CN110175589A - A kind of household retail business information sharing platform based on face alignment video camera - Google Patents
A kind of household retail business information sharing platform based on face alignment video camera Download PDFInfo
- Publication number
- CN110175589A CN110175589A CN201910469476.2A CN201910469476A CN110175589A CN 110175589 A CN110175589 A CN 110175589A CN 201910469476 A CN201910469476 A CN 201910469476A CN 110175589 A CN110175589 A CN 110175589A
- Authority
- CN
- China
- Prior art keywords
- face
- photo
- client
- video camera
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0281—Customer communication at a business location, e.g. providing product or service information, consulting
-
- 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
Abstract
The invention belongs to AI artificial intelligence identification technology fields, and in particular to a kind of household retail business information sharing platform based on face alignment video camera, including face alignment video camera, cloud server and salesman end;The face comparison video camera for candid photograph and primary filter human face photo and transmits result to cloud server;The human face photo that the cloud server is used to receive face comparison camera transmissions obtains client into shop information, and client is pushed to salesman end into shop information, and the client includes the FACE ID archives into shop position and client of client into shop information;The salesman end is for receiving client into shop information and judging, if the FACE ID archives of client are new staff, then the reverse transfer FACE ID file transmission to face compares video camera and is added to blacklist library, if the FACE ID archives of client are not new staff, the FACE ID file transmission to face is simultaneously compared video camera and is added to white list library by salesman's normal service client.
Description
Technical field
The invention belongs to AI artificial intelligence identification technology fields, and in particular to a kind of household based on face alignment video camera
Retail business information sharing platform.
Background technique
Household retail trade, after a client is into shop, the salesman in each shop requires to restart to understand customer demand,
Cause the problems such as Customer Reception is difficult;It is by shopkeeper, salesman's craft statistical report side entirely about passenger flow data for agent
Formula, data inaccuracy, and also the subjective factor of people is too strong.What is more, and part shopkeeper has in other purposes such as examinations and repairs
The phenomenon that changing data exists.
Summary of the invention
Customer demand cannot be understood in time for household retail trade salesman existing in the prior art and cause to repeat
The problem of labour and Customer Reception difficulty, the household retail business information based on face alignment video camera that the present invention provides a kind of are total
Platform is enjoyed, adopts the following technical scheme that realization:
One kind being based on face alignment video camera, including camera and communication module, further includes image processing module, front end ratio
To module and DDR memory module;
The camera is used to capture the face for entering shooting area;
Described image processing module is for pre-processing the human face photo that camera is captured;
The front end comparison module is for analyzing the human face photo that image processing module pre-processes;
The DDR memory module is for storing blacklist human face data, caching to the face of candid photograph;
The human face photo that the communication module is used to filter out front end comparison module is transmitted to cloud server.
Further, the camera captures the face for entering shooting area according to the speed of 10/second, obtains
One group of photographic intelligence of same face.
Further, the pretreatment of described image processing module are as follows:
Carry out characteristic point label by the human face photo captured to camera, including to face eyes, nose, mouth,
The characteristic point of eyebrow and profile carries out label, wherein each eye label number is 6-10, nose label number is 8-12, mouth
Bar label number is 15-20, every eyebrow label number is 4-10, profile label number is 15-20.
Further, the front end comparison module includes positive face angle judgment module, black and white lists library comparison module and prolongs
When filtering module;
The positive face angle judgment module is used in same group of photo according to outside the left and right eye profile of face and face
Whether the left side of symmetry principle confirmation face of shape outline proportion, the angle on right side meet positive face, pass through lower lip on face
The profile distance proportion of profile, eyebrow and eyes, come judge the state of face in picture be come back, whether the angle bowed meets
Positive face filters out the positive face photo in same group of photo;
The positive face photo and DDR that black and white lists library comparison module is used to select positive face angle judgment module store mould
Black and white lists library in block compares, corresponding with white list library if positive face photo or continue if not corresponding to black and white lists library
Transmission downwards stops to transmit if positive face photo is corresponding with blacklist library;
The delay filtering module includes buffer area, all positive face photos in the buffer area memory buffers time, delay
If filtering module is used to the face picture that black and white lists library has compared photo is compared with the positive face photo of buffer area and delay
It deposits area's photo and reaches similarity threshold, picture, which will be filtered, not to be transmitted to cloud, otherwise photo will be compared by network to cloud
Server transport.
Further, the positive face angle judgment module selection left eye is marked as 37-42, and right eye is marked as 43-46, nose
Be 49-58 marked as 28-36, mouth label number, left eyebrow marked as 18-22, right eyebrow marked as 23-27, profile marked as
1-17, the label carry out positive face angle according to following rule and judge:
When label meets (X37-X40)/(X43-X46) > 1.2 or (X37-X40)/(X43-X46) < 0.8 then judges the face figure
Piece is left and right directions side face, non-positive face picture, wherein X37、X40、X43And X46Indicate the characteristic point marked as 37,40,43 and 46
Abscissa;
When label meets (Y18-Y37)/(Y20-Y37) > 0.9 or (Y50-Y61)/(Y51-Y61) > 0.8, then judge in picture
Face is angle of bowing, wherein Y18、Y20、Y37、Y50、Y51And Y61Indicate the characteristic point marked as 18,20,37,50,51 and 61
Ordinate;
When label meets (Y18-Y37)/(Y20-Y37) > 0.9 or (Y61-Y60)/(Y61-Y58) > 0.8, then judge in picture
Face is new line angle, wherein Y60And Y58Indicate the ordinate of the characteristic point marked as 60 and 58.
Further, the similarity threshold of the delay filtering module is 80%.
Further, the communication module includes 4G/5G module or WIFI module.
A kind of household retail business information sharing platform based on face alignment video camera, including face alignment video camera, cloud
Hold server and salesman end;
The face comparison video camera for candid photograph and primary filter human face photo and transmits result to cloud server;
The human face photo that the cloud server is used to receive face comparison camera transmissions obtains client into shop information,
And client is pushed into salesman end into shop information, the client includes the FACE into shop position and client of client into shop information
ID archives, the client's obtains into shop position according to the number of the face comparison video camera of transmission human face photo;
The salesman end is for receiving client into shop information and judging, if existing customer human face photo is newly to work
Personnel, then mark FACE ID archives and the reverse transfer FACE ID archives to face compares video camera, is added to blacklist
Library, if existing customer human face photo is not new staff, salesman services existing customer and fills in FACE ID and by the FACE
ID file transmission to face compares video camera and is added to white list library.
Further, it the primary filter human face photo and transmits result to cloud server and refers to:
The human face photo captured is compared with black, white list library respectively after pretreatment, and will compare after with it is white
List library correspondence or human face photo not corresponding with black and white lists library are designated as client and continue transmission downwards, will be with blacklist library
Corresponding human face photo is designated as staff and stops transmission.
Further, the FACE ID archives include:
Customer name, customer phone, client's WeChat ID, building information, intention product, quotation discount, DESA personality, house type
Area, decoration style, decoration company, client age, client occupation, client interests, children's age, children's gender, kinsfolk,
Education level and consumptive power analysis.
The present invention also has the following beneficial effects:
(1) present invention built-in face recognition algorithms and DDR memory module in recognition of face video camera, can prestore black
White list can choose in only push list library human face photo in human face photo or filter list library according to actual needs, or
Person pushes the human face photo all captured.It additionally can control and do not repeat to push in same people's setting time.
(2) recognition of face video camera of the invention can carry out track of the whole process to the face for entering shooting area, select one
Optimal positive face human face photo push;If facial angle is greater than comprehensive 12 degree in optimal photo, photo angle is not achieved
Push standard, the equipment human face photo that automatic fitration is below standard.
(3) built-in 4G/5G communication module and WIFI communication module, video camera can in recognition of face video camera by the present invention
To use cable, flow card or WIFI and server to carry out network communication according to the actual situation, there is wider applied field
Scape.
(4) present invention can help the acquisition of salesman's real-time and precise into shop customer information, and realize the letter between more shops
Breath is shared;The present invention may also help in client's relevant statistics that agency obtains accurately shop.
Detailed description of the invention
Fig. 1 is work flow diagram of the invention;
Fig. 2 is the composition block diagram of video camera of the invention;
Fig. 3 is the human face characteristic point label figure of the embodiment of the present invention;
Fig. 4 is that black and white lists library updates flow chart;
Fig. 5 is that new client shoots comparison flow chart;
Fig. 6 is that frequent customer shoots comparison flow chart;
Fig. 7 is that staff compares flow chart.
Specific embodiment
The following provides a specific embodiment of the present invention, it should be noted that the invention is not limited to implement in detail below
Example, all equivalent transformations made on the basis of the technical solutions of the present application each fall within protection scope of the present invention.
In the present invention, in the absence of explanation to the contrary, the noun of locality used such as " upper and lower " is typically referred to corresponding
It is defined on the basis of the drawing of attached drawing, " inside and outside " refers to the inner and outer of corresponding component profile.
One kind being based on face alignment video camera, including camera, image processing module, front end comparison module, DDR store mould
Block and communication module;
The camera is used to capture the face for entering shooting area;
Described image processing module is for pre-processing the human face photo that camera is captured;
The front end comparison module is for analyzing the human face photo that image processing module pre-processes;
The DDR memory module is for storing blacklist human face data, caching to the face of candid photograph;
The human face photo that the communication module is used to filter out front end comparison module is transmitted to cloud server.
Face alignment video camera very good solution of the invention face enters the lasting track up, preferably of shooting area
The function that photo push, interference signal screen out, greatly strengthens the AI artificial intelligence ability of equipment, realizes and reduces concurrency biography
Defeated, removal interference-nulls photo transmission and comparison, improve the computing capability and processing speed of Cloud Server;
Such as: from the point of view of the hardware transport data comparison of retail shop installation, traditional video camera has a large amount of weight
Note in reply piece and side face photo, average daily face picture 760 of transmitting is opened, and uses the same shops day transmission face of new technology of the present invention
Picture 46 is opened;Efficiency is greatly improved, the unnecessary wasting of resources is reduced.
Specifically, the camera captures the face for entering shooting area according to the speed of 10/second, obtain same
One group of photographic intelligence of one face, the shooting area are at the entrance and exit of the passage of camera high angle shot.
Preferably, the installation requirement of video camera are as follows: 10 ° ± 3 of camera looks down angle, 10 ° of X deflection angle α <, most
Big detection width is 2.5m, mounting height h=2.05-2.2 (m), mounting distance d=6-8 (m)
Specifically, the pretreatment of described image processing module is to carry out feature by the human face photo captured to camera
Point label carries out label including the characteristic point to face eyes, nose, mouth, eyebrow and profile, and each eye label number is 6-
10, nose label number be 8-12, mouth label number is 15-20, every eyebrow label number is 4-10, profile label number
It is 15-20.
Preferably, as shown in figure 3, two eyes labels are respectively No. 37-42, No. 43-48, nose marked as No. 28-36,
Mouth is marked as No. 49-68, and two eyebrow labels are respectively No. 18-22, No. 23-27, and profile is marked as No. 1-17.
Specifically, the front end comparison module includes positive face angle judgment module, black and white lists library comparison module and delay
Filtering module;
The positive face angle judgment module is used in same group of photo according to outside the left and right eye profile of face and face
Whether the left side of symmetry principle confirmation face of shape outline proportion, the angle on right side meet positive face, pass through lower lip on face
The profile distance proportion of profile, eyebrow and eyes, come judge the state of face in picture be come back, whether the angle bowed meets
Positive face filters out the positive face photo in same group of photo;
Preferably, the positive face angle judgment module selection left eye is marked as 37-42, and right eye is marked as 43-46, nose mark
Number be 28-36, mouth label number is 49-58, left eyebrow is marked as 18-22, right eyebrow marked as 23-27, profile is marked as 1-
17, the label carries out positive face angle according to following rule and judges:
When label meets (X37-X40)/(X43-X46) > 1.2 or (X37-X40)/(X43-X46) < 0.8 then judges the face figure
Piece is left and right directions side face, non-positive face picture, wherein X37、X40、X43And X46Indicate the characteristic point marked as 37,40,43 and 46
Abscissa;
When label meets (Y18-Y37)/(Y20-Y37) > 0.9 or (Y50-Y61)/(Y51-Y61) > 0.8, then judge in picture
Face is angle of bowing, wherein Y18、Y20、Y37、Y50、Y51And Y61Indicate the characteristic point marked as 18,20,37,50,51 and 61
Ordinate;
When label meets (Y18-Y37)/(Y20-Y37) > 0.9 or (Y61-Y60)/(Y61-Y58) > 0.8, then judge in picture
Face is new line angle, wherein Y60And Y58Indicate the ordinate of the characteristic point marked as 60 and 58.
Then it is clear a positive face preferably to be exported in one group of photo according to the condition of " preferential clarity, preferential positive face " screening
Clear photo;
The positive face photo and DDR that black and white lists library comparison module is used to select positive face angle judgment module store mould
Black and white lists library in block compares, and continues transmission downwards if positive face photo is corresponding with white list library, if just face photo and
Blacklist library correspondence then stops to transmit;
Preferably, the blacklist library is the face picture information of staff, and the white list library is the face of client
Pictorial information;
The delay filtering module includes buffer area, all positive face photos in the buffer area memory buffers time, delay
Filtering module is used to for the face picture that black and white lists library has compared being compared with the positive face photo of buffer area, including eyebrow length and width
Ratio, eyebrow spacing ratio, eyes Aspect Ratio, eyes spacing ratio, nose Aspect Ratio, mouth Aspect Ratio, outer face wheel
Wide and face position ratio comparison, if photo and buffer area photo similarity reach threshold value, picture will be filtered not to
Cloud transmission guarantees that same face does not repeat to push within the set time, otherwise photo will be compared to cloud by network and be serviced
Device transmission,
Preferably, the threshold value set is reaches 80% similarity.
Preferably, the cache-time of the delay filtering module is set as 6 minutes.
Specifically, the communication module includes 4G/5G module or WIFI module, can use according to the actual situation cable,
Flow card or WIFI and server carry out network communication, have wider application scenarios.
Specifically, the backing positions of the video camera are provided with improved universal joint, equipment and mounting bracket ensure that
Integral structure, and the comprehensive 360 rotation installation of equipment can be very easily carried out, convenient for the simple type and convenient of worker's installation
Property.
Specifically, the furthermore also built-in house dog of video camera, is used to periodically repeat video camera, prevents product from transporting online for a long time
In row, since external force or the identification operation of cause specific video camera fall into program endless loop and equipment are caused to can not work normally.
The workflow of video camera of the invention is as follows as shown in Figure 1:
(1) face enters shooting area, and video camera starts tracking and captures client;
(2) face leaves shooting area, and video camera screens optimal positive face photo, pushes away if human face photo reaches push standard
Face make a gift to someone to performing the next step, does not otherwise push;
(3) blacklist library searching human face photo, if not pushing face if blacklist library searching to matched face information,
Otherwise push face is in next step;
(4) face cache library searching human face photo, if retrieve meet matched face information if do not push face, otherwise
It pushes human face photo and caches library to server end and by current face's photo addition face.
A kind of household retail business information sharing platform based on face alignment video camera, including face alignment video camera, cloud
Hold server and salesman end;
The face comparison video camera for candid photograph and primary filter human face photo and transmits result to cloud server;
The human face photo that the cloud server is used to receive face comparison camera transmissions obtains client into shop information,
And client is pushed into salesman end into shop information, the client includes the FACE into shop position and client of client into shop information
ID archives;
The salesman end is for receiving client into shop information and judging, if the FACE ID archives of client are new works
Make personnel, then reverse transfer FACE ID file transmission to face compares video camera and is added to blacklist library, if client
FACE ID archives are not new staff, then salesman's normal service client and by the FACE ID file transmission to face comparison take the photograph
Camera is simultaneously added to white list library, it is ensured that timely adds black and white lists function, ensure that the interference signal of staff not
The resource for wasting data transmission again and comparing.
Specifically, affiliated salesman end carrier is salesman APP, H5 or small routine etc..
Specifically, the primary filter human face photo and transmitting result to cloud server and referring to:
The human face photo captured is compared with black, white list library respectively after pretreatment, and will compare after with it is white
List library correspondence or human face photo not corresponding with black and white lists library are designated as client and continue transmission downwards, will be with blacklist library
Corresponding human face photo is designated as staff and stops transmission;
Specifically, the client obtains in the following manner into shop information:
According to transmission human face photo face comparison video camera number judge client into shop position, will be with black and white lists
The not corresponding human face photo in library be labeled as new client, establish the FACE ID archives of new client, by after the comparison received with it is white
The corresponding client's face photograph tags in list library are frequent customer, the FACE ID archives of more old and new customers.
Specifically, this platform can also be applied to sale of automobile industry and real estate sale industry.
Specifically, cloud server daily can be in the form of statements by each StoreFront into shop customer information and salesman's mark
Information shows agent.
Preferably, the FACE ID archives of client include: customer name, customer phone, client's WeChat ID, building information, meaning
To product, quotation discount, DESA personality, house type area, decoration style, decoration company, client age, client occupation, Ke Huxing
Interest, children's age, children's gender, kinsfolk, education level and consumptive power analysis.
Claims (10)
1. one kind is based on face alignment video camera, including camera and communication module, which is characterized in that further include image procossing mould
Block, front end comparison module and DDR memory module;
The camera is used to capture the face for entering shooting area;
Described image processing module is for pre-processing the human face photo that camera is captured;
The front end comparison module is for analyzing the human face photo that image processing module pre-processes;
The DDR memory module is for storing blacklist human face data, caching to the face of candid photograph;
The human face photo that the communication module is used to filter out front end comparison module is transmitted to cloud server.
2. face alignment video camera as described in claim 1, which is characterized in that the camera according to 10/second speed
The face for entering shooting area is captured, one group of photographic intelligence of same face is obtained.
3. face alignment video camera as described in claim 1, which is characterized in that the pretreatment of described image processing module are as follows:
Characteristic point label is carried out by the human face photo captured to camera, including to face eyes, nose, mouth, eyebrow
Label is carried out with the characteristic point of profile, wherein each eye label number is 6-10, nose label number is 8-12, mouth mark
Number is 15-20, every eyebrow label number is 4-10, profile label number is 15-20.
4. face alignment video camera as described in claim 1, which is characterized in that the front end comparison module includes positive face angle
Judgment module, black and white lists library comparison module and delay filtering module;
The positive face angle judgment module is used in same group of photo according to the left and right eye profile of face and face outlines wheel
Whether the symmetry principle confirmation left side of face of wide ratio, the angle on right side meet positive face, by the profile of lower lip on face,
The profile distance proportion of eyebrow and eyes, come judge the state of face in picture be come back, whether the angle bowed meets positive face,
Filter out the positive face photo in same group of photo;
In the positive face photo and DDR memory module that black and white lists library comparison module is used to select positive face angle judgment module
Black and white lists library compare, if positive face photo it is corresponding with white list library or with black and white lists library it is corresponding if continuation downwards
Transmission stops to transmit if positive face photo is corresponding with blacklist library;
The delay filtering module includes buffer area, all positive face photos in the buffer area memory buffers time, delay filtering
If module is used to the face picture that black and white lists library has compared photo and buffer area is compared with the positive face photo of buffer area
Photo reaches similarity threshold, and picture, which will be filtered, not to be transmitted to cloud, otherwise photo will be compared to cloud by network and be serviced
Device transmission.
5. face alignment video camera as claimed in claim 4, which is characterized in that the positive face angle judgment module selects left eye
Marked as 37-42, right eye is 49-58, left eyebrow marked as 18- marked as 28-36, mouth label number marked as 43-46, nose
22, right eyebrow is marked as 23-27, and marked as 1-17, the label carries out positive face angle according to following rule and judges profile:
When label meets (X37-X40)/(X43-X46) > 1.2 or (X37-X40)/(X43-X46) < 0.8 then judges the face picture for a left side
Right direction side face, non-positive face picture, wherein X37、X40、X43And X46Indicate the horizontal seat of the characteristic point marked as 37,40,43 and 46
Mark;
When label meets (Y18-Y37)/(Y20-Y37) > 0.9 or (Y50-Y61)/(Y51-Y61) > 0.8 then judges that the face in picture is
It bows angle, wherein Y18、Y20、Y37、Y50、Y51And Y61Indicate the vertical seat of the characteristic point marked as 18,20,37,50,51 and 61
Mark;
When label meets (Y18-Y37)/(Y20-Y37) > 0.9 or (Y61-Y60)/(Y61-Y58) > 0.8 then judges that the face in picture is
New line angle, wherein Y60And Y58Indicate the ordinate of the characteristic point marked as 60 and 58.
6. face alignment video camera as claimed in claim 4, which is characterized in that the similarity threshold of the delay filtering module
It is 80%.
7. face alignment video camera as described in claim 1, which is characterized in that the communication module include 4G/5G module or
WIFI module.
8. a kind of household retail business information sharing platform based on face alignment video camera, which is characterized in that wanted including such as right
Ask face alignment video camera, cloud server described in 1-7 any bar and salesman end;
The face comparison video camera for candid photograph and primary filter human face photo and transmits result to cloud server;
The human face photo that the cloud server is used to receive face comparison camera transmissions obtains client into shop information, and will
Client pushes to salesman end into shop information, the client into shop information include client into the FACEID of shop position and client shelves
Case, the client's obtains into shop position according to the number of the face comparison video camera of transmission human face photo;
The salesman end is for receiving client into shop information and judging, if existing customer human face photo is new work people
Member, then mark FACEID archives and the reverse transfer FACEID archives to face compares video camera, is added to blacklist library, if
Existing customer human face photo is not new staff, then salesman services existing customer and fills in FACEID and pass the FACEID archives
It transports to face comparison video camera and is added to white list library.
9. the household retail business information sharing platform based on face alignment video camera as claimed in claim 8, which is characterized in that
The primary filter human face photo simultaneously transmits result to cloud server and refers to:
The human face photo captured is compared with black, white list library respectively after pretreatment, and will compare after with white list
Library correspondence or human face photo not corresponding with black and white lists library are designated as client and continue transmission downwards, will be corresponding with blacklist library
Human face photo be designated as staff and stop transmission.
10. the household retail business information sharing platform based on face alignment video camera, feature exist as claimed in claim 8
In the FACEID archives include:
Customer name, customer phone, client's WeChat ID, building information, intention product, quotation discount, DESA personality, house type face
Product, decoration style, decoration company, client age, client occupation, client interests, children's age, children's gender, kinsfolk, by
Education degree and consumptive power analysis.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910469476.2A CN110175589A (en) | 2019-05-31 | 2019-05-31 | A kind of household retail business information sharing platform based on face alignment video camera |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910469476.2A CN110175589A (en) | 2019-05-31 | 2019-05-31 | A kind of household retail business information sharing platform based on face alignment video camera |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110175589A true CN110175589A (en) | 2019-08-27 |
Family
ID=67696213
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910469476.2A Pending CN110175589A (en) | 2019-05-31 | 2019-05-31 | A kind of household retail business information sharing platform based on face alignment video camera |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110175589A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111241932A (en) * | 2019-12-30 | 2020-06-05 | 广州量视信息科技有限公司 | Automobile exhibition room passenger flow detection and analysis system, method and storage medium |
CN111401232A (en) * | 2020-03-13 | 2020-07-10 | 厦门瑞为信息技术有限公司 | Customer type judgment method, system, equipment and medium |
CN111814551A (en) * | 2020-06-06 | 2020-10-23 | 中信百信银行股份有限公司 | Human face recognition method, device and equipment based on small program and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104504408A (en) * | 2015-01-12 | 2015-04-08 | 吴建忠 | Human face identification comparing method and system for realizing the method |
CN108965683A (en) * | 2018-09-27 | 2018-12-07 | 上海良相智能化工程有限公司 | Intelligent human-face identifies camera |
CN109214324A (en) * | 2018-08-27 | 2019-01-15 | 曜科智能科技(上海)有限公司 | Most face image output method and output system based on polyphaser array |
-
2019
- 2019-05-31 CN CN201910469476.2A patent/CN110175589A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104504408A (en) * | 2015-01-12 | 2015-04-08 | 吴建忠 | Human face identification comparing method and system for realizing the method |
CN109214324A (en) * | 2018-08-27 | 2019-01-15 | 曜科智能科技(上海)有限公司 | Most face image output method and output system based on polyphaser array |
CN108965683A (en) * | 2018-09-27 | 2018-12-07 | 上海良相智能化工程有限公司 | Intelligent human-face identifies camera |
Non-Patent Citations (1)
Title |
---|
陈惠红等: ""人脸识别技术分析与系统架构"", 《新型工业化》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111241932A (en) * | 2019-12-30 | 2020-06-05 | 广州量视信息科技有限公司 | Automobile exhibition room passenger flow detection and analysis system, method and storage medium |
CN111401232A (en) * | 2020-03-13 | 2020-07-10 | 厦门瑞为信息技术有限公司 | Customer type judgment method, system, equipment and medium |
CN111401232B (en) * | 2020-03-13 | 2023-04-07 | 厦门瑞为信息技术有限公司 | Customer type judgment method, system, equipment and medium |
CN111814551A (en) * | 2020-06-06 | 2020-10-23 | 中信百信银行股份有限公司 | Human face recognition method, device and equipment based on small program and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110175589A (en) | A kind of household retail business information sharing platform based on face alignment video camera | |
CN109614882A (en) | A kind of act of violence detection system and method based on human body attitude estimation | |
CN104303193B (en) | Target classification based on cluster | |
JP5569990B2 (en) | Attribute determination method, attribute determination apparatus, program, recording medium, and attribute determination system | |
CN109145844A (en) | Archive management method, device and electronic equipment for city safety monitoring | |
US20040151374A1 (en) | Video segmentation using statistical pixel modeling | |
CN109344271A (en) | Video portrait records handling method and its system | |
CN112347941B (en) | Motion video collection intelligent generation and distribution method based on 5G MEC | |
CN104091176A (en) | Technology for applying figure and head portrait comparison to videos | |
KR102097781B1 (en) | Apparatus and Method for Providing Object Information | |
CN209248550U (en) | Data analysis and supplying system based on recognition of face | |
US11948373B2 (en) | Automatic license plate recognition | |
US20240111835A1 (en) | Object detection systems and methods including an object detection model using a tailored training dataset | |
CN107977613A (en) | Improve the method and face identification system of recognition of face efficiency | |
CN110366000A (en) | A kind of video pictures transmission method and system | |
CN113657933A (en) | Preparation method of elevator advertisement recommendation data | |
WO2021082548A1 (en) | Living body testing method and apparatus, server and facial recognition device | |
CN110659615A (en) | Passenger group flow and structural analysis system and method based on face recognition | |
CN110197162A (en) | A kind of more communication modes full angle candid cameras based on face alignment | |
CN109859011A (en) | Based on the information push method in store, system and its storage medium in jewellery wire | |
CN202374374U (en) | Shopping mall crowd flow dynamic management system based on remote images | |
CN109726750A (en) | A kind of passenger falls down detection device and its detection method and passenger conveying appliance | |
US20230260325A1 (en) | Person category attribute-based remote care method and device, and readable storage medium | |
CN106327602A (en) | Cloud architecture based on biological recognition and application system thereof | |
TW201822082A (en) | Intelligent image recognition dynamic planning system and method capable of improving overall use efficiency of venue space, avoiding crowding, and improving shopping quality of the customers |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190827 |