the method includes:
s100, acquiring a face image shot by a shooting module on a goods-taking user in a goods-taking area at present to obtain a goods-taking face image;
s200, identifying the first image similarity of each registered face image in a prestored registered image library and the goods-taking face image respectively; the registered image library records face images of all goods supply objects;
and S300, controlling the shipment module to execute shipment operation when the first image similarity which is greater than or equal to the first similarity threshold is detected.
In one embodiment, the intelligent supply method based on face recognition further includes:
s400, if the similarity of each first image is smaller than the first similarity threshold, when the similarity of the first images is larger than or equal to the second similarity threshold, determining the registered face image corresponding to the similarity of the first images larger than or equal to the second similarity threshold as an image to be compared;
s500, inputting the goods-taking face image into a preprocessing model for filtering to obtain a preprocessing image; the preprocessing model is used for filtering noise information of the face image;
s600, identifying second image similarity between the preprocessed image and the image to be compared, and controlling the delivery module to execute delivery operation if the second image similarity is greater than or equal to a first similarity threshold value.
Specifically, the training process of the preprocessing model comprises the following steps:
s510, acquiring face images shot for a plurality of test users in a specific shooting environment to obtain input sample images, and acquiring high-definition face images corresponding to the input sample images to obtain output sample images; the high-definition face image is a face image with quality parameters meeting preset quality conditions;
s520, training a convolutional neural network by taking the input sample image as input and the output sample image as output, and acquiring a loss function of the convolutional neural network in the training process;
and S540, when the loss function reaches a preset state, determining a preprocessing model according to the network parameters of the convolutional neural network.
Specifically, the intelligent supply method based on face recognition further includes:
s530, obtaining the minimum value of the loss function, and if the minimum value is smaller than or equal to a convergence threshold value, judging that the loss function reaches a preset state; if the minimum value is greater than the convergence threshold, increasing the number of the input sample images and the number of the output sample images, and returning to execute step S520 until the minimum value of the loss function is less than or equal to the convergence threshold.
In one embodiment, the intelligent supply terminal further includes a pickup window, and the controlling the shipment module to perform shipment operations includes:
s310, outputting a selection range of the supplied goods, and reading the target goods selected by the goods taking user in the selection range;
and S320, controlling the goods outlet module to push the target object to a goods taking window.
Specifically, the registered image library records balance data of each registered face image; the controlling the shipment module to push the target item to a pickup window comprises:
and obtaining the selling price data of the target article, if the selling price data is less than or equal to the balance data, controlling the shipment module to push the target article to a pickup window, and updating the balance data into the difference between the balance data and the selling price data.
Specifically, the intelligent supply method based on face recognition further includes:
s700, if the similarity of each first image is smaller than the second similarity threshold value, acquiring a credit evaluation parameter corresponding to the goods-taking face image from an external credit evaluation platform, acquiring a contact account number of the goods-taking user through a dialog window of the acquired contact account number when the credit evaluation parameter is larger than or equal to the credit threshold value, controlling the goods-taking module to execute goods-taking operation, acquiring goods-taking information, and pushing the contact account number, the goods-taking information and the goods-taking face image to a management terminal so that the management terminal provides a payment path and/or a registration path for the goods-taking user through the contact account number.
Specifically, the intelligent supply method based on face recognition further includes:
s800, if the registration information of the goods-taking face image fed back by the management terminal is detected within a set time period, adding the goods-taking face image as a registration face image to the registration image library; if the registration information or payment information of the goods-taking face image fed back by the management terminal is not detected within a set time period, adding the goods-taking face image to a limited image library; the limited image library is used for recording face images without goods taking authority.
Specifically, when each of the first image similarities is smaller than the second similarity threshold, the intelligent supply method based on face recognition further includes:
and S900, identifying the similarity between each limit face image in the limit image library and a third image of the goods-taking face image, and outputting a prompt message of the end of shipment if the similarity of the third image is greater than or equal to a third similarity threshold.
Another aspect of the application provides an intelligent goods supply terminal, which includes a shooting module, a shipment module, a processor and a storage medium; the storage medium having program code stored thereon; the shooting module is used for shooting a face image of a goods taking user in a goods taking area to obtain a goods taking face image and uploading the goods taking face image to the processor; the processor is used for calling the program codes stored in the storage medium to execute any one of the intelligent goods supplying methods based on the face recognition; the shipment module is used for executing shipment operation under the control of the processor.
The intelligent goods supply method and the terminal based on face recognition can control the shooting module to shoot the face of a goods taking user located in a goods taking area so as to obtain a goods taking face image, recognize the first image similarity of each registered face image in the registered image library and the goods taking face image, control the goods delivery module to execute goods delivery operation when detecting that the first image similarity is larger than or equal to a first similarity threshold value, timely supply goods, effectively simplify the goods supply process, improve the goods supply efficiency, are beneficial to saving labor cost and improve the goods taking experience.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of an intelligent goods supply method based on face recognition according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of an intelligent goods supply system based on face recognition according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an intelligent supply terminal according to an embodiment of the present application.
Detailed Description
As described in the background art, the scheme of managing articles such as office documents, living users and/or daily food by a specially-assigned person is difficult to realize on duty all day long, and is liable to cause unstable supply efficiency, and the supply manner of the self-service supply terminal is relatively complicated, and liable to affect the shipment efficiency.
The application aims at the problems and provides an intelligent supply method and a terminal based on face recognition, wherein the intelligent supply method based on face recognition can be operated on the intelligent supply terminal. The intelligent goods supply terminal can be arranged in a corresponding area according to the goods taking characteristics of a target user needing to supply goods, such as goods receiving use in a certain office area, a front desk of a certain office building or a free goods sending place of a certain public service organization; it is also possible to provide a recharge function as a vending terminal at a related vending place, etc. The intelligent goods supply terminal can shoot (or upload) the face image of the user or collect the registered face image by related management personnel during user registration, the registered face image is stored in a preset registered image library, when the intelligent goods supply terminal supplies goods, the shooting module can be controlled to shoot the face of a goods taking user in a goods taking area so as to obtain the goods taking face image, the similarity between each registered face image in the registered image library and a first image of the goods taking face image is identified, when the similarity of the first image is detected to be larger than or equal to a first similarity threshold value, the goods output module is controlled to execute goods output operation, and the goods supply process is effectively simplified, the goods supply efficiency is improved, the labor cost is saved, and the goods taking experience is improved.
The technical solutions in the embodiments of the present application are clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application. The following embodiments and their technical features may be combined with each other without conflict.
The first aspect of the present application provides an intelligent supply method based on face recognition, which is applied to an intelligent supply terminal, and specifically can be run in a processor of the intelligent supply terminal, where the intelligent supply terminal includes a shipment module, as shown in fig. 1, and the method includes:
s100, acquiring a face image shot by the shooting module on the goods taking user in the goods taking area at present to obtain the goods taking face image.
The goods taking area is usually arranged right in front of the intelligent goods supplying terminal, and the shooting module can be arranged at the front side of the intelligent goods supplying terminal and close to the upper position, so that the face of the goods taking user can be shot smoothly when the goods taking user is located in the goods taking area.
Specifically, above-mentioned shooting module is including taking a picture the camera lens, and this taking a picture the mounted position of camera lens can preset, and this mounted position includes horizontal position and vertical position, and horizontal position can set up on the central line of intelligent supply terminal front side or the symmetry line of vertical direction, and target user's height equipment can be referred to vertical position, for example sets up in target user's average height. In one example, an infrared detector can be further arranged on the front side of the intelligent goods supply terminal to detect height information and station information of a goods-taking user and upload the height information and the station information to a processor of the intelligent goods supply terminal; the shooting module can be used for controlling the shooting lens to move in a certain range of the front side surface of the intelligent supply terminal, for example, in a range taking the installation position as the center of a circle and taking the set length as the radius. Therefore, after the processor receives the height information and the station information detected by the infrared detector, the optimal shooting position of the shooting lens is calculated by combining the moving range of the shooting lens, the optimal shooting position is sent to the shooting module, the shooting module controls the shooting lens to move to the optimal shooting position, the face of the goods taking user is accurately and completely shot, and the effective goods taking face image is obtained.
S200, identifying the first image similarity of each registered face image in a prestored registered image library and the goods-taking face image respectively; the registered image library records face images of all goods supplying objects.
The registered image library can be preset and can record face images of all target users (goods supply objects) needing goods supply; the system can be set according to the characteristics of a goods supply object (target user), for example, if the goods supply object is all employees of a certain company, the administrative staff of the company can collect the face images of all employees, so that a registered image stock is constructed and stored in an intelligent goods supply terminal; for example, if the goods supply object is a public service goods receiving person, an active registration channel can be provided for the person to provide registration information and a face image, a registration image library is constructed according to the corresponding face image after the registration information is checked, and the registration image library is updated according to the corresponding face image after the new registration information is checked and passed when the new registration information and the corresponding face image are received subsequently.
The above steps respectively calculate the similarity (first image similarity) between each registered face image in the registered image library and the pickup face image, so as to search the registered face image matched with the pickup face image in the registered image library. The process for determining the similarity between a certain registered face image and a goods-taking face image comprises the following steps: respectively extracting feature codes of the registered face image and the goods-taking face image, and calculating the similarity of the registered face image and the goods-taking face image according to the feature codes of the registered face image and the goods-taking face image; or respectively comparing the pixel similarity of corresponding pixel points between the registered face image and the goods-taking face image, determining the pixel similarity between the registered face image and the goods-taking face image according to the pixel similarity, and the like. It should be noted that, the determination process of the similarity between two images is applicable to the identification of the similarity of each image (such as the similarity of the first image, the similarity of the second image, and the similarity of the third image) in the present application.
And S300, controlling a discharging module (also called as a discharging module) to execute discharging operation when the first image similarity which is greater than or equal to the first similarity threshold is detected.
The first similarity threshold may be set to a value close to 1, such as 95%. The similarity of a certain first image is greater than or equal to a first similarity threshold value, the registered face image with the similarity of the first image and the goods-taking face image are represented to be images of the same user, the goods-taking user is a goods-supplying object of the intelligent goods-supplying terminal, and at the moment, the goods-outputting module can be controlled to execute goods-outputting operation, so that corresponding goods are provided, and the goods-supplying efficiency is ensured.
In one embodiment, the intelligent supply method based on face recognition further includes:
s400, if the similarity of each first image is smaller than the first similarity threshold, when the similarity of the first images is larger than or equal to the second similarity threshold, determining the registered face image corresponding to the similarity of the first images larger than or equal to the second similarity threshold as an image to be compared;
s500, inputting the goods-taking face image into a preprocessing model for filtering to obtain a preprocessing image; the preprocessing model is used for filtering noise information of the face image;
s600, identifying the second image similarity between the preprocessed image and the image to be compared, and controlling the delivery module to execute delivery operation if the second image similarity is larger than or equal to a first similarity threshold value.
The second similarity threshold may be set to a value slightly smaller than the first similarity threshold, such as 92%. The similarity of each first image is smaller than a first similarity threshold, which indicates that each registered face image in the registered image library cannot be directly matched with the goods-taking face image, if the similarity of the first image is larger than or equal to a second similarity threshold, the similarity of the corresponding registered face image (image to be compared) and the goods-taking face image with the first image similarity larger than or equal to the second similarity threshold is higher, and the goods-taking face image has high noise and/or low quality due to shooting angles, shooting environments and the like, at this time, the goods-taking face image can be input into a preprocessing model for filtering so as to remove noise and/or repair, so as to obtain a preprocessed image with quality higher than that of the original goods-taking face image, and then the preprocessed image is compared with the images to be compared to obtain the similarity of the second image between the preprocessed image and the goods-taking face image, and the preprocessed image can be matched with the images to be compared, so that a corresponding goods-taking user is one of goods-providing objects, at this time, the goods-taking terminal can be controlled to perform the goods-taking operation, and promote the intelligent goods-taking user.
Specifically, the training process of the preprocessing model comprises the following steps:
s510, acquiring face images shot for a plurality of test users in a specific shooting environment to obtain input sample images, and acquiring high-definition face images corresponding to the input sample images to obtain output sample images; the high-definition face image is a face image with quality parameters meeting preset quality conditions;
s520, training a convolutional neural network by taking the input sample image as input and the output sample image as output, and acquiring a loss function of the convolutional neural network in the training process;
and S540, when the loss function reaches a preset state, determining a preprocessing model according to the network parameters of the convolutional neural network. The preset state may be set according to a specific type of the convolutional neural network, for example, the loss function is set to reach a convergence state, or a value of the loss function is smaller than a certain convergence threshold, and the like.
The specific shooting environment may be determined according to a requirement of the preprocessing, and generally includes a plurality of environments with different environmental factors such as brightness and/or light, for example, an environment of a pickup area close to the intelligent supply terminal under different brightness conditions, and in one example, shooting devices with different specifications may be used to shoot a user for testing under the specific environment, so as to obtain a plurality of input sample images with different quality, where most of the images are low-quality images. After a plurality of test users shoot in a plurality of specific shooting environments with incompletely consistent environmental parameters to obtain required input sample images, a high-definition shooting device is adopted for each test user to shoot face images of the test users in a professional shooting environment with sufficient light and low background noise to obtain output sample images corresponding to each input sample image, and each output sample image is a high-definition face image with certain quality requirements (preset quality conditions) such as resolution, pixel depth, an image color model and/or an image file storage format. Therefore, the convolution neural network is trained by taking each input sample image as input and the output sample image corresponding to each input sample image as output, and a preprocessing model capable of effectively carrying out filtering processing such as denoising and/or repairing on the face image can be obtained.
Specifically, the intelligent supply method based on face recognition further includes:
s530, obtaining a minimum value of the loss function, and if the minimum value is smaller than or equal to a convergence threshold value, judging that the loss function reaches a preset state; if the minimum value is greater than the convergence threshold, increasing the number of the input sample images and the number of the output sample images, and returning to execute step S520 until the minimum value of the loss function is less than or equal to the convergence threshold. The convergence threshold may be set (for example, set to a smaller value such as 0.1) according to the preprocessing precision of the preprocessing model, and the higher the preprocessing precision is, the smaller the value of the convergence threshold is.
In the training process of the convolutional neural network, if the minimum value of the loss function is smaller than or equal to the convergence threshold value, the determined network model can effectively preprocess the input image of the network model, at the moment, the loss function is judged to reach the preset state, the preprocessing model is determined, the needed preprocessing model can be obtained in time, and the corresponding training efficiency is improved. The minimum value is greater than the convergence threshold, which indicates that the preprocessing performed by the current network model has not yet met the relevant requirements, where the number of the input sample images and the number of the corresponding output sample images need to be increased (for example, the number of the input sample images and the number of the corresponding output sample images are increased to two times of the original number), and then the process returns to step S520 to retrain the convolutional neural network until the minimum value of the loss function is less than or equal to the convergence threshold, that is, the determined network model can effectively preprocess the input image thereof, and then the preprocessing model is determined according to the current network parameters of the convolutional neural network, which can ensure the quality of the determined preprocessing model, thereby improving the quality of the subsequent preprocessing of the corresponding goods-taking face images.
In one embodiment, the intelligent supply terminal further includes a pickup window, and the controlling the shipment module to perform the shipment operation includes:
s310, outputting a selection range of supplied goods, and reading a target goods selected by the goods taking user in the selection range;
and S320, controlling the goods outlet module to push the target object to a goods taking window.
In this embodiment, office supplies can be deposited to intelligence supply terminal, multiple article such as articles for daily use and/or daily food, the selection range of the article that supplies can be exported through mode such as setting up selection button or selection interface to intelligence supply terminal this moment, get the target object article that the goods user can select self needs to take in this selection range, make intelligence supply terminal control shipment module with this target object propelling movement to getting the goods window, let get the goods user and get required article, in order to guarantee the accuracy of supplying goods.
Specifically, the registered image library records balance data of each registered face image; the controlling the shipment module to push the target item to a pickup window comprises:
and obtaining the selling price data of the target object, if the selling price data is less than or equal to the balance data, controlling the shipment module to push the target object to a pickup window, and updating the balance data into the difference between the balance data and the selling price data.
The registered image library can record the balance data of each registered face image, so that the intelligent goods supply terminal provided by the embodiment can have a vending function. Specifically, in one example, when the user registers for the intelligent supply terminal, the user may pay, so that when the intelligent supply terminal constructs a registered image library including registered face images of each supply object, the payment fee corresponding to each registered face image is recorded, and balance data corresponding to each registered face image is determined. In other examples, the relevant management user may also allocate an initial balance to each offering object when acquiring the face image of the offering object, so that the constructed registered image library records each registered face image and balance data corresponding to each registered face image. Correspondingly, the intelligent supply terminal can also prestore the selling price data of each supplied article so as to obtain the selling price data of the target article in time after reading the target article selected by the goods-taking user and sell the target article.
As an embodiment, the intelligent supply method based on face recognition further includes:
s700, if the similarity of each first image is smaller than the second similarity threshold, acquiring a credit evaluation parameter corresponding to the goods-taking facial image from an external credit evaluation platform, acquiring a contact account (such as a mobile phone number and/or a mailbox address) of the goods-taking user through a dialog window of an acquisition contact account when the credit evaluation parameter is larger than or equal to the credit threshold, controlling the goods-taking module to execute goods-taking operation, acquiring goods-out information, pushing the contact account, the goods-taking information and the goods-taking facial image to a management terminal, and enabling the management terminal to provide a payment path and/or a registration path for the goods-taking user through the contact account; wherein the shipment information may include the time of the shipment, the identity information of the goods and the corresponding intelligent supply terminal, and so on.
The external credit evaluation platform can be a credit recording platform which is in contact with more users in daily life, such as a credit recording platform of a bank with the user number ranked at the front in a corresponding area, a credit recording platform adopted by precious sesame credit or WeChat payment, and the like. The credit threshold may be set according to a credit record characteristic of the credit evaluation platform, and is generally set as a parameter threshold capable of characterizing that a corresponding user has no bad records such as arrears and/or defaults.
In this embodiment, the intelligent supply terminal may include a communication module, so as to communicate with an external platform (such as a credit evaluation platform) and an external device (such as a management terminal) through the communication module. Each first image similarity is smaller than the second similarity threshold, which indicates that the current goods-taking user is almost impossible to be a goods-supplying object of the intelligent goods-supplying terminal, but is possible to be a potential goods-supplying object, such as a staff newly working in a certain company, a frequently-coming client, a trial user of a certain public goods or a customer who is not registered in time when the intelligent goods-supplying terminal serves as a goods-selling function, and the like. The identity information of the goods-taking face image can be further identified at the moment, the credit evaluation parameter corresponding to the identity information is obtained from an external credit evaluation platform, if the credit evaluation parameter is larger than or equal to a credit threshold value, it is indicated that the current goods-taking user has no problem of poor credit, a dialogue window for collecting a contact account number can be displayed at the moment, so that the goods-taking user inputs the contact account number through the dialogue window, after the contact account number of the goods-taking user is obtained at the intelligent goods-supplying terminal, the goods-outputting module can be controlled to execute goods-outputting operation, goods-supplying is carried out, and user experience brought by goods-supplying is further improved. After timely supply, the intelligent supply terminal can acquire shipment information, and pushes the shipment information of the pickup user, the pickup face image and the shipment information to the management terminal, so that the management terminal can timely receive the special supply behavior of the intelligent supply terminal, and subsequent processing can be conveniently performed.
The management terminal is an intelligent terminal for managing an intelligent supply terminal, such as a management terminal of an intelligent supply terminal used by administrative staff of a certain company. The management terminal receives the contact account number, the shipment information and the goods-taking face image of the goods-taking user, and the management user (such as administrative staff of a certain company) can know the information through display or short message push and the like. The management user judges the pickup user, the pickup authority of the pickup user can be directly and newly set (such as registration and corresponding balance data setting) according to the judgment result, and the pickup face image is used as a registration face image to be added to a registration image library; and a payment channel and a registration channel can be provided, so that the user can pay in time, registration and fee storage can be performed if a goods taking requirement exists subsequently, the intelligent goods supply terminal can obtain registration information and paid fee of the intelligent goods supply terminal, and registered face images and balance data corresponding to the goods taking user are recorded in a registered image library. Therefore, the registered image library of the intelligent goods supply terminal comprises the registered face image corresponding to the goods taking user, and the next goods taking requirement of the goods taking user can be responded by the intelligent goods taking terminal in time.
Specifically, the intelligent supply method based on face recognition further includes:
s800, if the registration information of the goods-taking face image fed back by the management terminal is detected within a set time period, adding the goods-taking face image as a registration face image to the registration image library; if the registration information or payment information of the goods-taking face image fed back by the management terminal is not detected within a set time period, adding the goods-taking face image to a limited image library; the limited image library is used for recording face images without goods taking authority; the set time period can be set according to the management characteristics of the management user or the related characteristics of the supply group (all supply objects), such as 5 days or 7 days.
In this embodiment, after receiving the special supply behavior of the intelligent supply terminal, the management terminal may enable a management user (e.g., an administrative staff of a certain company) to know the special supply behavior through display or short message push, so that the management user performs fee collection or new registration on the corresponding goods-taking user, and feeds back a result of the fee collection and/or the new registration to the intelligent supply terminal through information push or manual input. If the management user judges that the goods-taking user is not a potential goods-supplying object and does not smoothly collect corresponding fees, other operations can be omitted, so that the goods-supplying terminal does not receive the related feedback of the management terminal, and if the intelligent goods-supplying terminal does not detect the registration information or payment information of the goods-taking face image fed back by the management terminal within a set time period, the goods-taking face image shot at the time can be added to the limited image library to be used as a basis for checking the subsequent goods-supplying object.
Further, when each first image similarity is smaller than the second similarity threshold, the method further includes:
s900, identifying the similarity between each limit face image in the limit image library and a third image of the goods-taking face image, and outputting a prompt message of goods-delivery completion if the similarity of the third image is greater than or equal to a third similarity threshold value; wherein the prompt message can be output in the form of display and/or audio playing.
The third image similarity may be set to a value close to 1, such as 95%. The similarity of a certain third image is greater than or equal to a third similarity threshold value, the characteristic goods taking user is not a potential goods supplying object of the intelligent goods supplying terminal, and at the moment, the prompt information of goods delivery completion can be given to avoid invalid goods supplying, so that the goods supplying effectiveness can be improved, the user can be informed in time, the user can carry out other arrangements, and the waste of time and energy of the user is avoided.
Specifically, the intelligent supply method based on face recognition further includes: and acquiring the temperature of the face area of the goods taking user. In S300, when the first image similarity greater than or equal to the first similarity threshold is detected and the temperature is lower than the preset value, the shipment module is controlled to execute the shipment operation. And if the temperature exceeds the preset value, controlling the delivery module not to respond to the instruction for executing the delivery operation, namely not delivering the product. Therefore, the possibility of other users being infected is reduced by limiting the goods taking of the goods taking users with health problems. Alternatively, the preset value may be 37 ℃.
Or, intelligence supply of material terminal is including the electron bin that is used for storing protective gloves, the electron bin is equipped with the trompil, if the temperature exceeds the default, control the electron bin stretches out protective gloves the trompil, detect the protective gloves that stretch out and taken out the back, control shipment module carries out shipment operation, herein, if get goods user's temperature and exceed the default, stretch out the trompil with protective gloves through control electron bin, can remind the user of getting goods to wear protective gloves and get goods, furtherly, detect protective gloves and be taken out the back, just shipment, can let the user of getting goods who has the health problem get goods, can reduce the probability that other users are infected again.
Or, the intelligent supply terminal further comprises a disinfection article electronic bearing table, and in the step S300, if the temperature exceeds a preset value, the delivery module can be controlled to execute delivery operation; however, when the step S100 is returned to detect the next pickup user, before the next pickup user controls the pickup module to perform the pickup operation, the prompt message for prompting the sterilization is sent first, and the electronic carrying platform is put back within a preset time (for example, 3 minutes) after the sterilized product of the electronic carrying platform is detected to be taken out, and this detection result indicates that the next pickup user has taken the sterilized product according to the prompt message, sterilizes pickup positions such as the pickup window, and puts the sterilized product back to the original position after the sterilization is completed, and at this time, the pickup module can be controlled to perform the pickup operation. During the concrete realization, the electron plummer includes pressure sensor, and accessible pressure change information detects whether the articles for use of disinfecting are taken out and put back. If the current goods taking user has a health problem, the next goods taking user is prompted to perform disinfection operation, so that the probability of infection can be effectively reduced.
The intelligent goods supply method based on face recognition can preset a registered image library comprising face images of target goods supply objects for storage, when a user needs to pick goods, the user only needs to stand in a goods picking area to enable a shooting module to shoot the goods picking face images, and the goods picking face images are uploaded to a processor of an intelligent goods supply terminal.
It should be understood that, although the steps in the flowchart of fig. 1 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 1 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
In a second aspect, the present application provides an intelligent goods supply system based on face recognition, as shown in fig. 2, the intelligent goods supply system based on face recognition includes:
the acquisition unit 100 is used for acquiring a face image shot by a shooting module on a goods taking user in a goods taking area at present to obtain a goods taking face image;
the identification unit 200 is configured to identify a first image similarity between each registered face image in a pre-stored registered image library and the pickup face image; the registered image library records face images of all goods supplying objects;
the control unit 300 is configured to control the shipment module to perform a shipment operation when the first image similarity greater than or equal to the first similarity threshold is detected.
For specific limitations of the intelligent delivery system based on face recognition, reference may be made to the above limitations of the intelligent delivery method based on face recognition, and details are not repeated here. All or part of the modules in the intelligent goods supply system based on the face recognition can be realized through software, hardware and a combination thereof. 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.
The division of each unit in the intelligent supply system based on face recognition is only used for illustration, and in other embodiments, the intelligent supply system based on face recognition may be divided into different units as needed to complete all or part of the functions of the intelligent supply system based on face recognition.
In a third aspect, the present application provides an intelligent goods supply terminal based on face recognition, and as shown in fig. 3, the intelligent goods supply terminal may include a shooting module, a shipment module, a processor, and a storage medium; the storage medium having program code stored thereon; the shooting module and the delivery module are respectively connected with the processor; the shooting module is used for shooting a face image of a goods-taking user in a goods-taking area to obtain a goods-taking face image and uploading the goods-taking face image to the processor; the processor is used for calling the program codes stored in the storage medium to execute the intelligent goods supply method based on face recognition provided by any one of the above embodiments.
The intelligent goods supply terminal can be arranged in a corresponding area according to the goods taking characteristics of a target user who needs to supply goods, such as the goods receiving purpose of a set office area, the front desk of a certain office building or the free goods sending place of a certain public service organization. The goods taking area of the intelligent goods supplying terminal is usually arranged right in front of the intelligent goods supplying terminal, and the shooting module can be arranged at the position, close to the upper side, of the front side of the intelligent goods supplying terminal, so that the face of a goods taking user can be shot smoothly when the goods taking user is located in the goods taking area.
Specifically, the intelligent supply terminal may further include a communication module, so as to communicate with an external platform (such as a credit evaluation platform) and an external device (such as a management terminal) through the communication module.
Furthermore, the intelligent supply terminal can also comprise a display module for displaying the prompt information such as the end of shipment and the like, and can also be used for displaying the selection range of the articles supplied by the display and the like.
The intelligent goods supply terminal can collect the registered face images in a mode of shooting the face images of a user when the user provides or registers the intelligent goods supply terminal, the registered face images are stored in a preset registered image library, when the intelligent goods supply terminal supplies goods, the shooting module can be controlled to shoot the faces of goods taking users located in a goods taking area, so that goods taking face images are obtained, the similarity between each registered face image in the registered image library and the first image of the goods taking face image is identified, when the similarity of the first image is detected to be larger than or equal to a first similarity threshold value, the goods output module is controlled to execute goods output operation, and goods supply is carried out in time, wherein the goods taking process is effectively simplified, the goods supply efficiency is improved, the labor cost is saved, and the goods taking experience of the user is improved.
The intelligent supply terminal can also comprise a display module, when game software is operated, the display module is used for displaying a game interface, at the moment, screenshot can be carried out on the displayed game interface at regular intervals, required game display pictures can be continuously obtained, the intelligent supply method based on face recognition is respectively executed aiming at each game display picture, each game display picture is subjected to saturation enhancement processing, and a corresponding fusion image is obtained. In the fused images, target elements required to be extracted are enhanced, background elements including noise are weakened, and therefore the intelligent supply terminal can accurately extract the target elements.
Although the application has been shown and described with respect to one or more implementations, equivalent alterations and modifications will occur to others skilled in the art based upon a reading and understanding of this specification and the annexed drawings. This application is intended to embrace all such modifications and variations and is limited only by the scope of the appended claims. In particular regard to the various functions performed by the above described components, the terms used to describe such components are intended to correspond, unless otherwise indicated, to any component which performs the specified function of the described component (e.g., that is functionally equivalent), even though not structurally equivalent to the disclosed structure which performs the function in the herein illustrated exemplary implementations of the specification.
That is, the above description is only an embodiment of the present application, and not intended to limit the scope of the present application, and all equivalent structures or equivalent flow transformations made by using the contents of the specification and the drawings of the present application, such as the combination of technical features between various embodiments, or the direct or indirect application to other related technical fields, are all included in the scope of the present application.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or to implicitly indicate the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
The previous description is provided to enable any person skilled in the art to make or use the present application. In the foregoing description, various details have been set forth for the purpose of explanation. It will be apparent to one of ordinary skill in the art that the present application may be practiced without these specific details. In other instances, well-known processes have not been set forth in detail in order not to obscure the description of the present application with unnecessary detail. Thus, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.
Claims (9)
1. An intelligent supply method based on face recognition is characterized in that the intelligent supply method is applied to an intelligent supply terminal, the intelligent supply terminal comprises a shipment module, and the method comprises the following steps:
s100, acquiring a face image shot by a shooting module at the current goods taking area for a goods taking user to obtain a goods taking face image, wherein the steps of: after the processor receives the height information and the station information detected by the infrared detector, the optimal shooting position of the shooting lens is calculated by combining the moving range of the shooting lens, and the optimal shooting position is sent to the shooting module, so that the shooting module controls the shooting lens to move to the optimal shooting position to shoot the face of the goods-taking user; acquiring the temperature of the face area of a goods-taking user;
s200, identifying the first image similarity of each registered face image in a prestored registered image library and the goods-taking face image respectively; the registered image library records face images of all goods supplying objects;
s300, when the first image similarity which is larger than or equal to the first similarity threshold is detected and the temperature is lower than a preset value, controlling the delivery module to execute delivery operation; if the temperature exceeds a preset value, controlling the delivery module not to respond to an instruction for executing delivery operation;
s400, if the similarity of each first image is smaller than the first similarity threshold, when the similarity of the first images is larger than or equal to the second similarity threshold, determining the registered face image corresponding to the similarity of the first images larger than or equal to the second similarity threshold as an image to be compared;
s500, inputting the goods-taking face image into a preprocessing model for filtering to obtain a preprocessing image; the preprocessing model is used for filtering noise information of the face image;
s600, identifying second image similarity between the preprocessed image and the image to be compared, and controlling the delivery module to execute delivery operation if the second image similarity is greater than or equal to a first similarity threshold value.
2. The intelligent supply method based on face recognition as claimed in claim 1, wherein the training process of the preprocessing model comprises:
s510, acquiring face images shot for a plurality of test users in a specific shooting environment to obtain input sample images, and acquiring high-definition face images corresponding to the input sample images to obtain output sample images; the high-definition face image is a face image with quality parameters meeting preset quality conditions;
s520, training a convolutional neural network by taking the input sample image as input and the output sample image as output, and acquiring a loss function of the convolutional neural network in the training process;
and S540, when the loss function reaches a preset state, determining a preprocessing model according to the network parameters of the convolutional neural network.
3. The intelligent delivery method based on face recognition as claimed in claim 2, further comprising:
s530, obtaining the minimum value of the loss function, and if the minimum value is smaller than or equal to a convergence threshold value, judging that the loss function reaches a preset state; if the minimum value is greater than the convergence threshold, increasing the number of the input sample images and the number of the output sample images, and returning to execute step S520 until the minimum value of the loss function is less than or equal to the convergence threshold.
4. The intelligent supply method based on face recognition as claimed in claim 1, wherein the intelligent supply terminal further comprises a goods-taking window, and the controlling of the shipment module to perform shipment operation comprises:
s310, outputting a selection range of supplied goods, and reading a target goods selected by the goods taking user in the selection range;
s320, controlling the goods outlet module to push the target object to the goods taking window.
5. The intelligent supply method based on face recognition according to claim 4, wherein the registered image library records balance data of each registered face image; the controlling the shipment module to push the target item to a pickup window comprises:
and obtaining the selling price data of the target article, if the selling price data is less than or equal to the balance data, controlling the shipment module to push the target article to the goods taking window, and updating the balance data into the difference between the balance data and the selling price data.
6. The intelligent delivery method based on face recognition as claimed in claim 5, further comprising:
s700, if the similarity of each first image is smaller than the second similarity threshold, acquiring a credit evaluation parameter corresponding to the goods-taking face image from an external credit evaluation platform, acquiring a contact account number of the goods-taking user through a dialogue window for acquiring the contact account number when the credit evaluation parameter is larger than or equal to the credit threshold, controlling the goods-taking module to execute goods-taking operation, acquiring goods-taking information, pushing the contact account number, the goods-taking information and the goods-taking face image to a management terminal, and enabling the management terminal to provide a payment path and/or a registration path for the goods-taking user through the contact account number.
7. The intelligent supply method based on face recognition as claimed in claim 6, further comprising:
s800, if the registration information of the goods-taking face image fed back by the management terminal is detected within a set time period, adding the goods-taking face image as a registration face image to the registration image library; if the registration information or payment information of the goods-taking face image fed back by the management terminal is not detected within a set time period, adding the goods-taking face image to a limited image library; the limited image library is used for recording face images without goods taking authority.
8. The intelligent delivery method based on face recognition of claim 7, wherein when each first image similarity is less than the second similarity threshold, the method further comprises:
and S900, identifying the similarity between each limit face image in the limit image library and a third image of the goods-taking face image, and outputting a prompt message of the end of shipment if the similarity of the third image is greater than or equal to a third similarity threshold.
9. An intelligent goods supply terminal based on face recognition is characterized by comprising a shooting module, a goods delivery module, a processor and a storage medium; the storage medium has program code stored thereon;
the shooting module is used for shooting a face image of a goods taking user in a goods taking area to obtain a goods taking face image and uploading the goods taking face image to the processor;
the processor is used for calling the program codes stored in the storage medium to execute the intelligent goods supply method based on the face recognition according to any one of claims 1 to 8;
the shipment module is used for executing shipment operation under the control of the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110422007.2A CN113516814B (en) | 2021-04-19 | 2021-04-19 | Intelligent supply method and terminal based on face recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110422007.2A CN113516814B (en) | 2021-04-19 | 2021-04-19 | Intelligent supply method and terminal based on face recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113516814A CN113516814A (en) | 2021-10-19 |
| CN113516814B true CN113516814B (en) | 2023-04-18 |
Family
ID=78062418
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110422007.2A Active CN113516814B (en) | 2021-04-19 | 2021-04-19 | Intelligent supply method and terminal based on face recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113516814B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108376434A (en) * | 2018-02-22 | 2018-08-07 | 陈崇 | A kind of intelligent home control system based on Internet of Things |
| CN109241720A (en) * | 2018-09-05 | 2019-01-18 | 广州小楠科技有限公司 | A kind of tripper based on recognition of face |
| CN110765866A (en) * | 2019-09-18 | 2020-02-07 | 新疆爱华盈通信息技术有限公司 | Face recognition method and face recognition equipment |
| CN111724522A (en) * | 2020-05-25 | 2020-09-29 | 浙江大华技术股份有限公司 | Access control system, method and device, control equipment and storage medium |
| CN111814735A (en) * | 2020-07-24 | 2020-10-23 | 深圳市爱深盈通信息技术有限公司 | Ticket taking method, device and equipment based on face recognition and storage medium |
| CN211979685U (en) * | 2020-05-15 | 2020-11-20 | 广州致远电子有限公司 | Face detection equipment and access control system |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100468467C (en) * | 2006-12-01 | 2009-03-11 | 浙江工业大学 | Access control device and check on work attendance tool based on human face identification technique |
| TW201232425A (en) * | 2011-01-24 | 2012-08-01 | Taiwan Colour And Imaging Technology Corp | Face recognition intelligent self-service system |
| CN103559758B (en) * | 2013-11-06 | 2015-12-30 | 上海煦荣信息技术有限公司 | A kind of intelligentized vending system and good selling method |
| CN107633600A (en) * | 2017-08-11 | 2018-01-26 | 深兰科技（上海）有限公司 | A kind of unattended intelligent purchase method and self-help shopping cabinet |
| CN107749115A (en) * | 2017-10-30 | 2018-03-02 | 中米（北京）农业科技股份有限公司 | One kind opens automatic selling equipment door method and vending equipment based on credit |
| CN108648377A (en) * | 2018-04-10 | 2018-10-12 | 合肥美的智能科技有限公司 | Automatically vending system based on unmanned retail units and method |
| CN109801438A (en) * | 2019-01-18 | 2019-05-24 | 创新奇智(南京)科技有限公司 | A kind of intelligent sales counter based on recognition of face and interactive voice |
| CN110211302B (en) * | 2019-04-18 | 2022-08-30 | 湖南悟空教育科技有限公司 | Control method and device of self-service locker |
| CN112052780A (en) * | 2020-09-01 | 2020-12-08 | 北京嘀嘀无限科技发展有限公司 | Face verification method, device and system and storage medium |
| CN112329679B (en) * | 2020-11-12 | 2023-10-10 | 济南博观智能科技有限公司 | Face recognition method, face recognition system, electronic equipment and storage medium |
-
2021
- 2021-04-19 CN CN202110422007.2A patent/CN113516814B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108376434A (en) * | 2018-02-22 | 2018-08-07 | 陈崇 | A kind of intelligent home control system based on Internet of Things |
| CN109241720A (en) * | 2018-09-05 | 2019-01-18 | 广州小楠科技有限公司 | A kind of tripper based on recognition of face |
| CN110765866A (en) * | 2019-09-18 | 2020-02-07 | 新疆爱华盈通信息技术有限公司 | Face recognition method and face recognition equipment |
| CN211979685U (en) * | 2020-05-15 | 2020-11-20 | 广州致远电子有限公司 | Face detection equipment and access control system |
| CN111724522A (en) * | 2020-05-25 | 2020-09-29 | 浙江大华技术股份有限公司 | Access control system, method and device, control equipment and storage medium |
| CN111814735A (en) * | 2020-07-24 | 2020-10-23 | 深圳市爱深盈通信息技术有限公司 | Ticket taking method, device and equipment based on face recognition and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113516814A (en) | 2021-10-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11501614B2 (en) | Skip-scanning identification method, apparatus, and self-service checkout terminal and system | |
| CN108320404B (en) | Commodity identification method and device based on neural network and self-service cash register | |
| US20200258070A1 (en) | Purchased product checkout support system | |
| CN109726759B (en) | Unmanned vending method, device, system, electronic equipment and computer readable medium | |
| CN207624039U (en) | A kind of vending system | |
| CN109190705A (en) | Self-service method, apparatus and system | |
| CN107862515A (en) | A kind of good selling method and system | |
| JP5768010B2 (en) | Signage system and program | |
| CN109801438A (en) | A kind of intelligent sales counter based on recognition of face and interactive voice | |
| CN108805495A (en) | Article storage management method and system and computer-readable medium | |
| US11488126B2 (en) | Cashier fraud detecting system and method and product image selection generation for artificial neural network learning related applications | |
| WO2023198182A1 (en) | Method and system for confirming number of products in shopping cart, and storage medium | |
| US20190370885A1 (en) | Data processing method, device and storage medium | |
| CN111428621A (en) | Shelf interaction method and device and shelf | |
| CN113128898A (en) | Vending machine management method and device, electronic equipment and storage medium | |
| CN117151595A (en) | Commodity inventory management method, equipment and storage medium | |
| US20200279238A1 (en) | Automated Store Checkout | |
| CN113887884A (en) | Business-super service system | |
| CN113066225A (en) | Shopping method based on shared refrigerator and shared refrigerator | |
| CN113516814B (en) | Intelligent supply method and terminal based on face recognition | |
| CN111523348A (en) | Information generation method and device and equipment for man-machine interaction | |
| WO2022034298A1 (en) | Recycling mobile devices | |
| CN112884332A (en) | Intelligent terminal management system based on integrated circuit perception technology | |
| CN114596682B (en) | Method and system for managing cash register for unmanned market | |
| CN113129501B (en) | Anti-theft early warning method for unmanned retail terminal |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240508 Address after: Building 9, Building 203B, Phase II, Nanshan Yungu Entrepreneurship Park, No. 2 Pingshan 1st Road, Pingshan Community, Taoyuan Street, Nanshan District, Shenzhen, Guangdong Province, 518033 Patentee after: Core Computing Integrated (Shenzhen) Technology Co.,Ltd. Country or region after: China Address before: Room 1010, 10 / F, building a, Chuangzhi building, Xinjiang Software Park, 455 Kanas Hubei Road, Urumqi Economic and Technological Development Zone, 830000 Xinjiang Uygur Autonomous Region Patentee before: XINJIANG AIHUA YINGTONG INFORMATION TECHNOLOGY Co.,Ltd. Country or region before: China |