CN103646390B - Image processing system based on multi-level image location and method - Google Patents
Image processing system based on multi-level image location and method Download PDFInfo
- Publication number
- CN103646390B CN103646390B CN201310449728.8A CN201310449728A CN103646390B CN 103646390 B CN103646390 B CN 103646390B CN 201310449728 A CN201310449728 A CN 201310449728A CN 103646390 B CN103646390 B CN 103646390B
- Authority
- CN
- China
- Prior art keywords
- image
- characteristic
- target
- carry out
- same number
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 86
- 238000012545 processing Methods 0.000 title claims abstract description 55
- 230000008878 coupling Effects 0.000 claims description 8
- 238000010168 coupling process Methods 0.000 claims description 8
- 238000005859 coupling reaction Methods 0.000 claims description 8
- 238000003672 processing method Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 abstract description 39
- 230000004807 localization Effects 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 description 10
- 208000031481 Pathologic Constriction Diseases 0.000 description 9
- 210000001215 vagina Anatomy 0.000 description 9
- 230000000875 corresponding effect Effects 0.000 description 6
- 238000006073 displacement reaction Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 239000003292 glue Substances 0.000 description 3
- 230000033001 locomotion Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000007639 printing Methods 0.000 description 2
- 238000012372 quality testing Methods 0.000 description 2
- 241000406668 Loxodonta cyclotis Species 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- IXSZQYVWNJNRAL-UHFFFAOYSA-N etoxazole Chemical compound CCOC1=CC(C(C)(C)C)=CC=C1C1N=C(C=2C(=CC=CC=2F)F)OC1 IXSZQYVWNJNRAL-UHFFFAOYSA-N 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000007645 offset printing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of image processing system based on multi-level image location and method, this system includes the image collecting device being sequentially connected with, image positioning device and image processing apparatus, the master sample image of image acquisition device same number of frames and target image, image positioning device sets characteristic image and hunting zone according to gray scale and/or the Gradient Features of each frame master sample image gathered in the master sample image of described frame, and then carry out characteristic image matching treatment in the target image of the same number of frames gathered, image processing apparatus carries out data and processes the side-play amount obtaining characteristic image, utilize digital image processing techniques that target image and the master sample image of the same number of frames of collection are carried out image comparison, again comparison result is analyzed image procossing.System and method of the present invention can Global localization, by fully aligned to target image and master sample image, improve accuracy and the forme accuracy of detection of image procossing.
Description
Technical field
The present invention relates to quality testing field based on machine vision technique, a kind of image based on multi-level image location
Processing system and method.
Background technology
For realizing the free convertible long-range objectives of RMB, it is ensured that its print quality is important prerequisite, and money glue gravure master and
Plate quality is the basis of basic assurance print quality, and quality problems occurs in any of which one, all can printing product quality produce tight
Ghost image rings.The forme of detection includes multiple edge litho master, offset printing forme, gravure master, gravure forme etc..Detection object breadth
Greatly, accuracy of detection requires that high, detection speed must be very fast.
The mode that various formes carry out manual detection is affected greatly by artificial subjective factor, inefficient, when there is the situation of missing inspection
There is generation, along with the development of science and technology and the raising of human cost progressively occur in that plate quality detecting system substitutes and manually carry out
Detection, existing detecting system is to utilize machine vision technique that with master sample image, the target image gathered is carried out pixel ratio
To and analyze, wherein, gather the mode that target image and master sample image generally use camera shoot, although shooting is most every time
According to the position of agreement, but minute angle, vibrations etc. may be placed with because of machine error, electrical movement error, detection object
Factor, the target image of shooting every time and master sample image can not 100% ground alignments.If target image and master sample figure
As being not aligned with, then both carry out pixel comparison and can there is deviation, affect successive image result, and then affect printing matter
Amount accuracy of detection.
Current existing framing mode has the positioning print device using plate cylinder, controller and the first-class parts of detection to constitute
Carrying out the location of target image, this location mode structure is complicated, and positioning precision is low；Also have and positioned by image matching technology
With image procossing, this location mode is all to use single fixing location technology to carry out images match location, due to detection
Object is complicated and changeable, and some places image is intensive, some places image sparse, and some figure stricture of vaginas are relatively thick, and some figure stricture of vaginas are relatively thin, adopt
Cannot complete to be accurately positioned for all detection objects by single image coupling location technology so that processing result image exists error,
The requirement to forme accuracy of detection can not be met.
Summary of the invention
The present invention is directed to existing detecting system to be accurately positioned for all detection objects and then can not meet forme detection essence
The problem of the requirement of degree, it is provided that a kind of image processing system based on multi-level image location, it is possible to Global localization, by target figure
Picture and master sample image are fully aligned, it is ensured that the accuracy that successive image processes, and improve forme accuracy of detection.The present invention is also
A kind of method relating to image procossing based on multi-level image location.
Technical scheme is as follows:
A kind of image processing system based on multi-level image location, it is characterised in that the image collecting device that includes being sequentially connected with,
Image positioning device and image processing apparatus, the master sample image of described image acquisition device same number of frames and target image,
Described image positioning device according to the gray scale of each frame master sample image gathered and/or Gradient Features at the standard sample of described frame
This image sets characteristic image and hunting zone, and then carries out at characteristic image coupling in the target image of the same number of frames gathered
Reason, described image processing apparatus carries out data process according to the characteristic image matching result that image positioning device obtains and obtains characteristic pattern
The side-play amount of picture, and use digital image processing techniques by the target figure of the same number of frames of collection according to the side-play amount of described characteristic image
Picture and master sample image carry out image comparison, then comparison result has been analyzed image procossing.
Described image positioning device in the target image of the same number of frames gathered based on gray scale and/or the image distance of gradient and/or
Distribution coefficient carries out characteristic image matching treatment.
Described image positioning device according to the gray scale of master sample image gathered and/or Gradient Features by the whole of target image or
Major part is set as characteristic image, and then the global registration carrying out characteristic image in the target image of the same number of frames gathered processes.
The gray scale of the master sample image of collection and/or the image setting of Gradient Features distinctness are characterized by described image positioning device
Image, in the target image of the same number of frames gathered, extensive search characteristic image is to carry out characteristic image matching treatment.
The gray scale of the master sample image of collection and/or the image setting of Gradient Features distinctness are characterized by described image positioning device
Image, has the characteristic image of repetition in described target image, little range searching feature in the target image of the same number of frames gathered
Image is to carry out characteristic image local matching process.
Described image positioning device in the zones of different of the master sample image gathered according to the gray scale of image and/or Gradient Features
Set different characteristic images and hunting zone, and carry out the complete of each characteristic image respectively in the target image of the same number of frames gathered
Office's matching treatment and/or each characteristic image of extensive search are to carry out characteristic image matching treatment and/or each characteristic pattern of little range searching
As to carry out characteristic image local matching process.
The characteristic image matching result that described image processing apparatus obtains according to image positioning device carries out data process, and in feature
Images match result carries out standardization processing when comprising multiple value, according to gray scale and/or the image distance of gradient and/or matching factor
Weight coefficient is weighted and processes the side-play amount obtaining characteristic image.
A kind of image processing method based on multi-level image location, it is characterised in that first gather the master sample image of same number of frames
With target image, and according to the gray scale of each frame master sample image gathered and/or Gradient Features at the master sample figure of described frame
Set characteristic image and hunting zone in Xiang, and then carry out characteristic image matching treatment in the target image of the same number of frames gathered,
Then carry out data process according to the characteristic image matching result obtained and obtain the side-play amount of characteristic image, and according to described characteristic pattern
The side-play amount of picture uses digital image processing techniques that target image and the master sample image of the same number of frames of collection are carried out image ratio
Right, then comparison result has been analyzed image procossing.
In the zones of different of the master sample image gathered, gray scale and/or Gradient Features according to image set one or more spies
Levy image and the hunting zone corresponding with described characteristic image, and in the target image of the same number of frames gathered based on gray scale and/or
The image distance of gradient and/or matching factor carry out characteristic image matching treatment.
Described characteristic image matching treatment includes that the global registration of characteristic image processes and/or extensive search characteristic image is to carry out
Characteristic image matching treatment and/or little range searching characteristic image are to carry out characteristic image local matching process；At described global registration
Reason is according to the gray scale of master sample image gathered and/or Gradient Features target image to be wholly or largely set as feature
Image, and then in the target image of the same number of frames gathered, carry out the global registration process of characteristic image；Described extensive search is special
Levying image to carry out characteristic image matching treatment is by image distinct to the gray scale of master sample image gathered and/or Gradient Features
Being set as characteristic image, in the target image of the same number of frames gathered, extensive search characteristic image is to carry out at characteristic image coupling
Reason；Described little range searching characteristic image is by the gray scale of the master sample image gathered carry out characteristic image local matching to process
And/or the image setting of Gradient Features distinctness is characterized image, there is the characteristic image of repetition, gather in described target image
In the target image of same number of frames, little range searching characteristic image is to carry out characteristic image local matching process.
Carry out standardization processing when characteristic image matching result comprises multiple value, according to gray scale and/or gradient image distance and/
Or matching factor chooses oplimal Location result, or comprehensive partly or entirely positioning result is as final positioning result.
The technique effect of the present invention is as follows:
The present invention relates to a kind of based on multi-level image location image processing system, arrange be sequentially connected with image collecting device,
Image positioning device and image processing apparatus, image positioning device is according to the gray scale of each frame master sample image gathered and/or ladder
Degree feature sets characteristic image and hunting zone in the master sample image of described frame, and then at the target figure of the same number of frames gathered
Carrying out characteristic image matching treatment in Xiang, the characteristic image matching result that image processing apparatus obtains according to image positioning device is carried out
Data process the side-play amount obtaining characteristic image, and complete successive image process.I.e. image positioning device is according to each frame gathered
The actual graphical situation of master sample image sets characteristic image and hunting zone, and utilizes image matching technology to carry out characteristic pattern
As coupling, in conjunction with image processing apparatus, matching result is carried out data process and accurately obtain characteristic image side-play amount such that it is able to be real
Existing target image and master sample image are fully aligned, process for successive image and provide the foundation, the gray scale of master sample image and/
Or Gradient Features dynamic flexible sets characteristic image and hunting zone, it is achieved the multi-level Global localization of image, it is ensured that at image
The accuracy of reason, further increases forme accuracy of detection, eliminates the baroque location print that existing location mode is used
Brush device, it is often more important that solve existing detecting system cannot be accurately positioned for all detection objects so that can not meet right
The problem of the requirement of forme accuracy of detection.Even if system of the present invention is uneven and figure stricture of vagina at the intensive density of image detecting object
Thickness unequal complicated and changeable in the case of, also can by image positioning device directly according to gather each frame master sample image
Gray scale and/or Gradient Features in this frame master sample image, manually or automatically set characteristic image and hunting zone, use image
Matching technique carries out data process and obtains characteristic image side-play amount, it is achieved target image positions, and reliability is high, it is possible to ensure paper money
Certificate glue gravure master and plate quality, and then lay solid for realizing money design master, the datumization of forme production and standardization
Basis.
The invention still further relates to a kind of image processing method based on multi-level image location, according to each frame master sample figure gathered
The gray scale of picture and/or Gradient Features set characteristic image and hunting zone in the master sample image of described frame, and then in collection
Carry out characteristic image matching treatment in the target image of same number of frames, then carry out at data according to the characteristic image matching result obtained
Reason obtains the side-play amount of characteristic image, it is possible to the location realizing target image with master sample image, i.e. realize detection object
Multi-level Global localization so that target image and master sample image are fully aligned, it is adaptable to detection object images flexible and changeable
Situation, then use digital image processing techniques that target image and the master sample image of the same number of frames of collection are carried out image comparison,
Again comparison result is analyzed, improves the accuracy of image procossing, further increase plate quality accuracy of detection.
Accompanying drawing explanation
Fig. 1 is the structural representation of the image processing system that the present invention positions based on multi-level image.
Fig. 2 a and Fig. 2 b is master sample image and the target of the image processing system that the present invention positions based on multi-level image respectively
The first location fundamental diagram of image.
Fig. 3 a and Fig. 3 b is master sample image and the target of the image processing system that the present invention positions based on multi-level image respectively
The second location fundamental diagram of image.
Fig. 4 a and Fig. 4 b is the 3rd of the master sample image of the image processing system that the present invention positions based on multi-level image respectively
Plant location fundamental diagram.
Fig. 5 a and Fig. 5 b is that the third of the target image of the image processing system that the present invention positions based on multi-level image is fixed respectively
Position fundamental diagram.
Fig. 6 is the workflow diagram of the method for the image procossing that the present invention positions based on multi-level image.
Detailed description of the invention
The present invention will be described below in conjunction with the accompanying drawings.
The present invention relates to a kind of image processing system based on multi-level image location, figure during for forme being carried out quality testing
As processing, this detection object can be glue gravure master, forme, film, print product, circuit board etc..This system structure is shown
It is intended to as it is shown in figure 1, include image collecting device, image positioning device and the image processing apparatus being sequentially connected with, wherein, will
Detection object lies in detection platform, and image collecting device can be arranged on detection platform overhead the driving at electric device
Lower motion in the range of justifying, at the volley or fixed point gathers high quality graphic, the standard sample of image acquisition device same number of frames
This image and target image, image positioning device according to the gray scale of each frame master sample image gathered and/or Gradient Features in institute
State and the master sample image of frame sets characteristic image and hunting zone, and then carry out spy in the target image of the same number of frames gathered
Levy images match to process；Image processing apparatus carries out data according to the characteristic image matching result that image positioning device obtains and processes
To the side-play amount of characteristic image, and the same number of frames that will gather according to the side-play amount employing digital image processing techniques of described characteristic image
Target image and master sample image carry out image comparison and (as image alignment, pointwise carry out pixel value and compare, the most also can adopt
By smoothing processing and Fuzzy Processing etc.), then comparison result has been analyzed image procossing.
System of the present invention uses multi-level Global localization technology, after image acquisition device one frame target image, first passes through
Target image is positioned by image positioning device, and it is the most fixed that image processing apparatus utilizes when processing a certain two field picture near it
The positioning result of this frame target image of position, carries out next step the image procossing such as image template study or figure stricture of vagina detection.Specifically,
Image positioning device uses images match treatment technology to employ three kinds of method of works:
(1) first method is global registration, i.e. image positioning device according to the gray scale of the master sample image gathered and/or ladder
Target image is wholly or largely set as characteristic image by degree feature, by target image to be positioned and master sample image
Wholly or largely contrast, so gather same number of frames target image in image distance based on gray scale and/or gradient and
/ or matching factor carry out characteristic image global registration process.The characteristic image that image processing apparatus obtains according to image positioning device
Matching result carries out data process, calculates based on color and/or the image distance of gradient and/or relevant matches coefficient, takes matching result
The side-play amount of optimum, or the comprehensive calculated side-play amount of multiple method, obtain the side-play amount of characteristic image, can be used as two
The horizontal and vertical side-play amount of width image.
As shown in Figure 2 a and 2 b, Fig. 2 a is master sample image to specific embodiment, is large-area characteristic image in bold box,
The major part of master sample image is set as characteristic image by i.e. image positioning device；Fig. 2 b is to be detected and the target figure of location
Picture, fine rule frame is matching result.
(2) second method uses location core (also known as characteristic image) to mate, the standard that i.e. image positioning device will gather
The image setting of the gray scale of sample image and/or Gradient Features distinctness is characterized image, and this location core can be automatically to calculate or hands
Dynamic specify, extensive search location core in target image to be positioned, so in the target image of the same number of frames gathered based on
Gray scale and/or the image distance of gradient and/or matching factor carry out the matching treatment of characteristic image.Image processing apparatus is fixed according to image
The characteristic image matching result that position device obtains carries out data process, calculates based on color and/or the image distance of gradient and/or is correlated with
Matching factor, takes the side-play amount of matching result optimum, or the comprehensive calculated side-play amount of multiple method, obtains this location core
Horizontal and vertical side-play amount.Can there is multiple location core, then the result of multiple location core is carried out preferred or comprehensive.
As shown in Figure 3 a and Figure 3 b shows, Fig. 3 a is master sample image to specific embodiment, for location core (characteristic image) in bold box,
The fine rule frame surrounding this bold box is hunting zone；Fig. 3 b is to be detected and the target image of location, and fine rule frame is matching result.
(3) the third method uses local positioning core (also known as local feature image) to mate, i.e. image positioning device will be adopted
The image setting of the gray scale of the master sample image of collection and/or Gradient Features distinctness is characterized image, and this location core can be automatically to count
Calculate or manually specify, at target image medium and small range searching location core to be positioned, and then at the target figure of the same number of frames gathered
Carry out the local matching of characteristic image based on gray scale and/or the image distance of gradient and/or matching factor process as interior.Image procossing fills
Put the characteristic image matching result obtained according to image positioning device and carry out data process, calculate based on color and/or the image of gradient
Distance and/or relevant matches coefficient, take the side-play amount of matching result optimum, or the comprehensive calculated side-play amount of multiple method,
Obtain the horizontal and vertical side-play amount of this local positioning core.Can there is multiple local positioning core, then the result of multiple location core is entered
Row is preferred or comprehensive.The third method and the difference of second method are that the former hunting zone is little, are suitable for the characteristic pattern with repetition
The location of picture, need by the positioning result (utilize the side-play amount of contiguous frames image essentially identical this favorably true) of adjacent image,
Or the Primary Location result using other technical method to obtain finely positions.
One by the positioning result of adjacent image is implemented shown in such as Fig. 4 a, 4b, 5a and 5b.Wherein, Fig. 4 a and Fig. 4 b
For two frame master sample images of close position collection shooting, Fig. 5 a and 5b is that two frames of close position collection shooting are to be detected
Target image, corresponding with Fig. 4 a and 4b respectively.It is characterized image in the bold box of Fig. 4 b, surrounds the fine rule frame of this bold box
For hunting zone, this two field picture uses second method (location core coupling) to position, the target image of frame corresponding to Fig. 4 b
As shown in Figure 5 b.Being local positioning core in bold box in Fig. 4 a, the fine rule frame surrounding this bold box is hunting zone, permissible
Seeing that hunting zone is the least, because location core pattern nearby has repetition, the target image of frame corresponding to Fig. 4 a is as shown in Figure 5 a.
In detection and localization, can first carry out Fig. 5 b positioning core coupling, matching result is as shown in the fine rule frame of Fig. 5 b；Again to Fig. 5 a
Carry out local positioning core coupling, the hunting zone defined based on Fig. 5 b side-play amount result and Fig. 4 a, can obtain Fig. 5 a's
Hunting zone is as shown in relatively large wire frame in this figure, and wire frame less in Fig. 5 a is matching result.
Certain characteristic image used for any of the above described a kind of location technology means, after image positioning device positions, at image
The characteristic image matching result that reason device obtains according to image positioning device carries out data process, if at image processing apparatus data
The result that obtains of reason comprises multiple value, such as color distance, color correlation coefficient, gradient distance, gradient relevant matches coefficient etc.,
Then they are carried out standardization processing, according still further to such as the weight coefficient meter of the image distance of gray scale and/or gradient and/or matching factor etc.
Calculate weighted sum, as this matching result.
Image positioning device sets according to the gray scale of image and/or Gradient Features in the zones of different of the master sample image gathered
Different characteristic images and hunting zone, and in the target image of the same number of frames gathered, carry out the overall situation of each characteristic image respectively
Join process and/or each characteristic image of extensive search with carry out characteristic image matching treatment and/or each characteristic image of little range searching with
Carry out characteristic image local matching process.System of the present invention can be according to each two field picture (master sample image and target image)
Gray scale and/or the configuration of the situation such as Gradient Features position mode accordingly, in other words according to each pixel value size feelings in each two field picture
Condition selects image positioning device and the working method of image processing apparatus, can be used alone a certain shape in above-mentioned duty
State, or it is used in combination two or three, their result of calculation is carried out comprehensive and selects.
The image collecting device of this system preferably includes area array cameras and laser displacement sensor, and this area array cameras can be CCD phase
Machine or CMOS camera etc., area array cameras carries out imaging to tested product, and is sent to image processing apparatus and processes, it is achieved figure
The matching measurement of stricture of vagina, figure stricture of vagina width measure and the measurement of miss distance.Arranged by guide rail and area array cameras and laser displacement are sensed
Moving in the horizontal plane that device is parallel with detection platform above detection platform, area array cameras automatically scans and lies in detection platform
Detection object obtains high-quality collection image to carry out the detection of figure stricture of vagina, and it is right that area array cameras or laser displacement sensor collect detection
The degree of depth of elephant is to carry out depth survey.
The invention still further relates to a kind of image processing method based on multi-level image location, the method is with above-mentioned based on multi-level image
The image processing system of location is corresponding, and its flow chart as shown in Figure 6, first gathers master sample image and the target figure of same number of frames
Picture, and the gray scale of each frame master sample image and/or Gradient Features according to gathering set in the master sample image of described frame
Characteristic image and hunting zone, and then carry out characteristic image matching treatment, then basis in the target image of the same number of frames gathered
The characteristic image matching result obtained carries out data and processes the side-play amount obtaining characteristic image, and according to the skew of described characteristic image
Amount uses digital image processing techniques that target image and the master sample image of the same number of frames of collection are carried out image comparison, then will compare
Result has been analyzed image procossing.
The method of the invention can carry out target image and the figure of master sample object by area array cameras and laser displacement sensor
As gathering, and arranged by guide rail and make area array cameras and laser displacement sensor do horizontal plane and vertical direction moves, face battle array phase
Machine automatically scans the detection object lain in detection platform and carries out figure stricture of vagina detection with collection high quality image in horizontal plane, described
Area array cameras or laser displacement sensor collect the degree of depth of detection object vertical direction to carry out depth survey, available high score
Resolution microtechnique and computer image processing technology, by the comparison with master sample, it is achieved to various masters and the figure of forme
The detection of stricture of vagina quality, space of a whole page size, space of a whole page defect etc..
The method preferably sets one according to the gray scale of image and/or Gradient Features in the zones of different of the master sample image gathered
Individual or multiple characteristic images and the hunting zone corresponding with described characteristic image, and base in the target image of the same number of frames gathered
Characteristic image matching treatment is carried out in gray scale and/or the image distance of gradient and/or matching factor.Characteristic image mentioned here mates
Process and include that the global registration process of characteristic image, extensive search characteristic image are to carry out characteristic image matching treatment, little scope
Search characteristics image with carry out characteristic image local matching process the one in these three processing mode, two or three.Described entirely
Office's matching treatment is gray scale and/or Gradient Features wholly or largely the setting target image of the master sample image according to gathering
It is set to characteristic image, and then the global registration carrying out characteristic image in the target image of the same number of frames gathered processes；Described big model
Enclosing search characteristics image to carry out characteristic image matching treatment is by fresh to the gray scale of master sample image and/or the Gradient Features that gather
Bright image setting is characterized image, and in the target image of the same number of frames gathered, extensive search characteristic image is to carry out characteristic pattern
As matching treatment；The master sample figure that described little range searching characteristic image is to gather to carry out local feature images match to process
The image setting of the gray scale of picture and/or Gradient Features distinctness is characterized image, has the characteristic image of repetition in described target image,
In the target image of the same number of frames gathered, little range searching characteristic image is to carry out characteristic image local matching process.
The method of the invention can select one or more location and image procossing modes according to the concrete condition of the every two field picture of reality,
And carry out standardization processing when certain characteristic image matching result comprises multiple value, according to gray scale and/or gradient image distance and
/ or the weight coefficient of matching factor be weighted and process the side-play amount obtaining characteristic image.
It should be pointed out that, that the above detailed description of the invention can make those skilled in the art that the invention is more fully understood,
But limit the invention never in any form.Therefore, although the invention is entered by this specification referring to the drawings with embodiment
Gone detailed description, it will be understood by those skilled in the art, however, that still the invention can be modified or etc.
With replacing, in a word, all are without departing from the technical scheme of the spirit and scope of the invention and improvement thereof, and it all should be contained at this
In the middle of the protection domain of patented invention-creation.
Claims (9)
1. an image processing system based on multi-level image location, it is characterised in that include the image collector being sequentially connected with
Put, image positioning device and image processing apparatus, the master sample image of described image acquisition device same number of frames and target figure
Picture, described image positioning device according to the gray scale of each frame master sample image gathered and/or Gradient Features in the standard of described frame
Sample image sets characteristic image and hunting zone, and then carries out characteristic image coupling in the target image of the same number of frames gathered
Processing, described image processing apparatus carries out data process according to the characteristic image matching result that image positioning device obtains and obtains feature
The side-play amount of image, and use digital image processing techniques by the target of the same number of frames of collection according to the side-play amount of described characteristic image
Image and master sample image carry out image comparison, then comparison result has been analyzed image procossing；
Described image positioning device in the zones of different of the master sample image gathered according to the gray scale of image and/or Gradient Features
Set different characteristic images and hunting zone, and carry out the complete of each characteristic image respectively in the target image of the same number of frames gathered
Office's matching treatment and/or each characteristic image of extensive search are to carry out characteristic image matching treatment and/or each characteristic pattern of little range searching
As to carry out characteristic image local matching process.
System the most according to claim 1, it is characterised in that described image positioning device is in the target of the same number of frames gathered
Characteristic image matching treatment is carried out in image based on gray scale and/or the image distance of gradient and/or matching factor.
System the most according to claim 1 and 2, it is characterised in that described image positioning device is according to the standard sample gathered
Target image is wholly or largely set as characteristic image by the gray scale of this image and/or Gradient Features, and then identical gather
The global registration carrying out characteristic image in the target image of frame processes.
System the most according to claim 1 and 2, it is characterised in that the master sample that described image positioning device will gather
The image setting of the gray scale of image and/or Gradient Features distinctness is characterized image, in the target image of the same number of frames gathered on a large scale
Search characteristics image is to carry out characteristic image matching treatment.
System the most according to claim 1 and 2, it is characterised in that the master sample that described image positioning device will gather
The image setting of the gray scale of image and/or Gradient Features distinctness is characterized image, has the characteristic pattern of repetition in described target image
Picture, in the target image of the same number of frames gathered, little range searching characteristic image is to carry out characteristic image local matching process.
System the most according to claim 1, it is characterised in that described image processing apparatus obtains according to image positioning device
Characteristic image matching result carry out data process, and carry out standardization processing when characteristic image matching result comprises multiple value,
It is weighted according to the weight coefficient of gray scale and/or the image distance of gradient and/or matching factor and processes obtaining the inclined of characteristic image
Shifting amount.
7. an image processing method based on multi-level image location, it is characterised in that first gather the master sample figure of same number of frames
Picture and target image, and according to the gray scale of each frame master sample image gathered and/or Gradient Features at the master sample of described frame
Image sets characteristic image and hunting zone, and then carries out characteristic image matching treatment in the target image of the same number of frames gathered,
Then carry out data process according to the characteristic image matching result obtained and obtain the side-play amount of characteristic image, and according to described characteristic pattern
The side-play amount of picture uses digital image processing techniques that target image and the master sample image of the same number of frames of collection are carried out image ratio
Right, then comparison result has been analyzed image procossing；
In the zones of different of the master sample image gathered, gray scale and/or Gradient Features according to image set one or more spies
Levy image and the hunting zone corresponding with described characteristic image, and in the target image of the same number of frames gathered based on gray scale and/or
The image distance of gradient and/or matching factor carry out characteristic image matching treatment.
Method the most according to claim 7, it is characterised in that described characteristic image matching treatment includes the complete of characteristic image
Office matching treatment and/or extensive search characteristic image with carry out characteristic image matching treatment and/or little range searching characteristic image with
Carry out characteristic image local matching process；The process of described global registration is gray scale and/or the gradient of the master sample image according to gathering
Feature is wholly or largely set as characteristic image by target image, and then carries out spy in the target image of the same number of frames gathered
The global registration levying image processes；Described extensive search characteristic image is the standard that will gather to carry out characteristic image matching treatment
The image setting of the gray scale of sample image and/or Gradient Features distinctness is characterized image, big in the target image of the same number of frames gathered
Range searching characteristic image is to carry out characteristic image matching treatment；Described little range searching characteristic image is to carry out characteristic image local
Matching treatment is that the gray scale of the master sample image of collection and/or the image setting of Gradient Features distinctness are characterized image, described mesh
Having the characteristic image of repetition in logo image, in the target image of the same number of frames gathered, little range searching characteristic image is to carry out spy
Levy image local matching treatment.
Method the most according to claim 8, it is characterised in that advise when characteristic image matching result comprises multiple value
Generalized processes, and chooses oplimal Location result, or comprehensive part or complete according to gray scale and/or the image distance of gradient and/or matching factor
Portion's positioning result is as final positioning result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310449728.8A CN103646390B (en) | 2013-09-27 | 2013-09-27 | Image processing system based on multi-level image location and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310449728.8A CN103646390B (en) | 2013-09-27 | 2013-09-27 | Image processing system based on multi-level image location and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103646390A CN103646390A (en) | 2014-03-19 |
| CN103646390B true CN103646390B (en) | 2016-11-23 |
Family
ID=50251600
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310449728.8A Active CN103646390B (en) | 2013-09-27 | 2013-09-27 | Image processing system based on multi-level image location and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103646390B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105241894B (en) * | 2015-08-28 | 2018-01-19 | 北京大恒图像视觉有限公司 | A kind of template method for registering surveyed for the product examine of multiple operation flexible printing |
| CN105957082A (en) * | 2016-05-04 | 2016-09-21 | 广东锐视智能检测有限公司 | Printing quality on-line monitoring method based on area-array camera |
| CN109829389B (en) * | 2019-01-08 | 2021-01-26 | 上海上湖信息技术有限公司 | Machine displacement determination method, device and computer storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1870855A2 (en) * | 2006-06-20 | 2007-12-26 | Ophthalmic Imaging systems | A device, method and system for automatic montage of segmented retinal images |
| CN101576956A (en) * | 2009-05-11 | 2009-11-11 | 天津普达软件技术有限公司 | On-line character detection method based on machine vision and system thereof |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7672540B2 (en) * | 2005-07-13 | 2010-03-02 | Siemens Medical Solutions USA, Inc, | Nonrigid registration of cardiac perfusion MR images using adaptive local template matching |
-
2013
- 2013-09-27 CN CN201310449728.8A patent/CN103646390B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1870855A2 (en) * | 2006-06-20 | 2007-12-26 | Ophthalmic Imaging systems | A device, method and system for automatic montage of segmented retinal images |
| CN101576956A (en) * | 2009-05-11 | 2009-11-11 | 天津普达软件技术有限公司 | On-line character detection method based on machine vision and system thereof |
Non-Patent Citations (2)
| Title |
|---|
| 基于数字图像处理技术的印刷品质量检测系统的应用研究;高军 等;《包装工程》;20061231;第27卷(第5期);111-113 * |
| 基于模板匹配的图像配准算法;高军 等;《西安交通大学学报》;20070331;第41卷(第3期);307-311 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103646390A (en) | 2014-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104574393B (en) | A kind of three-dimensional pavement crack pattern picture generates system and method | |
| CN103674962B (en) | Plate quality detection system and method | |
| CN105424350B (en) | Thin-wall part mode testing method and system based on machine vision | |
| CN104713885B (en) | A kind of structure light for pcb board on-line checking aids in binocular measuring method | |
| CN106840110B (en) | A kind of motion measuring method and device applied to large-scale more Lamb wave wave simulation systems | |
| CN106978774B (en) | A kind of road surface pit slot automatic testing method | |
| WO2018095213A1 (en) | Apparatus and method for measuring rotational speed of rotary shaft based on variable density sinusoidal fringe | |
| CN106996748A (en) | Wheel diameter measuring method based on binocular vision | |
| CN105699399B (en) | A kind of detection device and method of SMT masterplates quality | |
| CN104240262B (en) | Camera external parameter calibration device and calibration method for photogrammetry | |
| CN103581660B (en) | Line pair based full field sharpness test method and system | |
| CN103593663B (en) | A kind of image position method of money forme | |
| CN110146030A (en) | Side slope surface DEFORMATION MONITORING SYSTEM and method based on gridiron pattern notation | |
| CN111623942B (en) | Displacement measurement method for test structure model of unidirectional vibration table | |
| CN102768762A (en) | Digital camera calibration method targeted to shield tunnel defect digital radiography detection and device thereof | |
| CN109990703A (en) | A kind of size detecting method and system of prefabricated components | |
| CN103646390B (en) | Image processing system based on multi-level image location and method | |
| CN113554697A (en) | Cabin section profile accurate measurement method based on line laser | |
| CN103389072B (en) | An image point positioning precision assessment method based on straight line fitting | |
| CN101726316A (en) | Internal orientation element and distortion tester | |
| TW200817651A (en) | Distance measurement system and method | |
| CN117710588A (en) | Three-dimensional target detection method based on visual ranging priori information | |
| CN113850868B (en) | Wave climbing image recognition method | |
| CN106447729A (en) | 2 dimensional digital image related compensation method based on transformation of coordinates and 2 dimensional optical digital image related extensometer | |
| CN206709833U (en) | A kind of movement measuring device applied to large-scale more Lamb wave wave simulation systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210707 Address after: 100070 No.5 Zhonghe Road, Fengtai District, Beijing Patentee after: BEIJING BANKNOTE CURRENCY DESIGNING AND PLATING Co.,Ltd. Patentee after: China Banknote Printing Technology Research Institute Co.,Ltd. Patentee after: CHINA BANKNOTE PRINTING AND MINTING Corp. Address before: 100070 No.5 Zhonghe Road, Fengtai District, Beijing Patentee before: BEIJING BANKNOTE CURRENCY DESIGNING AND PLATING Co.,Ltd. Patentee before: SECURITY PRINTING INSTITUTE OF PEOPLE'S BANK OF CHINA Patentee before: CHINA BANKNOTE PRINTING AND MINTING Corp. |
|
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100070 No.5 Zhonghe Road, Fengtai District, Beijing Patentee after: BEIJING BANKNOTE CURRENCY DESIGNING AND PLATING Co.,Ltd. Patentee after: China Banknote Printing Technology Research Institute Co.,Ltd. Patentee after: China Banknote Printing and Minting Group Co.,Ltd. Address before: 100070 No.5 Zhonghe Road, Fengtai District, Beijing Patentee before: BEIJING BANKNOTE CURRENCY DESIGNING AND PLATING Co.,Ltd. Patentee before: China Banknote Printing Technology Research Institute Co.,Ltd. Patentee before: CHINA BANKNOTE PRINTING AND MINTING Corp. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231120 Address after: No. 5 Zhonghe Road, Fengtai Science and Technology Park, Fengtai District, Beijing, 100070 Patentee after: China Banknote design plate making Co.,Ltd. Patentee after: China Banknote Printing Technology Research Institute Co.,Ltd. Patentee after: China Banknote Printing and Minting Group Co.,Ltd. Address before: 100070 No.5 Zhonghe Road, Fengtai District, Beijing Patentee before: BEIJING BANKNOTE CURRENCY DESIGNING AND PLATING Co.,Ltd. Patentee before: China Banknote Printing Technology Research Institute Co.,Ltd. Patentee before: China Banknote Printing and Minting Group Co.,Ltd. |