CN206147669U - Mixed image recognition system of intelligent photoelectricity - Google Patents
Mixed image recognition system of intelligent photoelectricity Download PDFInfo
- Publication number
- CN206147669U CN206147669U CN201620899255.0U CN201620899255U CN206147669U CN 206147669 U CN206147669 U CN 206147669U CN 201620899255 U CN201620899255 U CN 201620899255U CN 206147669 U CN206147669 U CN 206147669U
- Authority
- CN
- China
- Prior art keywords
- unit
- image
- photoelectricity
- automatic identification
- digital signal
- 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.)
- Expired - Fee Related
Links
Landscapes
- Image Analysis (AREA)
Abstract
The utility model discloses a mixed image recognition system of intelligent photoelectricity, include image acquisition and acquire unit, the related converting unit of light ferroelectric phase and automatic identification unit, according to the technical solution of the integrated ceiling board, pass through field programmable gate array, the collection to target image is accomplished respectively to digital signal processor and ARM treater, handle and judge, at the image recognition in -process, the treater of the optimum matching that different task options correspond is accomplished, the advantage of the different treaters of full play, thereby quick to target image has been realized, accurate discernment, the processing speed of having solved the existence of the mixed image recognition system of current photoelectricity is slow, can not carry out real -time identification's problem.
Description
Technical field
The utility model is related to image identification technical field, and in particular to a kind of intelligent photoelectric mixed image identification system
System.
Background technology
Image recognition refers to and image is processed, analyzed and is understood, to recognize the target and object of various different modes.
Existing image recognition includes the identification of optical image recognition, computer picture recognition and photoelectricity mixed image, optical image recognition
It is big with information capacity, can parallel processing, the advantage of fast operation, but operational precision and flexibility are poor；Computer picture
Identification has PLC technology, analyzes, judges and store flexible advantage, but arithmetic speed is slower；Photoelectricity mixed image is recognized
Two methods mixing is 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, collection, process and the judgement of target image are adopted
Although same processor, which effectively reduces cost, but while greatly reducing the processing speed of whole system, it is impossible to
Satisfaction carries out the requirement of Real time identification to target image.
Utility model content
Technical problem to be solved in the utility model is to provide a kind of intelligent opto-electrical mixed image identifying system, and it is right to realize
Target image it is quick, accurately identify, solve that the processing speed that current Optoelectronic hybrid pattern recognition system is present is slow, Bu Nengjin
The problem of row Real time identification.
The utility model is achieved through the following technical solutions：
A kind of intelligent photoelectric mixed image identifying system, including IMAQ and acquiring unit, photoelectricity associated transform
Unit and automatic identification unit, wherein,
Described image collection is electrically connected with acquiring unit with photoelectricity associated transform unit and automatic identification unit, for complete
Into the collection and process of target image, and collection is sent to photoelectricity associated transform unit, described image with the result for processing
Collection specifically includes the first camera, field programmable gate array, digital signal processor with acquiring unit, the first camera with
Field programmable gate array, digital signal processor are sequentially connected, digital signal processor connection photoelectricity associated transform unit
And automatic identification unit；
The photoelectricity associated transform unit is electrically connected with automatic identification unit, for generating target image and reference picture
Joint image frequency spectrum, and send it to automatic identification unit, specifically include laser instrument, spatial filter, collimation lens, liquid
Brilliant TV, Fourier transform lens, wave filter and second camera, the laser instrument and spatial filter, collimation lens, liquid crystal
TV, Fourier transform lens, low pass filter and second camera are sequentially connected, LCD TV connection Digital Signal Processing
Device, second camera connection automatic identification unit；
The automatic identification unit is used to control IMAQ and acquiring unit action, while according to photoelectricity associated transform
The joint image frequency spectrum that unit sends is identified to target image, specifically includes arm processor；
Especially, the laser instrument adopts He-Ne laser.
Especially, the field programmable gate array adopts EPF10K30A chips.
Especially, the digital signal processor adopts TMS320C6416 chips.
Especially, the arm processor adopts S3C2440 chips.
The utility model compared with prior art, has the following advantages and advantages：
A kind of intelligent photoelectric mixed image identifying system described in the utility model, the collection of target image, process and
Judge each using the processor of corresponding best match, give full play to the advantage of different processor, realize to target image
It is quick, accurately identify, solve that the processing speed that current Optoelectronic hybrid pattern recognition system is present is slow, can not carry out in real time
The problem of identification.
Description of the drawings
Accompanying drawing described herein is used for providing further understanding the utility model embodiment, constitutes the one of the application
Part, does not constitute the restriction to the utility model embodiment.In the accompanying drawings：
Fig. 1 is the intelligent photoelectric mixed image identifying system structured flowchart that the utility model embodiment 1 is provided.
Specific embodiment
To make the purpose of this utility model, technical scheme and advantage become more apparent, with reference to embodiment and accompanying drawing,
The utility model is described in further detail, and exemplary embodiment of the present utility model and its explanation are only used for explaining this
Utility model, is not intended as to restriction of the present utility model.
Embodiment 1
As shown in figure 1, Fig. 1 is the intelligent photoelectric mixed image identifying system structure that the utility model embodiment 1 is provided
Block diagram.
In the present embodiment, a kind of intelligent photoelectric mixed image identifying system includes IMAQ and acquiring unit, photoelectricity
Associated transform unit and automatic identification unit.
Described image collection is electrically connected with acquiring unit with photoelectricity associated transform unit and automatic identification unit, for complete
Into the collection and process of target image, and collection is sent to photoelectricity associated transform unit with the result for processing, specifically included
First camera, field programmable gate array and digital signal processor.First camera, field programmable gate array and numeral
Signal processor is sequentially connected, and is respectively completed the acquisition to target image, collection and processes, and digital signal processor will be by processing
The joint image that target image signal and the reference image signal of its internal preset afterwards is constituted sends to photoelectricity is associated and becomes
Change unit.
Field programmable gate array is the product further developed on the basis of the programming devices such as PAL, GAL, PLD,
It is that integrated level highest is a kind of in special IC, FPGA employs 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 interconnector（Interconnect）Three parts, user can be to its inside
Logic module and I/O modules are reconfigured, to realize the logic of user.It also has static repeatable programming and dynamic in system
The characteristic of reconstruct so that the function of hardware can be changed as software by programming.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 it is original can
The limited shortcoming of programming device gate circuit number.Therefore, the use of field programmable gate array is very flexible, and is seen with sequential
Long, inside possesses very abundant logical resource, and the working method that it is most matched i.e. data acquisition, the present embodiment can using scene
Programming gate array completes the collection of target image and not only can match polytype camera, while IMAQ speed is obtained
Greatly improve.Field programmable gate array described in the present embodiment specifically adopts EPF10K30A chips.
Digital signal processor is the device that bulk information is processed with data signal, and it has powerful data processing energy
The speed of service of power and superelevation, real time execution speed up to per 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, the working method that it is most matched i.e. data processing, the present embodiment completes the process of target image using digital signal processor
Image semantic classification speed can be greatly improved.The present embodiment digital signal processor specifically adopts TMS320C6416 chips.
The photoelectricity associated transform unit is electrically connected with automatic identification unit, generates the connection of target image and reference picture
Image spectrum is closed, and sends it to automatic identification unit, specifically include laser instrument, spatial filter, collimation lens, liquid crystal electricity
Depending on, Fourier transform lens, wave filter and second camera.Laser instrument, spatial filter, collimation lens, LCD TV, Fu Li
Leaf transformation lens, low pass filter and second camera are sequentially connected, LCD TV connection digital signal processor, the second shooting
Head connection automatic identification unit.Wherein, the laser implement body adopts He-Ne laser, and as light source infrared ray is sent, and Jing is empty
Between wave filter strengthen after radiation collimation lens, collimation lens projects the light collection launched into parallel light, irradiating liquid crystal
TV, LCD TV simultaneous connection word signal processor receives combined image signal, and the collimated lens of combined image signal are penetrated
After the light irradiation for going out, after being fourier transformed lens, joint image frequency spectrum is obtained, the low-pass filtered device of the frequency spectrum is filtered
Afterwards, Jing second cameras are exported to automatic identification unit.
The automatic identification unit is electrically connected with digital signal processing unit and second camera, control IMAQ with
Acquiring unit action, while the joint image frequency spectrum sent according to photoelectricity associated transform unit is identified to target image,
Specifically include arm processor.
Arm processor is a kind of microprocessor towards low budget market, while with stronger transaction management function, its
Advantage is mainly reflected in control aspect, and the present embodiment completes the identification of target image using arm processor, in the same of reduces cost
When can greatly improve the speed of image recognition.The present embodiment arm processor specifically adopts S3C2440 chips.
Above-mentioned intelligent photoelectric mixed image identifying system specific work process is：First camera and field programmable gate
Array is respectively completed the acquisition and collection of target image, digital signal processor the image for gathering is pre-processed and distortion at
Reason, while digital signal processor internal preset reference picture, and using the target image after reference picture and process as joint
Image is exported in real time to LCD TV, and joint image is fourier transformed lens forming connection after the irradiation of laser beam
Image Fourier spectrum is closed, after the frequency spectrum is low-pass filtered, is received by second camera and is entered arm processor, complete image
The Modulation and Amplitude Modulation of frequency spectrum and the process of inverse Fourier transform, obtain required cross correlation results.Due to true target cross-correlated signal compared with
By force, glitch cross-correlated signal is very weak, can work as phase by judging true and false target image in arm processor given threshold
When closing result more than threshold value, true target is designated, during less than threshold value, is designated decoy.When decoy is judged as, by logical
Letter Interface Controller digital signal processor, digital signal processor further controls field programmable gate array by communication interface
Proceed IMAQ and process, the image recognition of next target is realized, until determining true target.
The technical solution of the utility model, by field programmable gate array, digital signal processor and arm processor point
The collection to target image is not completed, is processed and is judged, in image recognition processes, different task selects corresponding optimal
The processor matched somebody with somebody gives full play to the advantage of different processor, it is achieved thereby that quick, the accurate knowledge to target image completing
Not, solve the problems, such as that the processing speed that current Optoelectronic hybrid pattern recognition system is present is slow, Real time identification can not be carried out.
Above-described specific embodiment, is entered to the purpose of this utility model, technical scheme and beneficial effect
One step is described in detail, be should be understood that and be the foregoing is only a kind of specific embodiment of the present utility model, and without
It is all within spirit of the present utility model and principle in protection domain of the present utility model is limited, any modification, the equivalent made
Replace, improve etc., should be included within protection domain of the present utility model.
Claims (5)
1. a kind of intelligent photoelectric mixed image identifying system, it is characterised in that including IMAQ and acquiring unit, photoelectricity phase
Correlative transformation unit and automatic identification unit, wherein,
Described image collection is electrically connected with acquiring unit with photoelectricity associated transform unit and automatic identification unit, for completing mesh
The collection of logo image and process, and collection is sent to photoelectricity associated transform unit, described image collection with the result for processing
The first camera, field programmable gate array, digital signal processor, the first camera and scene are specifically included with acquiring unit
Programmable gate array, digital signal processor are sequentially connected, digital signal processor connection photoelectricity associated transform unit and from
Dynamic recognition unit；
The photoelectricity associated transform unit is electrically connected with automatic identification unit, for generating the connection of target image and reference picture
Image spectrum is closed, and sends it to automatic identification unit, specifically include laser instrument, spatial filter, collimation lens, liquid crystal electricity
Depending on, Fourier transform lens, wave filter and second camera, the laser instrument and spatial filter, collimation lens, liquid crystal electricity
Depending on, Fourier transform lens, low pass filter and second camera be sequentially connected, LCD TV connection digital signal processor,
Second camera connects automatic identification unit；
The automatic identification unit is used to control IMAQ and acquiring unit action, while according to photoelectricity associated transform unit
The joint image frequency spectrum of transmission is identified to target image, specifically includes arm processor.
2. intelligent photoelectric mixed image identifying system according to claim 1, it is characterised in that the laser instrument is adopted
He-Ne laser.
3. intelligent photoelectric mixed image identifying system according to claim 1, it is characterised in that the field-programmable
Gate array adopts EPF10K30A chips.
4. intelligent photoelectric mixed image identifying system according to claim 1, it is characterised in that at the data signal
Reason device adopts TMS320C6416 chips.
5. intelligent photoelectric mixed image identifying system according to claim 1, it is characterised in that the arm processor
Using S3C2440 chips.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201620899255.0U CN206147669U (en) | 2016-08-18 | 2016-08-18 | Mixed image recognition system of intelligent photoelectricity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201620899255.0U CN206147669U (en) | 2016-08-18 | 2016-08-18 | Mixed image recognition system of intelligent photoelectricity |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN206147669U true CN206147669U (en) | 2017-05-03 |
Family
ID=58627292
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201620899255.0U Expired - Fee Related CN206147669U (en) | 2016-08-18 | 2016-08-18 | Mixed image recognition system of intelligent photoelectricity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN206147669U (en) |
-
2016
- 2016-08-18 CN CN201620899255.0U patent/CN206147669U/en not_active Expired - Fee Related
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111062880B (en) | Underwater image real-time enhancement method based on condition generation countermeasure network | |
| CN107369635B (en) | Intelligent semiconductor equipment system based on deep learning | |
| CN105719188A (en) | Method and server for achieving insurance claim anti-fraud based on consistency of multiple pictures | |
| CN103020590B (en) | A kind of vehicle identification system based on three-dimensional model and images match and method thereof | |
| CN101711676A (en) | Finger vein authentication apparatus and finger vein authentication method | |
| CN108921814A (en) | A kind of Citrus Huanglongbing pathogen on-line quick detection system and method based on deep learning | |
| CN105841793A (en) | Optical fiber vibration source identification method, device and system | |
| Alareqi et al. | Design and FPGA implementation of Real-Time Hardware Co-Simulation for image enhancement in biomedical applications | |
| CN112730454A (en) | Intelligent damage detection method for composite material based on fusion of optics, infrared thermal waves and ultrasonic waves | |
| CN103712699A (en) | Laser pulse contrast ratio measurement device based on optical limiting | |
| CN206147669U (en) | Mixed image recognition system of intelligent photoelectricity | |
| Katayama et al. | GAN-based color correction for underwater object detection | |
| CN107016324A (en) | A kind of fingerprint image processing method and fingerprint detection equipment | |
| CN106203421A (en) | A kind of Optoelectronic hybrid pattern recognition system | |
| CN107608570A (en) | What laser ionization air was imaged can touch-control system and touch-control detection method | |
| US20240119130A1 (en) | Authentication System, Device, and Method | |
| CN104458206A (en) | Labview-based image sensor testing system | |
| Tao et al. | Utilization of both machine vision and robotics technologies in assisting quality inspection and testing | |
| CN113591323B (en) | Embedded image dynamic scene simulation imaging system and method | |
| CN109886895A (en) | local fitting filtering method | |
| CN109584278A (en) | A kind of Target Identification Unit and method | |
| CN106791415A (en) | A kind of intelligent image processing unit | |
| CN103714524B (en) | Automatic fusion method for cold-rolled strip steel surface images | |
| CN108956395A (en) | A kind of method and terminal of air atom Concentration Testing | |
| Cornett et al. | Through the windshield driver recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170503 Termination date: 20180818 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |