CN109635663A - A kind of Distributive System of Face Recognition - Google Patents
A kind of Distributive System of Face Recognition Download PDFInfo
- Publication number
- CN109635663A CN109635663A CN201811354014.8A CN201811354014A CN109635663A CN 109635663 A CN109635663 A CN 109635663A CN 201811354014 A CN201811354014 A CN 201811354014A CN 109635663 A CN109635663 A CN 109635663A
- Authority
- CN
- China
- Prior art keywords
- module
- characteristic
- face
- data distribution
- face recognition
- 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
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of Distributive System of Face Recognition, including characteristic extracting module, message queue module, data distribution module, Characteristic Contrast module, result comparison module, feature database；Successively data connection, feature database are communicatively connected to Characteristic Contrast module for the characteristic extracting module, message queue module, data distribution module, Characteristic Contrast module, result comparison module.The present invention passes through the setting of the modules such as message queue module, data distribution module, Characteristic Contrast module, can be to reduce equipment cost, raising system stability, the whole energy consumption of reduction to provide solid strong basis in terms of the realization that embedded human face identifies.
Description
Technical field
The present invention relates to a kind of Distributive System of Face Recognition.
Background technique
The face recognition technology extracted in the prior art based on feature decomposition is already mature, but at present mostly with server or
Desktop computer is main calculating core, and the powerful performance realization of reliance server or desktop computer quickly calculates, however in actual demand
In, it needs the embedded device of terminated largely to carry out recognition of face, such as to complete calculating efficient enough at this time, then often
The processor of very high performance is needed, or directlys adopt FPGA, it is clear that not only equipment cost is high, but also is faced with unstable, energy consumption
A series of high troubles.
Summary of the invention
In order to solve the above technical problems, the present invention provides a kind of Distributive System of Face Recognition, fast face identification system
System can be identified by the setting of the modules such as message queue module, data distribution module, Characteristic Contrast module in embedded human face
It realizes aspect and provides solid strong basis to reduce equipment cost, raising system stability, reducing whole energy consumption.
The present invention is achieved by the following technical programs.
A kind of Distributive System of Face Recognition provided by the invention, including characteristic extracting module, message queue module, data point
Send out module, Characteristic Contrast module, result comparison module, feature database；The characteristic extracting module, message queue module, data point
Hair module, Characteristic Contrast module, successively data connection, feature database are communicatively connected to Characteristic Contrast module to result comparison module；
The characteristic extracting module receives facial image and extracts to face characteristic；
Face characteristic is a data unit hair with the face characteristic in each facial image by the message queue module
It send to data distribution module；
The face characteristic received is sent to multiple Characteristic Contrast modules with different order by the data distribution module；
The Characteristic Contrast module compares the people read from feature database according to the sequence of the face characteristic received item by item
Face feature, and comparing result is sent to result comparison module；
The result comparison module compares the comparing result that multiple Characteristic Contrast modules are sent.
The received facial image of characteristic extracting module is to face facial image.
The message queue module receives and dispatches face characteristic data in the way of first in first out.
The result comparison module judges multiple comparison knots when comparing the comparing result that multiple Characteristic Contrast modules are sent
Whether fruit is consistent, by comparing result output and to data distribution module feedback pass signal if consistent, to number if inconsistent
According to distribution module feeding back unsuccessful signal.
The data distribution module is re-transmitted to after changing the putting in order of face characteristic when receiving failure signal
Characteristic Contrast module.
The characteristic extracting module is STM32F7 series processors.
The data distribution module is STM32F3 series processors.
The result comparison module is STM32F3 series processors.
The beneficial effects of the present invention are: pass through the modules such as message queue module, data distribution module, Characteristic Contrast module
Setting can reduce equipment cost in terms of the realization that embedded human face identifies, improve system stability, reduce whole energy consumption
Solid strong basis is provided.
Detailed description of the invention
Fig. 1 is connection schematic diagram of the invention.
Specific embodiment
Be described further below technical solution of the present invention, but claimed range be not limited to it is described.
A kind of Distributive System of Face Recognition as shown in Figure 1, including characteristic extracting module, message queue module, data point
Send out module, Characteristic Contrast module, result comparison module, feature database；The characteristic extracting module, message queue module, data point
Hair module, Characteristic Contrast module, successively data connection, feature database are communicatively connected to Characteristic Contrast module to result comparison module；
The characteristic extracting module receives facial image and extracts to face characteristic；
Face characteristic is a data unit hair with the face characteristic in each facial image by the message queue module
It send to data distribution module；
The face characteristic received is sent to multiple Characteristic Contrast modules with different order by the data distribution module；
The Characteristic Contrast module compares the people read from feature database according to the sequence of the face characteristic received item by item
Face feature, and comparing result is sent to result comparison module；
The result comparison module compares the comparing result that multiple Characteristic Contrast modules are sent.
The received facial image of characteristic extracting module is to face facial image.
The message queue module receives and dispatches face characteristic data in the way of first in first out.
The result comparison module judges multiple comparison knots when comparing the comparing result that multiple Characteristic Contrast modules are sent
Whether fruit is consistent, by comparing result output and to data distribution module feedback pass signal if consistent, to number if inconsistent
According to distribution module feeding back unsuccessful signal.
The data distribution module is re-transmitted to after changing the putting in order of face characteristic when receiving failure signal
Characteristic Contrast module.
The characteristic extracting module is STM32F7 series processors.
The data distribution module is STM32F3 series processors.
The result comparison module is STM32F3 series processors.
As a result, based on the setting of message queue module, message queue mechanism is provided, may make feature extraction and Characteristic Contrast
Decoupling, it is more flexible in processing timing；Setting based on data distribution module and multiple Characteristic Contrast modules, can be largely
Upper guarantee accuracy, to reduce the additional computational overhead taken in the prior art in order to ensure accuracy.
Claims (8)
1. a kind of Distributive System of Face Recognition, including characteristic extracting module, message queue module, data distribution module, feature pair
Than module, result comparison module, feature database, it is characterised in that: the characteristic extracting module, message queue module, data distribution
Successively data connection, feature database are communicatively connected to Characteristic Contrast module for module, Characteristic Contrast module, result comparison module；
The characteristic extracting module receives facial image and extracts to face characteristic；
Face characteristic is that a data unit is sent to the face characteristic in each facial image by the message queue module
Data distribution module；
The face characteristic received is sent to multiple Characteristic Contrast modules with different order by the data distribution module；
It is special to compare the face read from feature database according to the sequence of the face characteristic received item by item for the Characteristic Contrast module
Sign, and comparing result is sent to result comparison module；
The result comparison module compares the comparing result that multiple Characteristic Contrast modules are sent.
2. Distributive System of Face Recognition as described in claim 1, it is characterised in that: the received face of characteristic extracting module
Image is to face facial image.
3. Distributive System of Face Recognition as described in claim 1, it is characterised in that: the message queue module is according to advanced elder generation
Mode out receives and dispatches face characteristic data.
4. Distributive System of Face Recognition as described in claim 1, it is characterised in that: the result comparison module is multiple in comparison
When the comparing result that Characteristic Contrast module is sent, judge whether multiple comparing results are consistent, exports comparing result if consistent
And to data distribution module feedback pass signal, to data distribution module feedback failure signal if inconsistent.
5. Distributive System of Face Recognition as claimed in claim 4, it is characterised in that: the data distribution module is receiving mistake
When losing signal, Characteristic Contrast module is re-transmitted to after changing the putting in order of face characteristic.
6. Distributive System of Face Recognition as described in claim 1, it is characterised in that: the characteristic extracting module is STM32F7
Series processors.
7. Distributive System of Face Recognition as described in claim 1, it is characterised in that: the data distribution module is STM32F3
Series processors.
8. Distributive System of Face Recognition as described in claim 1, it is characterised in that: the result comparison module is STM32F3
Series processors.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811354014.8A CN109635663A (en) | 2018-11-14 | 2018-11-14 | A kind of Distributive System of Face Recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811354014.8A CN109635663A (en) | 2018-11-14 | 2018-11-14 | A kind of Distributive System of Face Recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109635663A true CN109635663A (en) | 2019-04-16 |
Family
ID=66067999
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811354014.8A Pending CN109635663A (en) | 2018-11-14 | 2018-11-14 | A kind of Distributive System of Face Recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109635663A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103186772A (en) * | 2013-01-30 | 2013-07-03 | 上海交大高新技术股份有限公司 | Face recognition system and method based on cluster framework |
| CN105574506A (en) * | 2015-12-16 | 2016-05-11 | 深圳市商汤科技有限公司 | Intelligent face tracking system and method based on depth learning and large-scale clustering |
| CN105760817A (en) * | 2016-01-28 | 2016-07-13 | 深圳泰首智能技术有限公司 | Method and device for recognizing, authenticating, unlocking and encrypting storage space by using human face |
| CN106530567A (en) * | 2016-10-25 | 2017-03-22 | 上海银晨智能识别科技有限公司 | Alarm comparison module, system and method suitable for large-scale control |
| CN108229260A (en) * | 2016-12-21 | 2018-06-29 | 杭州海康威视系统技术有限公司 | A kind of identity information checking method and system |
-
2018
- 2018-11-14 CN CN201811354014.8A patent/CN109635663A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103186772A (en) * | 2013-01-30 | 2013-07-03 | 上海交大高新技术股份有限公司 | Face recognition system and method based on cluster framework |
| CN105574506A (en) * | 2015-12-16 | 2016-05-11 | 深圳市商汤科技有限公司 | Intelligent face tracking system and method based on depth learning and large-scale clustering |
| CN105760817A (en) * | 2016-01-28 | 2016-07-13 | 深圳泰首智能技术有限公司 | Method and device for recognizing, authenticating, unlocking and encrypting storage space by using human face |
| CN106530567A (en) * | 2016-10-25 | 2017-03-22 | 上海银晨智能识别科技有限公司 | Alarm comparison module, system and method suitable for large-scale control |
| CN108229260A (en) * | 2016-12-21 | 2018-06-29 | 杭州海康威视系统技术有限公司 | A kind of identity information checking method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA2973393C (en) | A system and a method for image recognition | |
| US11138903B2 (en) | Method, apparatus, device and system for sign language translation | |
| US10438056B2 (en) | Face recognition system and face recognition method | |
| EP4030381A1 (en) | Artificial-intelligence-based image processing method and apparatus, and device and storage medium | |
| CN108108711B (en) | Face control method, electronic device and storage medium | |
| CN110827432B (en) | Class attendance checking method and system based on face recognition | |
| CN103686345A (en) | Video content comparing method based on digital signal processor | |
| CN103632127A (en) | An intelligent biological characteristic identification system based on cloud computing | |
| CN109033981A (en) | The method for reducing palm vein identification system power consumption based on ultrasonic distance measurement | |
| CN115329265A (en) | Method, device and equipment for determining graph code track association degree and storage medium | |
| CN110348272B (en) | Dynamic face recognition method, device, system and medium | |
| CN109635663A (en) | A kind of Distributive System of Face Recognition | |
| CN106844172A (en) | The log recording method and system of a kind of efficient alignment system failure | |
| Wu et al. | Real-time gender classification | |
| CN208580412U (en) | A kind of low-power consumption vena metacarpea identification equipment and system | |
| WO2020133734A1 (en) | Biological information recognition method, device and system, and computer storable medium | |
| CN114842413A (en) | Automatic push enjoyment learning system according to fatigue monitoring | |
| CN109614903A (en) | A kind of external face identification device of monitor camera | |
| CN207624037U (en) | A kind of tracking system based on Internet of Things logistics | |
| CN109684918A (en) | A kind of high-speed object identifying system | |
| CN103745504A (en) | Automatic attendance system | |
| CN111178322B (en) | Identification acceleration system and method for edge image | |
| CN114187435A (en) | Text recognition method, device, equipment and storage medium | |
| CN114257655A (en) | IEC104 protocol processing method and device based on 5G communication | |
| CN208314877U (en) | A kind of access control system based on RFID |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190416 |