CN109242755A - Computer vision processing server framework neural network based - Google Patents
Computer vision processing server framework neural network based Download PDFInfo
- Publication number
- CN109242755A CN109242755A CN201810863338.8A CN201810863338A CN109242755A CN 109242755 A CN109242755 A CN 109242755A CN 201810863338 A CN201810863338 A CN 201810863338A CN 109242755 A CN109242755 A CN 109242755A
- Authority
- CN
- China
- Prior art keywords
- neural network
- child servers
- server
- computer vision
- vision processing
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 45
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 238000000605 extraction Methods 0.000 claims 2
- 238000000586 desensitisation Methods 0.000 abstract description 8
- 238000000034 method Methods 0.000 abstract description 3
- 230000005540 biological transmission Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 239000000284 extract Substances 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/20—Processor architectures; Processor configuration, e.g. pipelining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
- G06F21/6254—Protecting personal data, e.g. for financial or medical purposes by anonymising data, e.g. decorrelating personal data from the owner's identification
-
- 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
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/505—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the load
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Bioethics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention discloses a kind of computer vision processing server frameworks neural network based, including a female server and several child servers.Each child servers are under the jurisdiction of female server simultaneously.Each child servers are respectively equipped with neural network, and each child servers are pre-processed by respective neural network simultaneously.Female server is further processed to form computer vision processing data according to preprocessing image data.Computer vision processing server framework neural network based disclosed by the invention first pre-processes the picture or video that need computer vision to handle by child servers, to extract characteristics of image, realizes data desensitization, evades privacy leakage problem；Advanced treating is carried out to preprocessing image data by female server again, so that server architecture realizes load balancing as far as possible, reaches equalization point, realizes maximally utilizing for every server resource.
Description
Technical field
The invention belongs to server technology fields, and in particular to a kind of computer vision processing service neural network based
Device framework.
Background technique
Application system website, database, file system are concentrated on same server, material is thus formed initial stages
Server system.However, above-mentioned server system undertakes, pressure is excessive, and bandwidth, CPU, memory pressure may also be excessive, exists and delays
Machine risk.
On the other hand, the calculation amount of artificial intelligence project is bigger at present.These projects generally use GPU server, equally
There are similar problems, it is difficult to which realization allows multiple servers to achieve the purpose that load balancing.
In addition to this, image or video processing based on computer vision, is calculated and is located if you need to upload onto the server
The problem of managing, may also relate to image privacy leakage during transmission.
Summary of the invention
The present invention is directed to the situation of the prior art, overcomes drawbacks described above, provides a kind of computer view neural network based
Feel processing server framework.
The present invention uses following technical scheme, and the computer vision processing server framework neural network based is used
In picture or video that processing needs computer vision to handle, the computer vision processing server neural network based
Framework includes a female server and several child servers, in which:
Each child servers are under the jurisdiction of female server simultaneously；
Each child servers are respectively equipped with neural network, and each child servers are located by respective neural network in advance simultaneously
Reason prevents image privacy leakage problem occur in output transmission process to realize the desensitization of initial data；
Mother's server is obtained through the pretreated preprocessing image data of each child servers, while according to above-mentioned pre- place
Reason image data is further processed to form computer vision processing data.
According to the above technical scheme, each child servers by respective neural network carry out pretreatment be embodied as it is each
Child servers extract the characteristics of image of above-mentioned picture or video.
Present patent application also discloses a kind of computer vision processing server framework neural network based, it uses
In picture or video that processing needs computer vision to handle, the computer vision processing server neural network based
Framework includes a female server and several child servers, in which:
Each child servers are under the jurisdiction of female server simultaneously, and mother's server is selectively enabled one or more
A or whole child servers；
Each child servers are respectively equipped with neural network, each child servers selectively respective neural network of controlled starting
It is pre-processed, to realize the desensitization of initial data, prevents image privacy leakage problem occur in output transmission process；
Mother's server is obtained through the pretreated preprocessing image data of each child servers, while according to above-mentioned pre- place
Reason image data is further processed to form computer vision processing data.
According to the above technical scheme, each child servers by respective neural network carry out pretreatment be embodied as it is each
Child servers extract the characteristics of image of above-mentioned picture or video.
According to the above technical scheme, one or more or whole sub-services are selectively enabled in female server
Before device, the ratio of the child servers enabled needed for being assessed by female server according to overall load.
Computer vision processing server framework neural network based disclosed by the invention, the beneficial effect is that, first
(simple operation) is pre-processed to the picture or video that need computer vision to handle by child servers, to extract image
Feature realizes data desensitization, evades privacy leakage problem；Advanced treating is carried out to preprocessing image data by female server again
(complex calculation) reaches equalization point so that server architecture realizes load balancing as far as possible, realizes every server resource most
Bigization utilizes.
Specific embodiment
The invention discloses a kind of computer vision processing server frameworks neural network based, below with reference to preferred reality
Example is applied, further description of the specific embodiments of the present invention.
Preferably, the computer vision processing server framework neural network based needs computer for handling
The picture or video of visual processes, the computer vision processing server framework neural network based include a female clothes
Business device and several child servers, in which:
Each child servers are under the jurisdiction of female server simultaneously；
Each child servers are respectively equipped with neural network, and each child servers are located by respective neural network in advance simultaneously
Reason prevents image privacy leakage problem occur in output transmission process to realize the desensitization of initial data；
Mother's server is obtained through the pretreated preprocessing image data of each child servers, while according to above-mentioned pre- place
Reason image data is further processed to form computer vision processing data.
Further, each child servers are pre-processed by respective neural network, can be embodied as each height clothes
Business device extracts the characteristics of image of above-mentioned (computer vision is needed to handle) picture or video.
According to above preferred embodiment, computer vision processing clothes neural network based disclosed in present patent application
Business device framework is first pre-processed (simple operation) to the picture or video that need computer vision to handle by child servers,
To extract characteristics of image, realizes data desensitization, evade privacy leakage problem；Again by female server to preprocessing image data into
Row advanced treating (complex calculation) reaches equalization point so that server architecture realizes load balancing as far as possible, realizes every service
Device resource maximally utilizes.
According to above preferred embodiment, present patent application also discloses a kind of deformation implementation of above preferred embodiment
Example.Above-mentioned variant embodiment is described below.
According to above-mentioned variant embodiment, the computer vision processing server framework neural network based, for locating
The picture or video that reason needs computer vision to handle, the computer vision processing server framework neural network based
Including a female server and several child servers, in which:
Each child servers are under the jurisdiction of female server simultaneously, and mother's server is selectively enabled one or more
A or whole child servers；
Each child servers are respectively equipped with neural network, each child servers selectively respective neural network of controlled starting
It is pre-processed, to realize the desensitization of initial data, prevents image privacy leakage problem occur in output transmission process；
Mother's server is obtained through the pretreated preprocessing image data of each child servers, while according to above-mentioned pre- place
Reason image data is further processed to form computer vision processing data.
Further, each child servers are pre-processed by respective neural network, can be embodied as each height clothes
Business device extracts the characteristics of image of above-mentioned (computer vision is needed to handle) picture or video.
According to above preferred embodiment, computer vision processing clothes neural network based disclosed in present patent application
Business device framework, the ratio of the child servers enabled needed for first being assessed by female server according to calculation amount (overall load), then by son
Server is pre-processed (simple operation) to the picture or video that need computer vision to handle, to extract image spy
Sign realizes data desensitization, evades privacy leakage problem；Advanced treating finally is carried out to preprocessing image data by female server
(complex calculation) reaches equalization point so that server architecture realizes load balancing as far as possible, realizes every server resource most
Bigization utilizes.
For a person skilled in the art, technical solution documented by foregoing embodiments can still be repaired
Change or equivalent replacement of some of the technical features, it is all within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should be included in protection scope of the present invention.
Claims (5)
1. a kind of computer vision processing server framework neural network based needs computer vision processing for handling
Picture or video, which is characterized in that the computer vision processing server framework neural network based includes a mother
Server and several child servers, in which:
Each child servers are under the jurisdiction of female server simultaneously；
Each child servers are respectively equipped with neural network, and each child servers are pre-processed by respective neural network simultaneously；
Mother's server is obtained through the pretreated preprocessing image data of each child servers, while according to above-mentioned pretreatment figure
Computer vision processing data are formed as data are further processed.
2. computer vision processing server framework neural network based according to claim 1, which is characterized in that each
A child servers carry out pretreatment by respective neural network and are embodied as the above-mentioned picture of each child servers extraction or view
The characteristics of image of frequency.
3. a kind of computer vision processing server framework neural network based needs computer vision processing for handling
Picture or video, which is characterized in that the computer vision processing server framework neural network based includes a mother
Server and several child servers, in which:
Each child servers are under the jurisdiction of female server simultaneously, mother's server be selectively enabled one or more or
Person's whole child servers；
Each child servers are respectively equipped with neural network, and selectively respectively neural network carries out controlled starting each child servers
Pretreatment；
Mother's server is obtained through the pretreated preprocessing image data of each child servers, while according to above-mentioned pretreatment figure
Computer vision processing data are formed as data are further processed.
4. computer vision processing server framework neural network based according to claim 3, which is characterized in that each
A child servers carry out pretreatment by respective neural network and are embodied as the above-mentioned picture of each child servers extraction or view
The characteristics of image of frequency.
5. computer vision processing server framework neural network based according to claim 3, which is characterized in that
Mother's server is selectively enabled before one or more or whole child servers, by female server according to whole negative
Carry the ratio of the child servers enabled needed for assessment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810863338.8A CN109242755A (en) | 2018-08-01 | 2018-08-01 | Computer vision processing server framework neural network based |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810863338.8A CN109242755A (en) | 2018-08-01 | 2018-08-01 | Computer vision processing server framework neural network based |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109242755A true CN109242755A (en) | 2019-01-18 |
Family
ID=65073392
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810863338.8A Pending CN109242755A (en) | 2018-08-01 | 2018-08-01 | Computer vision processing server framework neural network based |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109242755A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020207079A1 (en) * | 2019-04-10 | 2020-10-15 | 创新先进技术有限公司 | Image recognition-based desensitization processing method and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102222213A (en) * | 2010-07-29 | 2011-10-19 | 郑文明 | Distributed vision computing method based on open type Web Service framework |
| CN104376389A (en) * | 2014-12-10 | 2015-02-25 | 国电南京自动化股份有限公司 | Master-slave type micro-grid power load prediction system and master-slave type micro-grid power load prediction method based on load balancing |
| CN105005911A (en) * | 2015-06-26 | 2015-10-28 | 深圳市腾讯计算机系统有限公司 | Operating system for deep neural network and operating method |
| CN106293942A (en) * | 2016-08-10 | 2017-01-04 | 中国科学技术大学苏州研究院 | Neutral net load balance optimization method based on the many cards of multimachine and system |
| CN107516063A (en) * | 2016-09-29 | 2017-12-26 | 天津铂创国茂电子科技发展有限公司 | Method based on cloud branch server recognition of face |
| CN107578453A (en) * | 2017-10-18 | 2018-01-12 | 北京旷视科技有限公司 | Compressed image processing method, apparatus, electronic equipment and computer-readable medium |
| CN107977662A (en) * | 2017-11-06 | 2018-05-01 | 清华大学深圳研究生院 | A kind of layered calculation method for realizing high speed processing computer visual image |
| CN108255605A (en) * | 2017-12-29 | 2018-07-06 | 北京邮电大学 | Image recognition cooperative computing method and system based on neural network |
-
2018
- 2018-08-01 CN CN201810863338.8A patent/CN109242755A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102222213A (en) * | 2010-07-29 | 2011-10-19 | 郑文明 | Distributed vision computing method based on open type Web Service framework |
| CN104376389A (en) * | 2014-12-10 | 2015-02-25 | 国电南京自动化股份有限公司 | Master-slave type micro-grid power load prediction system and master-slave type micro-grid power load prediction method based on load balancing |
| CN105005911A (en) * | 2015-06-26 | 2015-10-28 | 深圳市腾讯计算机系统有限公司 | Operating system for deep neural network and operating method |
| CN106293942A (en) * | 2016-08-10 | 2017-01-04 | 中国科学技术大学苏州研究院 | Neutral net load balance optimization method based on the many cards of multimachine and system |
| CN107516063A (en) * | 2016-09-29 | 2017-12-26 | 天津铂创国茂电子科技发展有限公司 | Method based on cloud branch server recognition of face |
| CN107578453A (en) * | 2017-10-18 | 2018-01-12 | 北京旷视科技有限公司 | Compressed image processing method, apparatus, electronic equipment and computer-readable medium |
| CN107977662A (en) * | 2017-11-06 | 2018-05-01 | 清华大学深圳研究生院 | A kind of layered calculation method for realizing high speed processing computer visual image |
| CN108255605A (en) * | 2017-12-29 | 2018-07-06 | 北京邮电大学 | Image recognition cooperative computing method and system based on neural network |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020207079A1 (en) * | 2019-04-10 | 2020-10-15 | 创新先进技术有限公司 | Image recognition-based desensitization processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cai et al. | Blind inpainting using the fully convolutional neural network | |
| CN108182657A (en) | A kind of face-image conversion method that confrontation network is generated based on cycle | |
| CN106326939A (en) | Parameter optimization method and system of convolutional neural network | |
| CN106295584A (en) | Depth migration study is in the recognition methods of crowd's attribute | |
| Zhao et al. | Identity preserving face completion for large ocular region occlusion | |
| CN108509819A (en) | A kind of Quick Response Code binarization method even for uneven illumination | |
| CN105095919A (en) | Image recognition method and image recognition device | |
| CN107832684A (en) | A kind of intelligent vein authentication method and system with independent learning ability | |
| CN106548179A (en) | The detection method of object and dress ornament key point, device and electronic equipment | |
| CN110852941A (en) | Two-dimensional virtual fitting method based on neural network | |
| CN106295501A (en) | The degree of depth based on lip movement study personal identification method | |
| CN104820974A (en) | Image denoising method based on ELM | |
| CN110826420A (en) | Training method and device of face recognition model | |
| CN108109121A (en) | A kind of face based on convolutional neural networks obscures quick removing method | |
| CN114897742B (en) | Image restoration method with texture and structural features fused twice | |
| CN109242755A (en) | Computer vision processing server framework neural network based | |
| JP2022101645A (en) | Encryption mask determination method, image recognition method, model training method, apparatus, electronic device, storage medium, and computer program | |
| Capece et al. | Implementation of a coin recognition system for mobile devices with deep learning | |
| Zakharov et al. | A method for feature matching in images using descriptor structures | |
| CN114299573A (en) | Video processing method and device, electronic equipment and storage medium | |
| KR20150002187A (en) | System and method for image defogging based on gaussian filtering | |
| CN113822114A (en) | Image processing method, related equipment and computer readable storage medium | |
| CN103824262A (en) | Improved rapid image restoration processing method using R-L iterative algorithm | |
| Liu et al. | Object detection of UAV power line inspection images based on federated learning | |
| Hou et al. | Efficient L 1-based nonlocal total variational model of Retinex for image restoration |
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: 20190118 |