CN106203421A - A kind of Optoelectronic hybrid pattern recognition system - Google Patents
A kind of Optoelectronic hybrid pattern recognition system Download PDFInfo
- Publication number
- CN106203421A CN106203421A CN201610684293.9A CN201610684293A CN106203421A CN 106203421 A CN106203421 A CN 106203421A CN 201610684293 A CN201610684293 A CN 201610684293A CN 106203421 A CN106203421 A CN 106203421A
- Authority
- CN
- China
- Prior art keywords
- unit
- image
- pattern recognition
- recognition system
- photoelectricity
- 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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/147—Details of sensors, e.g. sensor lenses
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Vascular Medicine (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of Optoelectronic hybrid pattern recognition system, including image acquisition and acquiring unit, photoelectricity associated transform unit and automatic identification unit, technical scheme, pass through field programmable gate array, digital signal processor and arm processor are respectively completed the collection to target image, process and judge, in image recognition processes, different task selects the processor of corresponding optimal coupling to complete, give full play to the advantage of different processor, it is achieved thereby that quick to target image, accurately identify, the processing speed solving current Optoelectronic hybrid pattern recognition system existence is slow, the problem that can not carry out Real time identification.
Description
Technical field
The present invention relates to image identification technical field, be specifically related to a kind of Optoelectronic hybrid pattern recognition system.
Background technology
Image recognition refers to process image, analyze and understand, to identify target and the object of various different mode.
Existing image recognition includes optical image recognition, computer picture recognition and photoelectricity mixed image identification, optical image recognition
There is information capacity big, can parallel processing, the advantage of fast operation, but operational precision and motility are poor;Computer picture
Identification has PLC technology, analyzes, judges and stores advantage flexibly, but arithmetic speed is slower;Photoelectricity mixed image identification
Two kinds of method mixing are used, completes to control, analyze and judge by computer picture recognition, completed by optical image recognition
Image transformation and process.But existing Optoelectronic hybrid pattern recognition system, the collection of target image, processes and judges all to use
Same processor, although which effectively reduces cost, but greatly reduces the processing speed of whole system simultaneously, it is impossible to
Meet the requirement that target image is carried out Real time identification.
Summary of the invention
The technical problem to be solved is to provide a kind of intelligent opto-electrical mixed image identification system, it is achieved to target
Image quick, accurately identify, solve that the processing speed that current Optoelectronic hybrid pattern recognition system exists is slow, can not carry out reality
Time identify problem.
The present invention is achieved through the following technical solutions:
A kind of Optoelectronic hybrid pattern recognition system, including image acquisition and acquiring unit, photoelectricity associated transform unit and automatically
Recognition unit, wherein,
Described image acquisition electrically connects with photoelectricity associated transform unit and automatic identification unit with acquiring unit, has been used for mesh
The collection of logo image and process, and the result gathered and process is sent to photoelectricity associated transform unit, described image acquisition
Specifically including the first photographic head, field programmable gate array, digital signal processor with acquiring unit, the first photographic head is with on-the-spot
Programmable gate array, digital signal processor are sequentially connected with, digital signal processor connect photoelectricity associated transform unit and from
Dynamic recognition unit;
Described photoelectricity associated transform unit electrically connects with automatic identification unit, for generating the connection of target image and reference picture
Close image spectrum, and send it to automatic identification unit, specifically include laser instrument, spatial filter, collimating lens, liquid crystal electricity
Depending on, Fourier transform lens, wave filter and second camera, described laser instrument and spatial filter, collimating lens, liquid crystal electricity
Depending on, Fourier transform lens, low pass filter and second camera be sequentially connected with, LCD TV connects digital signal processor,
Second camera connects automatic identification unit;
Described automatic identification unit is used for controlling image acquisition and acquiring unit action, simultaneously according to photoelectricity associated transform unit
Target image is identified by the joint image frequency spectrum sent, and specifically includes arm processor;
Especially, described laser instrument uses helium neon laser.
Especially, described field programmable gate array uses EPF10K30A chip.
Especially, described digital signal processor uses TMS320C6416 chip.
Especially, described arm processor uses S3C2440 chip.
The present invention compared with prior art, has such advantages as and beneficial effect:
A kind of Optoelectronic hybrid pattern recognition system of the present invention, the collection of target image, process and judge each to use right
The processor of the optimal coupling answered, gives full play to the advantage of different processor, it is achieved that to target image quick, accurately know
, the problem that the processing speed that current Optoelectronic hybrid pattern recognition system exists is slow, can not carry out Real time identification is not solved.
Accompanying drawing explanation
Accompanying drawing described herein is used for providing being further appreciated by the embodiment of the present invention, constitutes of the application
Point, it is not intended that the restriction to the embodiment of the present invention.In the accompanying drawings:
The Optoelectronic hybrid pattern recognition system structured flowchart that Fig. 1 provides for the embodiment of the present invention 1.
Detailed description of the invention
For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with embodiment and accompanying drawing, to this
Invention is described in further detail, and the exemplary embodiment of the present invention and explanation thereof are only used for explaining the present invention, do not make
For limitation of the invention.
Embodiment 1
As it is shown in figure 1, the Optoelectronic hybrid pattern recognition system structured flowchart that Fig. 1 provides for the embodiment of the present invention 1.
In the present embodiment, a kind of Optoelectronic hybrid pattern recognition system includes that image acquisition is associated with acquiring unit, photoelectricity
Converter unit and automatic identification unit.
Described image acquisition electrically connects with photoelectricity associated transform unit and automatic identification unit with acquiring unit, for complete
Become collection and the process of target image, and the result gathered and process is sent to photoelectricity associated transform unit, specifically include
First photographic head, field programmable gate array and digital signal processor.First photographic head, field programmable gate array and numeral
Signal processor is sequentially connected with, and is respectively completed the acquisition to target image, gathers and process, and digital signal processor will be by processing
After target image signal and the joint image that constitutes of the reference image signal of its internal preset send to photoelectricity and be associated change
Change unit.
Field programmable gate array is the product of development further on the basis of the programming devices such as PAL, GAL, PLD,
Being the one that in special IC, integrated level is the highest, FPGA have employed logical cell array LCA(Logic Cell Array)
Such a new ideas, inside includes configurable logic blocks CLB(Configurable Logic Block), output input
Module I OB (Input Output Block) and three parts of interconnector (Interconnect), user can be to its inside
Logic module and I/O module reconfigure, to realize the logic of user.It also has static repeatable programming and dynamically in system
The characteristic of reconstruct so that the function of hardware can be revised by programming as software.As special IC (ASIC)
A kind of semi-custom circuit in field, field programmable gate array had both solved the deficiency of custom circuit, overcome again original can
The shortcoming that programming device gate circuit number is limited.Therefore, the use of field programmable gate array is very flexible, and sees with sequential
Long, inside has very abundant logical resource, its working method i.e. data acquisition mated most, and the present embodiment uses the scene can
Programming gate array completes the collection of target image and is possible not only to mate polytype photographic head, and image acquisition speed obtains simultaneously
It is greatly improved.Field programmable gate array described in the present embodiment specifically uses EPF10K30A chip.
Digital signal processor is to process the device of bulk information with digital signal, and it has powerful data and processes energy
Power and the speed of service of superelevation, real time execution speed up to every number of seconds with ten million bar complicated order program, considerably beyond general micro-
Processor, is the chip become more and more important in the digitalized electron world.Digital signal processor operational capability is strong, and speed is fast, volume
Little, its i.e. data of working method mated most process, and the present embodiment uses digital signal processor to complete the process of target image
Image semantic classification speed can be greatly improved.The present embodiment digital signal processor specifically uses TMS320C6416 chip.
Described photoelectricity associated transform unit electrically connects with automatic identification unit, generates the connection of target image and reference picture
Close image spectrum, and send it to automatic identification unit, specifically include laser instrument, spatial filter, collimating lens, liquid crystal electricity
Depending on, Fourier transform lens, wave filter and second camera.Laser instrument, spatial filter, collimating lens, LCD TV, Fu Li
Leaf transformation lens, low pass filter and second camera are sequentially connected with, and LCD TV connects digital signal processor, the second shooting
Head connects automatic identification unit.Wherein, described laser instrument specifically uses helium neon laser, sends infrared ray as light source, through sky
Between wave filter strengthen after radiation collimation lens, the light collection of transmitting is become parallel light to penetrate by collimating lens, irradiating liquid crystal
TV, LCD TV is simultaneously connected with digital signal processor, receives combined image signal, and the collimated lens of combined image signal are penetrated
After the light gone out irradiates, after being fourier transformed lens, it is thus achieved that joint image frequency spectrum, the low-pass filtered device of this frequency spectrum is filtered
After, export to automatic identification unit through second camera.
Described automatic identification unit all electrically connects with digital signal processing unit and second camera, control image acquisition with
Acquiring unit action, target image is identified by the joint image frequency spectrum simultaneously sent according to photoelectricity associated transform unit,
Specifically include arm processor.
Arm processor is a kind of microprocessor towards low budget market, has stronger transaction management function simultaneously, its
Advantage is mainly reflected in control aspect, and the present embodiment uses arm processor to complete the identification of target image, is reducing the same of cost
Time can be greatly improved the speed of image recognition.The present embodiment arm processor specifically uses S3C2440 chip.
Above-mentioned Optoelectronic hybrid pattern recognition system specific works process is: the first photographic head and field programmable gate array divide
Not completing acquisition and the collection of target image, the image gathered is carried out digital signal processor pretreatment and distortion processes, with
Time digital signal processor internal preset reference picture, and using real as joint image to reference picture and the target image after processing
Time output on LCD TV, joint image, after the irradiation of laser beam, is fourier transformed lens forming joint image
Fourier spectrum, after this frequency spectrum is low-pass filtered, is received by second camera and enters arm processor, complete image spectrum
Modulation and Amplitude Modulation and the process of inverse Fourier transform, obtain required cross correlation results.Owing to true target cross-correlated signal is relatively strong, false letter
Number cross-correlated signal is the most weak, can judge true and false target image by setting threshold value at arm processor, i.e. big when correlated results
When threshold value, it is designated true target, during less than threshold value, is designated decoy.When being judged as decoy, by communication interface control
Digital signal processor processed, digital signal processor controls field programmable gate array by communication interface further and proceeds
Image acquisition and process, it is achieved the image recognition of next target, until determining true target.
Technical scheme, has been distinguished by field programmable gate array, digital signal processor and arm processor
In pairs target image collection, process and judge, in image recognition processes, different task selects corresponding optimal coupling
Processor completes, and gives full play to the advantage of different processor, it is achieved thereby that to target image quick, accurately identify, solve
The problem that the processing speed that the Optoelectronic hybrid pattern recognition system having determined current exists is slow, can not carry out Real time identification.
Above-described detailed description of the invention, has been carried out the purpose of the present invention, technical scheme and beneficial effect further
Describe in detail, be it should be understood that a kind of detailed description of the invention that the foregoing is only the present invention, be not used to limit this
Invention protection domain, all within the spirit and principles in the present invention, any modification, equivalent substitution and improvement etc. done, all should
Within being included in protection scope of the present invention.
Claims (5)
1. an Optoelectronic hybrid pattern recognition system, it is characterised in that include that image acquisition is associated with acquiring unit, photoelectricity change
Change unit and automatic identification unit, wherein,
Described image acquisition electrically connects with photoelectricity associated transform unit and automatic identification unit with acquiring unit, has been used for mesh
The collection of logo image and process, and the result gathered and process is sent to photoelectricity associated transform unit, described image acquisition
Specifically including the first photographic head, field programmable gate array, digital signal processor with acquiring unit, the first photographic head is with on-the-spot
Programmable gate array, digital signal processor are sequentially connected with, digital signal processor connect photoelectricity associated transform unit and from
Dynamic recognition unit;
Described photoelectricity associated transform unit electrically connects with automatic identification unit, for generating the connection of target image and reference picture
Close image spectrum, and send it to automatic identification unit, specifically include laser instrument, spatial filter, collimating lens, liquid crystal electricity
Depending on, Fourier transform lens, wave filter and second camera, described laser instrument and spatial filter, collimating lens, liquid crystal electricity
Depending on, Fourier transform lens, low pass filter and second camera be sequentially connected with, LCD TV connects digital signal processor,
Second camera connects automatic identification unit;
Described automatic identification unit is used for controlling image acquisition and acquiring unit action, simultaneously according to photoelectricity associated transform unit
Target image is identified by the joint image frequency spectrum sent, and specifically includes arm processor.
Optoelectronic hybrid pattern recognition system the most according to claim 1, it is characterised in that described laser instrument uses He-Ne to swash
Light device.
Optoelectronic hybrid pattern recognition system the most according to claim 1, it is characterised in that described field programmable gate array
Use EPF10K30A chip.
Optoelectronic hybrid pattern recognition system the most according to claim 1, it is characterised in that described digital signal processor is adopted
Use TMS320C6416 chip.
Optoelectronic hybrid pattern recognition system the most according to claim 1, it is characterised in that described arm processor uses
S3C2440 chip.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610684293.9A CN106203421A (en) | 2016-08-18 | 2016-08-18 | A kind of Optoelectronic hybrid pattern recognition system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610684293.9A CN106203421A (en) | 2016-08-18 | 2016-08-18 | A kind of Optoelectronic hybrid pattern recognition system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106203421A true CN106203421A (en) | 2016-12-07 |
Family
ID=57522632
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610684293.9A Pending CN106203421A (en) | 2016-08-18 | 2016-08-18 | A kind of Optoelectronic hybrid pattern recognition system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106203421A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109684653A (en) * | 2017-10-19 | 2019-04-26 | 成都海存艾匹科技有限公司 | Programmable gate array encapsulation containing programmable computing unit |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101236091A (en) * | 2008-01-31 | 2008-08-06 | 北京控制工程研究所 | Visual light navigation sensor |
CN101393010A (en) * | 2008-08-11 | 2009-03-25 | 张育民 | Embedded vision detecting system |
CN101587009A (en) * | 2009-07-02 | 2009-11-25 | 北京理工大学 | Microminiature photoelectric LCD device dynamic image transmission apparatus |
-
2016
- 2016-08-18 CN CN201610684293.9A patent/CN106203421A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101236091A (en) * | 2008-01-31 | 2008-08-06 | 北京控制工程研究所 | Visual light navigation sensor |
CN101393010A (en) * | 2008-08-11 | 2009-03-25 | 张育民 | Embedded vision detecting system |
CN101587009A (en) * | 2009-07-02 | 2009-11-25 | 北京理工大学 | Microminiature photoelectric LCD device dynamic image transmission apparatus |
Non-Patent Citations (1)
Title |
---|
刘景琳 等: "基于双CPU的实时光电图像识别系统", 《单片机与嵌入式系统应用》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109684653A (en) * | 2017-10-19 | 2019-04-26 | 成都海存艾匹科技有限公司 | Programmable gate array encapsulation containing programmable computing unit |
CN109684653B (en) * | 2017-10-19 | 2023-12-22 | 成都海存艾匹科技有限公司 | Programmable gate array package containing programmable computing units |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Peng et al. | Single underwater image enhancement using depth estimation based on blurriness | |
CN109792485A (en) | System and method for blending image | |
Peng et al. | Image haze removal using airlight white correction, local light filter, and aerial perspective prior | |
CN110473179B (en) | Method, system and equipment for detecting surface defects of thin film based on deep learning | |
Huang et al. | High-speed structured light based 3D scanning using an event camera | |
Farzana FM et al. | Design and Analysis for Removing Salt and Pepper Noise in Image Processing | |
US20170308990A1 (en) | Synthesis of transformed image views | |
CN108363482A (en) | A method of the three-dimension gesture based on binocular structure light controls smart television | |
CN109948637A (en) | Object test equipment, method for checking object and computer-readable medium | |
CN111179329A (en) | Three-dimensional target detection method and device and electronic equipment | |
CN113744348A (en) | Parameter calibration method and device and radar vision fusion detection equipment | |
CN110851280A (en) | Automatic data acquisition method based on distributed intelligent edge computing technology | |
CN103020590A (en) | Vehicle identification system and method based on three-dimensional model and image matching | |
CN110780982A (en) | Image processing method, device and equipment | |
Korakoppa et al. | An area efficient FPGA implementation of moving object detection and face detection using adaptive threshold method | |
CN106203421A (en) | A kind of Optoelectronic hybrid pattern recognition system | |
Wei et al. | Robust attention deraining network for synchronous rain streaks and raindrops removal | |
US10298914B2 (en) | Light field perception enhancement for integral display applications | |
CN105467714A (en) | Liquid crystal lens imaging apparatus and liquid crystal lens imaging method | |
CN206147669U (en) | Mixed image recognition system of intelligent photoelectricity | |
CN104458206A (en) | Labview-based image sensor testing system | |
EP3165018A2 (en) | System and method for quantifying reflection e.g. when analyzing laminated documents | |
CN110310341A (en) | Method, device, equipment and storage medium for generating default parameters in color algorithm | |
CN103941872A (en) | Interactive projection device and method for achieving writing with two pens and writing with two pens approaching to each other infinitely | |
CN114046882A (en) | Method and equipment for acquiring color test information of optical equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into 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: 20161207 |