CN108122230A - The soldered ball position-recognizing system of the recognition methods of image block, device and flip-chip - Google Patents
The soldered ball position-recognizing system of the recognition methods of image block, device and flip-chip Download PDFInfo
- Publication number
- CN108122230A CN108122230A CN201810023180.3A CN201810023180A CN108122230A CN 108122230 A CN108122230 A CN 108122230A CN 201810023180 A CN201810023180 A CN 201810023180A CN 108122230 A CN108122230 A CN 108122230A
- Authority
- CN
- China
- Prior art keywords
- subgraph
- pixel
- images
- recognized
- image
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000013519 translation Methods 0.000 claims abstract description 46
- 238000006243 chemical reaction Methods 0.000 claims abstract description 22
- 230000003044 adaptive effect Effects 0.000 claims abstract description 12
- 230000006870 function Effects 0.000 claims description 41
- 230000000694 effects Effects 0.000 claims description 22
- 238000000926 separation method Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000000977 initiatory effect Effects 0.000 abstract 1
- 230000008569 process Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- LQBJWKCYZGMFEV-UHFFFAOYSA-N lead tin Chemical compound [Sn].[Pb] LQBJWKCYZGMFEV-UHFFFAOYSA-N 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241000218202 Coptis Species 0.000 description 1
- 235000002991 Coptis groenlandica Nutrition 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30148—Semiconductor; IC; Wafer
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses the soldered ball position-recognizing systems of a kind of recognition methods of image block, device and flip-chip.Method includes matching in advance and translates initial point and initiation parameter；During subgraph adaptively translates images to be recognized according to translational velocity value, judge whether the current location of subgraph meets preset condition；If so, selecting minimum of the subgraph in translation motion in all different angle value, meet the target minimum of spacing pixel condition from selection between each minimum, and calculate the position of target image block and number in images to be recognized；If not, the different angle value of current location is calculated using dissimilarity function, if different angle value is not less than pixel scale transform key, the subgraph for obtaining Pixel-level continues to translate the images to be recognized of Pixel-level, it is on the contrary, pixel-level image is converted into sub-pixel level image, and updates the image sizes values of subgraph after conversion, the images to be recognized after adaptive translation conversion.The application improves the matching efficiency of image block.
Description
Technical field
The present embodiments relate to technical field of image processing, more particularly to a kind of recognition methods of image block, device
And the soldered ball position-recognizing system of flip-chip.
Background technology
With the fast development of computer technology, image processing techniques has also obtained quick development.In image procossing skill
In art field, template matching algorithm by design with the target object in image almost possess shape, and pixel Distribution value
Almost identical image is as template.In the matching process, carried out on the image using a pixel as parasang by the template
Translation go through time, then obtain the value of a series of similarity or distinctiveness ratio.When similarity maximum or distinctiveness ratio minimum, just
Reaching best match effect, the center of the position of template in the picture is exactly the place-centric of certain objects in image,
The certain objects being equivalent in image are identified.
For example, in semiconductor chip manufacturing field, flip chip technology (fct) passes through gold thread due to solving positive cartridge chip
Realize electrical connection, caused by do not tolerate external force squeeze, the problem of reliability is low, become the favorite in chip manufacturing field.
Cartridge chip is that tin-lead ball is deposited on I/O plates, then mutually ties chip overturning heating with ceramic substrate using the tin-lead ball of melting
It closes, it is seen that the position of soldered ball in flip-chip is accurately positioned, is very necessary for processing such as the follow-up encapsulation of chip.
In the soldered ball identification process to flip-chip, the prior art can be used various sensors and measure, but pass
The installation of sensor limits the raising of whole equipment integrated level, and during use micro-vision progress manual identified, take too long, knowledge
Other inefficiency.In addition, using, it is necessary to more match time, matching efficiency is slower, causing to weld during some image matching methods
Ball recognition efficiency is relatively low.
It is this field skill so as to promote the efficiency of images match identification in consideration of it, how to shorten the image block matched time
Art personnel's urgent problem to be solved.
The content of the invention
The purpose of the embodiment of the present invention is to provide the soldered ball position of a kind of recognition methods of image block, device and flip-chip
Identifying system not only ensures the matched high-precision of image block, the image block matched time is also shortened, so as to promote image
Efficiency with identification.
In order to solve the above technical problems, the embodiment of the present invention provides following technical scheme：
On the one hand the embodiment of the present invention provides a kind of recognition methods of image block, including：
The translational velocity value of initialization subgraph, threshold coefficient, translation initial point, and according to pre-defined distinctiveness ratio letter
Number calculates the different angle value of the translation initial point；
During the subgraph adaptively translates images to be recognized according to the translational velocity value, the son is judged
Whether the current location of image meets preset condition；
If so, select the subgraph in translation motion with the pole in all different angle value of the images to be recognized
Small value meets the target minimum of spacing pixel condition from selection between each minimum, is treated according to calculating each target minimum
Identify the position of target image block and number in image；
If it is not, then the phase of the subgraph and the images to be recognized in current location is calculated using the dissimilarity function
Different angle value simultaneously stores；
If the different angle value of current location be not less than pixel scale transform key, obtain Pixel-level subgraph continue according to
The translational velocity value adaptively translates the images to be recognized of Pixel-level；If the different angle value of current location turns less than pixel scale
Change threshold value, the subgraph of Pixel-level and images to be recognized are converted into sub-pixel level image, and update the figure of subgraph after conversion
As sizes values, the images to be recognized after conversion is adaptively translated according to the translational velocity value；
Wherein, the subgraph is the target image block in the images to be recognized, and the pixel scale transform key is
The product of the threshold coefficient and best match effect average, the best match effect average are in the dissimilarity function
Under, advance with the average that template matching algorithm calculates the best match effect of the subgraph and the images to be recognized.
Optionally, the dissimilarity function is：
In formula, the image size of the subgraph is a × b (a ＜ A, b ＜ B), and the image size of the images to be recognized is
When A × B, f (x, y) are in (x, y) position for the subgraph, the subgraph and the different angle value of the images to be recognized.
Optionally, it is described the subgraph of Pixel-level and images to be recognized are converted into sub-pixel level image to include：
The pixel of predetermined number is inserted between two adjacent original image vegetarian refreshments using cubic spline interpolation, by picture
The subgraph of plain grade and the images to be recognized of Pixel-level are converted into sub-pixel level image.
Optionally, it is described to judge whether the subgraph meets preset condition in the position of the images to be recognized and be：
As x+a ＞ A, if performing subsequent operation；
As x+a ＜ A, and y+b ＞ B, then y=y0, x=x+1, according to the translational velocity value adaptively translation described in wait to know
Other image；
As x+a ＜ A, and y+b ＜ B, perform and subsequent operates if not；
Wherein, the image size of the subgraph is a × b (a ＜ A, b ＜ B), and the image size of the images to be recognized is
A × B, the coordinate of the subgraph current location is (x, y), and the translation initial point is (x0, y0)。
Optionally, the spacing pixel condition is：
Between each minimum, there are the number of pixels of the lateral separation between two or more adjacent minimums
Less than b；And/or
Between each minimum, there are the number of pixels of the fore-and-aft distance between two or more adjacent minimums
Less than a；
Wherein, the image size of the subgraph is a × b (a ＜ A, b ＜ B), and the image size of the images to be recognized is
A×B。
Optionally, the target minimum that spacing pixel condition is met from selection between each minimum includes：
Meet the first object minimum of the spacing pixel condition from selection between each minimum；
Selection minimum value from each first object minimum, using as the target minimum in current region.
Optionally, it is described that the position of target image block and number in the images to be recognized are calculated according to each target minimum
Including：
Obtain the corresponding matched position coordinate of each target minimum；
Calculating position of the respective objects image block in the images to be recognized according to each matched position coordinate isIn formula, matched position coordinate is (x, y), and the image size of the subgraph is a × b；
The number of each target minimum is counted, using the number as target image block in the images to be recognized.
Optionally, the subgraph for obtaining Pixel-level continues adaptively to translate Pixel-level according to the translational velocity value
Images to be recognized includes：
Judge whether the subgraph and the images to be recognized are pixel-level image；
When judging that the subgraph is not pixel-level image, then the subgraph is converted into pixel-level image；
When judging that the images to be recognized is not pixel-level image, then the images to be recognized is converted into Pixel-level figure
Picture；
When judging that the images to be recognized and the subgraph are pixel-level image, then retain the images to be recognized and
The subgraph；
Subgraph after conversion or the subgraph of reservation are adaptively translated into treating for Pixel-level according to the translational velocity value
Identify image.
On the other hand the embodiment of the present invention provides a kind of identification device of image block, including：
Preprocessing module, for initializing the translational velocity value of subgraph, threshold coefficient, translation initial point, and according to pre-
The dissimilarity function first defined calculates the different angle value of the translation initial point；
Judgment module, for adaptively translating the process of images to be recognized according to the translational velocity value in the subgraph
In, judge whether the current location of the subgraph meets preset condition；The subgraph is the mesh in the images to be recognized
Logo image block；
Target image block determining module for meeting preset condition when the current location for judging the subgraph, selects institute
Subgraph is stated in translation motion with the minimum in all different angle value of the images to be recognized, is chosen between each minimum
Meet the target minimum of spacing pixel condition, target image block in the images to be recognized is calculated according to each target minimum
Position and number；
Different angle value computing module then calculates the subgraph using the dissimilarity function and the images to be recognized exists
The different angle value of current location simultaneously stores；
The adaptive handover module of pixel scale, if converting threshold not less than pixel scale for the different angle value of current location
Value, the subgraph continuation for obtaining Pixel-level adaptively translate the images to be recognized of Pixel-level according to the translational velocity value；If work as
The different angle value of front position is less than pixel scale transform key, and the subgraph of Pixel-level and images to be recognized are converted into sub-pix
Grade image, and the image sizes values of subgraph after conversion are updated, it adaptively translates according to the translational velocity value and is treated after conversion
Identify image；The pixel scale transform key is the product of the threshold coefficient and best match effect average, described optimal
Matching effect average is under the dissimilarity function, advances with template matching algorithm and calculates the subgraph and described wait to know
The average of the best match effect of other image.
The embodiment of the present invention finally additionally provides a kind of soldered ball position-recognizing system of flip-chip, including flip-chip and
Processor, the processor realize the figure as described in preceding any one when being used to perform the recognizer of the image block stored in memory
As block recognition methods the step of；Wherein, the subgraph is soldered ball image, and the images to be recognized is flip-chip image,
The target image block is the soldered ball region in the images to be recognized.
An embodiment of the present invention provides a kind of recognition methods of image block, translational velocity value, the threshold value of subgraph are initialized
Coefficient, translation initial point, and the different angle value for translating initial point is calculated according to pre-defined dissimilarity function；It is pressed in subgraph
During adaptively translating images to be recognized according to translational velocity value, judge whether the current location of subgraph meets default item
Part；If so, select subgraph in translation motion with the minimum in all different angle value of images to be recognized, from each minimum
The target minimum for meeting spacing pixel condition is chosen between value, target image in images to be recognized is calculated according to each target minimum
The position of block and number；If it is not, then the distinctiveness ratio of subgraph and images to be recognized in current location is calculated using dissimilarity function
It is worth and stores；If the different angle value of current location be not less than pixel scale transform key, obtain Pixel-level subgraph continue by
The images to be recognized of Pixel-level is adaptively translated according to translational velocity value；If the different angle value of current location is converted less than pixel scale
The subgraph of Pixel-level and images to be recognized are converted into sub-pixel level image by threshold value, and update the image of subgraph after conversion
Sizes values adaptively translate the images to be recognized after conversion according to translational velocity value.
The advantages of technical solution that the application provides, is, phase of the subgraph in current location is calculated using dissimilarity function
Different angle value, then according to the different angle value of current location and the relation of presetted pixel rank transform key, adaptive switching
The pixel of image and images to be recognized identifies, coarse matching is carried out using the subgraph and images to be recognized of pixel scale, with this
Matching speed is improved, relatively fine and smooth matching is carried out using sub-pixel other subgraph and images to be recognized, is come with this true
Protect matching precision；Compared with the image matching algorithm of the prior art, there is higher matching efficiency, also ensure images match essence
Degree and robustness.
In addition, the embodiment of the present invention provides corresponding realization device and flip-chip also directed to the recognition methods of image block
Soldered ball position-recognizing system, further such that the method has more practicability, the soldered ball position of described device and flip-chip
Put identifying system have the advantages that it is corresponding.
Description of the drawings
It, below will be to embodiment or existing for the clearer technical solution for illustrating the embodiment of the present invention or the prior art
Attached drawing is briefly described needed in technology description, it should be apparent that, the accompanying drawings in the following description is only this hair
Some bright embodiments, for those of ordinary skill in the art, without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of flow diagram of the recognition methods of image block provided in an embodiment of the present invention；
Fig. 2 is the flow diagram of the recognition methods of another image block provided in an embodiment of the present invention；
Fig. 3 is a kind of specific embodiment structure chart of the identification device of image block provided in an embodiment of the present invention.
Specific embodiment
In order to which those skilled in the art is made to more fully understand the present invention program, with reference to the accompanying drawings and detailed description
The present invention is described in further detail.Obviously, described embodiment be only part of the embodiment of the present invention rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Lower all other embodiments obtained, belong to the scope of protection of the invention.
Term " first ", " second ", " the 3rd " " in the description and claims of this application and above-mentioned attached drawing
Four " etc. be for distinguishing different objects rather than for describing specific order.In addition term " comprising " and " having " and
Their any deformations, it is intended that cover non-exclusive include.Such as contain the process of series of steps or unit, method,
The step of system, product or equipment are not limited to list or unit, but the step of may include not list or unit.
After the technical solution of the embodiment of the present invention is described, the various nonrestrictive realities of detailed description below the application
Apply mode.
Referring first to Fig. 1, Fig. 1 is a kind of flow diagram of the recognition methods of image block provided in an embodiment of the present invention,
The embodiment of the present invention may include herein below：
S101：The translational velocity value of initialization subgraph, threshold coefficient, translation initial point, and according to pre-defined phase
Different degree function calculates the different angle value of translation initial point.
The image size of subgraph is a × b (a ＜ A, b ＜ B), translation unit value h ∈ N+, h ∈ [1, b), exist for subgraph
The translational velocity adaptively translated in images to be recognized, for example, translation unit value be 1 when, i.e., subgraph is in images to be recognized
Upper progress is using 1 pixel as the adaptive translation of parasang.
Pixel scale transform key l δ are the product of threshold coefficient l and best match effect average δ.Threshold coefficient l is pre-
What is first set is not less than 1 any number, and the application does not do any restriction to specific value.δ is best match effect average, most preferably
Matching effect average is to advance with traditional template matching algorithm, calculates subgraph under dissimilarity function and multiple are to be identified
The average of the best match effect of image.For example, the dissimilarity function in the case where cross entropy measure formulas defines, to n samples
This picture carries out in images to be recognized the conventional method adaptively translated using 1 pixel as parasang by subgraph,
The average of subgraph and images to be recognized matching best match effect is obtained, using as best match effect average.
Translation initial point is the position pixel that subgraph starts translation in images to be recognized.
Dissimilarity function can be defined using distance metric formula, and the dissimilarity function after defining is：
In formula, the image size of subgraph is a × b (a ＜ A, b ＜ B), and the image size of images to be recognized is A × B, f
When (x, y) is in (x, y) position for subgraph, the different angle value of subgraph and images to be recognized.
The image size of subgraph is a × b (a ＜ A, b ＜ B), when f (x, y) is in (x, y) position for subgraph, subgraph
As the different angle value with images to be recognized.
Certainly, it is possible to use other define dissimilarity function, and the application does not do this any restriction.
S102：During subgraph adaptively translates images to be recognized according to translational velocity value, subgraph is judged
Whether current location meets preset condition, if so, S105 is performed, if it is not, then performing S103.
Subgraph is the target image block in images to be recognized, that is to say, that subgraph is that some in images to be recognized is special
Comprising subgraph in the image of earnest body, i.e. images to be recognized, the image-region of certain objects is target image block.Utilize son
Image translation travels through images to be recognized, and target image block identical with subgraph in images to be recognized is obtained with matching.Citing comes
It says, subgraph is soldered ball image, and images to be recognized is flip-chip image, and multiple soldered balls are included in flip-chip, therefore in upside-down mounting
In chip image there are multiple regions be soldered ball image, traversal is translated on flip-chip using subgraph, it may be determined that soldered ball
Specific location of the image on flip-chip image, so as to fulfill the identification of the position of soldered ball.
During subgraph adaptively translates images to be recognized according to translation unit value, subgraph can be in y directions
On according to translation unit value adaptively translated, also can in the x direction according to translate unit value adaptively be translated, in y
It is adaptively translated according to translation unit value on direction, as x+a ＞ A, it is to be identified to illustrate that current subgraph has had stepped through
Image；When adaptively being translated according to translation unit value in the x direction, as y+b ＞ B, current subgraph is illustrated
Images to be recognized is traveled through.
It is adaptively translated according to translation unit value in y-direction, i.e. (x, y)=(x, y+h)；Judge working as subgraph
Whether front position meets preset condition detailed process：
As x+a ＞ A, S105 is performed；
As x+a ＜ A, and y+b ＞ B, then y=y0, x=x+1 continues adaptively to translate and wait to know according to present translation unit value
Other image；
As x+a ＜ A, and y+b ＜ B, perform S103；
The image size of subgraph is a × b (a ＜ A, b ＜ B), and the image size of images to be recognized is A × B, and image is current
The coordinate of position is (x, y).
Also it can first judge y+b ＞ B, then judge x+a ＞ A, this does not influence the realization of the application.
It should be noted that subgraph is in images to be recognized when adaptively being translated, often by a pixel or
One region of person is required for carrying out judging whether current location meets condition, be unsatisfactory for, continues adaptively to translate, meet condition
Then determine target area position.
It is adaptively translated according to translation unit value in the x direction, i.e. (x, y)=(x+h, y)；Judge working as subgraph
Whether front position meets preset condition detailed process, can refer to the above process, is not just repeating herein.
S103：Subgraph and images to be recognized are calculated in the different angle value of current location using dissimilarity function and are stored.
S104：If the different angle value of current location is not less than pixel scale transform key, obtain the subgraph of Pixel-level after
The continuous images to be recognized that Pixel-level is adaptively translated according to translational velocity value；If the different angle value of current location is less than pixel scale
The subgraph of Pixel-level and images to be recognized be converted into sub-pixel level image by transform key, and updates subgraph after conversion
Image sizes values adaptively translate the images to be recognized after conversion according to translational velocity value.
The images to be recognized that the subgraph continuation of acquisition Pixel-level adaptively translates Pixel-level according to translational velocity value is specific
It may include：
Judge whether subgraph and images to be recognized are pixel-level image；
When judging that subgraph is not pixel-level image, then subgraph is converted into pixel-level image；
When judging that images to be recognized is not pixel-level image, then images to be recognized is converted into pixel-level image；
When judging that images to be recognized and subgraph are pixel-level image, then retain images to be recognized and subgraph；
Subgraph after conversion or the subgraph of reservation are adaptively translated into the to be identified of Pixel-level according to translational velocity value
Image.
The subgraph of Pixel-level and images to be recognized are converted into sub-pixel level image concretely：
Judge whether subgraph and images to be recognized are sub-pixel level image；When judging that subgraph is not sub-pixel, then
Subgraph is converted into sub-pixel level image using cubic spline interpolation；It is when judging images to be recognized for sub-pixel, then sharp
Images to be recognized is converted into sub-pixel level image with cubic spline interpolation.
Can be using cubic spline interpolation conversion sub-pixel level image：
Cubic spline interpolation is carried out to image intensity value, the image of pixel scale, interpolation is converted into sub-pix rank.It inserts
During value, the point of predetermined number should be inserted between images to be recognized and the two neighboring original image vegetarian refreshments of subgraph.Insertion point
Number can be according to circumstances self-defined.Point used in cubic spline interpolation is 4 points of continuous adjacent in artwork.Interpolation terminates
Afterwards, sub-pixel location is still denoted as q (x, y) for the gray value at (x, y) in the image of the sub-pixel obtained, obtained sub- picture
Sub-pixel location still remembers p (i, j) for the gray value at (i, j) in the subgraph of plain grade.
Continue adaptive translation images to be recognized according to translation unit value, that is, continue to execute and translate the mistake while judging
Journey, (according to translation unit value adaptively translate in y-direction) until x+a ＞ A or y+b ＞ B (in the x direction according to
Unit value is translated adaptively translate), terminate translation motion.
S105：Select subgraph in translation motion with the minimum in all different angle value of images to be recognized, from each
The target minimum for meeting spacing pixel condition is chosen between minimum, target in images to be recognized is calculated according to each target minimum
The position of image block and number.
Spacing pixel condition can be following any one or combination：
Between each minimum, there are the number of pixels of the lateral separation between two or more adjacent minimums
Less than b；Between each minimum, the number of pixels there are the fore-and-aft distance between two or more adjacent minimums is small
In a；Wherein, the image size of subgraph is a × b (a ＜ A, b ＜ B), and the image size of images to be recognized is A × B.
Meeting the target minimum of spacing pixel condition from selection between each minimum specifically may include：
Meet the first object minimum of spacing pixel condition from selection between each minimum；
Selection minimum value from each first object minimum, using as the target minimum in current region.
Calculating the position of target image block and number in images to be recognized according to each target minimum includes：
Obtain the corresponding matched position coordinate of each target minimum；
Calculating position of the respective objects image block in images to be recognized according to each matched position coordinate is
In formula, matched position coordinate is (x, y), and the image size of subgraph is a × b；
The number of each target minimum is counted, using the number as target image block in images to be recognized.
For example, if the number of pixels of lateral separation between two or more minimums close to each other be less than b or
The number of pixels of person's fore-and-aft distance is less than the pixel of the lateral separation between a or two or more minimums close to each other
Number is less than b and the number of pixels of fore-and-aft distance is less than a, then that f (x, y) of minimum in these minimums is taken to be used as current region
The minimum of lower distinctiveness ratio, these minimums f (x, y) and corresponding matched position (x, y) finally obtained.So target figure
Position as where block isThe number of these minimums is the number of target image block.
In technical solution provided in an embodiment of the present invention, phase of the subgraph in current location is calculated using dissimilarity function
Different angle value, then according to the different angle value of current location and the relation of presetted pixel rank transform key, adaptive switching
The pixel of image and images to be recognized identifies, coarse matching is carried out using the subgraph and images to be recognized of pixel scale, with this
Matching speed is improved, relatively fine and smooth matching is carried out using sub-pixel other subgraph and images to be recognized, is come with this true
Protect matching precision；Compared with the image matching algorithm of the prior art, there is higher matching efficiency, also ensure images match essence
Degree and robustness.
Based on above-described embodiment, present invention also provides another embodiments, refer to Fig. 2, and Fig. 2 is implemented for the present invention
The flow diagram of the recognition methods for another image block that example provides, the soldered ball position of such as flip-chip of the embodiment of the present invention
In identification field, it specifically may include herein below：
S201：It describes with the S101 in above-described embodiment consistent, just repeats no more herein.
S202：It calls subgraph in y-direction, images to be recognized is adaptively translated according to translation unit value.
That is (x, y)=(x, y+h).
S203：Judge x+a ＞ A；If so, perform S204；If it is not, then perform S205.
S204：Select subgraph in translation motion with the minimum in all different angle value of images to be recognized, from each
The target minimum for meeting spacing pixel condition is chosen between minimum, target in images to be recognized is calculated according to each target minimum
The position of image block and number.
S205：Judge y+b ＞ B；If so, y=y0, x=x+1, and return to S203；If it is not, then perform S206.
S206：Subgraph and images to be recognized are calculated in the different angle value of current location using dissimilarity function and are stored.
S207：Judge f (x, y) >=l δ；If so, perform S208；If it is not, then perform S209.
F (x, y) >=l δ are that the different angle value of current location is not less than pixel scale transform key.
S208：Judge whether subgraph and images to be recognized are pixel-level image；If so, retain subgraph and to be identified
Image；If it is not, the image of non-pixel scale to be then converted into the image of pixel scale, S202 is returned.
S209：Judge whether subgraph and images to be recognized are sub-pixel level image；If so, retain subgraph and wait to know
Other image；If it is not, the other image of non-sub-pixel then is converted into the other image of sub-pixel, and update subgraph after conversion
Image sizes values return to S202.
From the foregoing, it will be observed that translational velocity of the embodiment of the present invention by adaptive subgraph, of image is not only ensured
Matching efficiency with precision, also raising image.
The embodiment of the present invention provides corresponding realization device also directed to the recognition methods of image block, further such that described
Method has more practicability.The identification device of image block provided in an embodiment of the present invention is introduced below, it is described below
The identification device of image block can correspond reference with the recognition methods of above-described image block.
Referring to Fig. 3, Fig. 3 is the identification device of image block provided in an embodiment of the present invention under a kind of specific embodiment
Structure chart, the device may include：
Preprocessing module 301, for initializing the translational velocity value of subgraph, threshold coefficient, translating initial point, and according to
Pre-defined dissimilarity function calculates the different angle value of translation initial point.
Judgment module 302 during adaptively translating images to be recognized according to translational velocity value in subgraph, is sentenced
Whether the current location of disconnected subgraph meets preset condition；Subgraph is the target image block in images to be recognized.
Target image block determining module 303 for meeting preset condition when the current location for judging subgraph, selects subgraph
As, with the minimum in all different angle value of images to be recognized, meeting spacing picture from being chosen between each minimum in translation motion
The target minimum of plain condition calculates the position of target image block and number in images to be recognized according to each target minimum.
Different angle value computing module 304 then calculates subgraph and images to be recognized in current location using dissimilarity function
Different angle value and store.
The adaptive handover module 305 of pixel scale, if being converted for the different angle value of current location not less than pixel scale
Threshold value, the subgraph continuation for obtaining Pixel-level adaptively translate the images to be recognized of Pixel-level according to translational velocity value；It is if current
The different angle value of position is less than pixel scale transform key, and the subgraph of Pixel-level and images to be recognized are converted into sub-pixel
Image, and the image sizes values of subgraph after conversion are updated, the figure to be identified after conversion is adaptively translated according to translational velocity value
Picture；Pixel scale transform key is threshold coefficient and the product of best match effect average, and best match effect average is in phase
Under different degree function, the average that template matching algorithm calculates the best match effect of subgraph and images to be recognized is advanced with.
Optionally, in some embodiments of the present embodiment, the adaptive handover module 305 of pixel scale can be
The pixel of predetermined number is inserted between two adjacent original image vegetarian refreshments using cubic spline interpolation, by the son of Pixel-level
The images to be recognized of image and Pixel-level is converted into the module of sub-pixel level image.
Optionally, the preprocessing module 301 can be the module that dissimilarity function is following formula：
In formula, the image size of subgraph is a × b (a ＜ A, b ＜ B), and the image size of images to be recognized is A × B, f
When (x, y) is in (x, y) position for subgraph, the different angle value of subgraph and images to be recognized.
In a kind of specific embodiment, the judgment module 302 can be as x+a ＞ A, and performance objective image block determines
Operation in module 303；As x+a ＜ A, and y+b ＞ B, then y=y0, x=x+1 adaptively translates according to translational velocity value and waits to know
Other image；As x+a ＜ A, and y+b ＜ B, perform the operation in different angle value computing module 304；Wherein, the image of subgraph is big
Small is a × b (a ＜ A, b ＜ B), and the image size of images to be recognized is A × B, and the coordinate of subgraph current location is (x, y), is put down
Shifting initial point is (x0, y0) module.
In addition,
Optionally, the target image block determining module 303 can be that the spacing pixel condition is：Each minimum it
Between, the number of pixels there are the lateral separation between two or more adjacent minimums is less than b；And/or each minimum
Between value, the number of pixels there are the fore-and-aft distance between two or more adjacent minimums is less than a；Wherein, it is described
The image size of subgraph is a × b (a ＜ A, b ＜ B), and the image size of the images to be recognized is the module of A × B.
The target image block determining module 303 can also be to meet the spacing pixel condition from selection between each minimum
First object minimum；Selection minimum value from each first object minimum, using as the target minimum in current region
Module.
The target image block determining module 304 for example may also include：
Acquiring unit, for obtaining the corresponding matched position coordinate of each target minimum；
Computing unit, for calculating position of the respective objects image block in images to be recognized according to each matched position coordinate
ForIn formula, matched position coordinate is (x, y), and the image size of subgraph is a × b；
Computing unit, for counting the number of each target minimum, using as target image block in images to be recognized
Number.
In addition, the adaptive handover module 305 of pixel scale for example may also include：
Judging unit, for judging whether subgraph and images to be recognized are pixel-level image；
Conversion unit, for when judging that subgraph is not pixel-level image, then subgraph being converted into pixel-level image；When
It is not pixel-level image to judge images to be recognized, then images to be recognized is converted into pixel-level image；
Stick unit, for when judging that images to be recognized and subgraph are pixel-level image, then retaining images to be recognized
And subgraph；
Translation unit, for the subgraph of the subgraph after converting or reservation adaptively to be translated picture according to translational velocity value
The images to be recognized of plain grade.
The function of each function module of the identification device of described image block of the embodiment of the present invention can be implemented according to the above method
The recognition methods specific implementation of image block, specific implementation process are referred to the associated description of above method embodiment in example,
Details are not described herein again.
From the foregoing, it will be observed that the embodiment of the present invention calculates different angle value of the subgraph in current location using dissimilarity function, so
Afterwards according to the relation of the different angle value of current location and presetted pixel rank transform key, adaptive switching subgraph and wait to know
The pixel identification of other image is carried out coarse matching using the subgraph and images to be recognized of pixel scale, is matched with this to improve
Speed carries out relatively fine and smooth matching using the other subgraph of sub-pixel and images to be recognized, ensures matching precision with this；
Compared with the image matching algorithm of the prior art, there is higher matching efficiency, also ensure images match precision and robust
Property.
The embodiment of the present invention additionally provides a kind of identification equipment of image block, specifically may include：
Memory, for storing the computer program of image recognition；
Processor, for performing computer program to realize the as above recognition methods of any one embodiment described image block
Step.
The function of each function module of the identification equipment of described image block of the embodiment of the present invention can be implemented according to the above method
Method specific implementation in example, specific implementation process are referred to the associated description of above method embodiment, no longer superfluous herein
It states.
From the foregoing, it will be observed that the embodiment of the present invention not only ensures the matched high-precision of image block, it is matched also to shorten image block
Time, so as to promote the efficiency of images match identification.
The embodiment of the present invention additionally provides a kind of computer readable storage medium, is stored with the recognizer of image block, institute
The step of stating when the recognizer of image block is executed by processor the as above recognition methods of any one embodiment described image block.
The function of each function module of computer readable storage medium described in the embodiment of the present invention can be real according to the above method
The method specific implementation in example is applied, specific implementation process is referred to the associated description of above method embodiment, herein no longer
It repeats.
From the foregoing, it will be observed that the embodiment of the present invention not only ensures the matched high-precision of image block, it is matched also to shorten image block
Time, so as to promote the efficiency of images match identification.
The embodiment of the present invention finally additionally provides a kind of soldered ball position-recognizing system of flip-chip, including flip-chip and
Processor, processor are realized when being used to perform the recognizer of the image block stored in memory such as the knowledge of any one preceding image block
The embodiment of other method；Wherein, subgraph is soldered ball image, and images to be recognized is flip-chip image, and target image block is to treat
Identify the soldered ball region in image.
The function of each function module of the soldered ball position-recognizing system of flip-chip described in the embodiment of the present invention can be according to upper
The method specific implementation in embodiment of the method is stated, specific implementation process is referred to the associated description of above method embodiment,
Details are not described herein again.
From the foregoing, it will be observed that the embodiment of the present invention not only ensures the high-precision of soldered ball position identification, the knowledge of soldered ball position is also shortened
Other time, so as to promote the efficiency of images match identification.
Each embodiment is described by the way of progressive in this specification, the highlights of each of the examples are with it is other
The difference of embodiment, just to refer each other for same or similar part between each embodiment.For dress disclosed in embodiment
For putting, since it is corresponded to the methods disclosed in the examples, so description is fairly simple, related part is referring to method part
Explanation.
Professional further appreciates that, with reference to each exemplary unit of the embodiments described herein description
And algorithm steps, can be realized with the combination of electronic hardware, computer software or the two, in order to clearly demonstrate hardware and
The interchangeability of software generally describes each exemplary composition and step according to function in the above description.These
Function is performed actually with hardware or software mode, specific application and design constraint depending on technical solution.Specialty
Technical staff can realize described function to each specific application using distinct methods, but this realization should not
Think beyond the scope of this invention.
It can directly be held with reference to the step of method or algorithm that the embodiments described herein describes with hardware, processor
The combination of capable software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
The soldered ball position of a kind of recognition methods of image block provided by the present invention, device and flip-chip is identified above
System is described in detail.Specific case used herein is set forth the principle of the present invention and embodiment, with
The explanation of upper embodiment is only intended to help the method and its core concept for understanding the present invention.It should be pointed out that it is led for this technology
For the those of ordinary skill in domain, without departing from the principle of the present invention, can also to the present invention carry out it is several improvement and
Modification, these improvement and modification are also fallen into the protection domain of the claims in the present invention.
Claims (10)
1. a kind of recognition methods of image block, which is characterized in that including：
The translational velocity value of initialization subgraph, threshold coefficient, translation initial point, and according to pre-defined dissimilarity function meter
Calculate the different angle value of the translation initial point；
During the subgraph adaptively translates images to be recognized according to the translational velocity value, the subgraph is judged
Current location whether meet preset condition；
If so, select the subgraph in translation motion with it is minimum in all different angle value of the images to be recognized
Value meets the target minimum of spacing pixel condition from selection between each minimum, waits to know according to calculating each target minimum
The position of target image block and number in other image；
If it is not, then the distinctiveness ratio of the subgraph and the images to be recognized in current location is calculated using the dissimilarity function
It is worth and stores；
If the different angle value of current location is not less than pixel scale transform key, the subgraph for obtaining Pixel-level continues according to described
Translational velocity value adaptively translates the images to be recognized of Pixel-level；If the different angle value of current location, which is less than pixel scale, converts threshold
Value, the subgraph of Pixel-level and images to be recognized are converted into sub-pixel level image, and update conversion after subgraph image it is big
Small value adaptively translates the images to be recognized after conversion according to the translational velocity value；
Wherein, the subgraph is the target image block in the images to be recognized, and the pixel scale transform key is described
The product of threshold coefficient and best match effect average, the best match effect average are under the dissimilarity function, in advance
The average of the best match effect of the subgraph and the images to be recognized is calculated first with template matching algorithm.
2. the recognition methods of image block according to claim 1, which is characterized in that the dissimilarity function is：
<mrow>
<mi>f</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mo>-</mo>
<mfrac>
<mn>1</mn>
<mrow>
<mi>a</mi>
<mi>b</mi>
</mrow>
</mfrac>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>b</mi>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>a</mi>
</munderover>
<mo>&lsqb;</mo>
<mi>p</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
<mi>ln</mi>
<mi> </mi>
<mi>q</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>+</mo>
<mi>i</mi>
<mo>,</mo>
<mi>y</mi>
<mo>+</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>-</mo>
<mi>p</mi>
<mo>(</mo>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mi>l</mi>
<mi>n</mi>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>-</mo>
<mi>q</mi>
<mo>(</mo>
<mrow>
<mi>x</mi>
<mo>+</mo>
<mi>i</mi>
<mo>,</mo>
<mi>y</mi>
<mo>+</mo>
<mi>j</mi>
</mrow>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mo>&rsqb;</mo>
<mo>;</mo>
</mrow>
In formula, the image size of the subgraph isThe image size of the images to be recognized for A ×
When B, f (x, y) are in (x, y) position for the subgraph, the subgraph and the different angle value of the images to be recognized.
3. the recognition methods of image block according to claim 1, which is characterized in that the subgraph by Pixel-level and treat
Identification image, which is converted into sub-pixel level image, to be included：
The pixel of predetermined number is inserted between two adjacent original image vegetarian refreshments using cubic spline interpolation, by Pixel-level
Subgraph and the images to be recognized of Pixel-level be converted into sub-pixel level image.
4. the recognition methods of the image block according to claims 1 to 3 any one, which is characterized in that described in the judgement
Whether subgraph meets preset condition in the position of the images to be recognized：
WhenIf perform subsequent operation；
WhenAndThen y=y0, x=x+1, according to the translational velocity value adaptively translation described in wait to know
Other image；
WhenAndIt performs and subsequent operates if not；
Wherein, the image size of the subgraph isThe image size of the images to be recognized for A ×
B, the coordinate of the subgraph current location is (x, y), and the translation initial point is (x0, y0)。
5. the recognition methods of the image block according to claims 1 to 3 any one, which is characterized in that the spacing pixel
Condition is：
Between each minimum, the number of pixels there are the lateral separation between two or more adjacent minimums is less than
b；And/or
Between each minimum, the number of pixels there are the fore-and-aft distance between two or more adjacent minimums is less than
a；
Wherein, the image size of the subgraph isThe image size of the images to be recognized for A ×
B。
6. the recognition methods of image block according to claim 5, which is characterized in that described to meet from selection between each minimum
The target minimum of spacing pixel condition includes：
Meet the first object minimum of the spacing pixel condition from selection between each minimum；
Selection minimum value from each first object minimum, using as the target minimum in current region.
7. the recognition methods of the image block according to claims 1 to 3 any one, which is characterized in that described according to each mesh
Mark minimum, which calculates the position of target image block and number in the images to be recognized, to be included：
Obtain the corresponding matched position coordinate of each target minimum；
Calculating position of the respective objects image block in the images to be recognized according to each matched position coordinate is
In formula, matched position coordinate is (x, y), and the image size of the subgraph is a × b；
The number of each target minimum is counted, using the number as target image block in the images to be recognized.
8. the recognition methods of image block according to claim 7, which is characterized in that it is described obtain Pixel-level subgraph after
The continuous images to be recognized for adaptively translating Pixel-level according to the translational velocity value includes：
Judge whether the subgraph and the images to be recognized are pixel-level image；
When judging that the subgraph is not pixel-level image, then the subgraph is converted into pixel-level image；
When judging that the images to be recognized is not pixel-level image, then the images to be recognized is converted into pixel-level image；
When judging that the images to be recognized and the subgraph are pixel-level image, then retain the images to be recognized and described
Subgraph；
Subgraph after conversion or the subgraph of reservation are adaptively translated into the to be identified of Pixel-level according to the translational velocity value
Image.
9. a kind of identification device of image block, which is characterized in that including：
Preprocessing module, for initializing the translational velocity value of subgraph, threshold coefficient, translation initial point, and according to fixed in advance
The dissimilarity function of justice calculates the different angle value of the translation initial point；
Judgment module, during adaptively translating images to be recognized according to the translational velocity value in the subgraph,
Judge whether the current location of the subgraph meets preset condition；The subgraph is the target figure in the images to be recognized
As block；
Target image block determining module for meeting preset condition when the current location for judging the subgraph, selects the son
Image, with the minimum in all different angle value of the images to be recognized, meets in translation motion from being chosen between each minimum
The target minimum of spacing pixel condition calculates the position of target image block in the images to be recognized according to each target minimum
And number；
Different angle value computing module then calculates the subgraph and the images to be recognized current using the dissimilarity function
The different angle value of position simultaneously stores；
The adaptive handover module of pixel scale if being not less than pixel scale transform key for the different angle value of current location, obtains
The subgraph of Pixel-level is taken to continue adaptively to translate the images to be recognized of Pixel-level according to the translational velocity value；If current location
Different angle value be less than pixel scale transform key, the subgraph of Pixel-level and images to be recognized are converted into sub-pixel figure
Picture, and the image sizes values of subgraph after conversion are updated, it is adaptively translated according to the translational velocity value to be identified after conversion
Image；The pixel scale transform key is the product of the threshold coefficient and best match effect average, the best match
Effect average is under the dissimilarity function, advances with template matching algorithm and calculates the subgraph and the figure to be identified
The average of the best match effect of picture.
10. a kind of soldered ball position-recognizing system of flip-chip, which is characterized in that including flip-chip and processor, the place
It is realized when reason device is for performing the image recognition program stored in memory such as any one of claim 1 to 8 described image block
Recognition methods the step of；Wherein, the subgraph is soldered ball image, and the images to be recognized is flip-chip image, described
Target image block is the soldered ball region in the images to be recognized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810023180.3A CN108122230B (en) | 2018-01-10 | 2018-01-10 | Image block identification method and device and solder ball position identification system of flip chip |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810023180.3A CN108122230B (en) | 2018-01-10 | 2018-01-10 | Image block identification method and device and solder ball position identification system of flip chip |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108122230A true CN108122230A (en) | 2018-06-05 |
| CN108122230B CN108122230B (en) | 2022-06-24 |
Family
ID=62232889
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810023180.3A Expired - Fee Related CN108122230B (en) | 2018-01-10 | 2018-01-10 | Image block identification method and device and solder ball position identification system of flip chip |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108122230B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112200864A (en) * | 2019-07-08 | 2021-01-08 | 深圳中科飞测科技有限公司 | Image processing method, positioning method, device, equipment and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101901334A (en) * | 2009-05-31 | 2010-12-01 | 汉王科技股份有限公司 | Static object detection method |
| CN101996398A (en) * | 2009-08-12 | 2011-03-30 | 睿励科学仪器（上海）有限公司 | Image matching method and equipment for wafer alignment |
| US8457411B2 (en) * | 2009-03-30 | 2013-06-04 | Carl Zeiss Sms Gmbh | Method and device for determining the position of an edge of a marker structure with subpixel accuracy in an image, having a plurality of pixels, of the marker structure |
| CN104408722A (en) * | 2014-11-26 | 2015-03-11 | 南京工业大学 | Detection method for PCB visual positioning |
| CN105069790A (en) * | 2015-08-06 | 2015-11-18 | 潍坊学院 | Rapid imaging detection method for gear appearance defect |
| EP2958054A2 (en) * | 2014-06-18 | 2015-12-23 | Mobileye Vision Technologies Ltd. | Hazard detection in a scene with moving shadows |
| WO2016076400A1 (en) * | 2014-11-13 | 2016-05-19 | オリンパス株式会社 | Calibration device, calibration method, optical device, imaging device, projection device, measurement system, and measurement method |
| CN105701492A (en) * | 2014-11-25 | 2016-06-22 | 宁波舜宇光电信息有限公司 | Machine vision identification system and implementation method thereof |
| US20160180188A1 (en) * | 2014-12-19 | 2016-06-23 | Beijing University Of Technology | Method for detecting salient region of stereoscopic image |
| CN105930858A (en) * | 2016-04-06 | 2016-09-07 | 吴晓军 | Fast high-precision geometric template matching method enabling rotation and scaling functions |
| CN106056586A (en) * | 2016-05-25 | 2016-10-26 | 湖南拓视觉信息技术有限公司 | Sub-pixel location method and sub-pixel location device |
| CN106600600A (en) * | 2016-12-26 | 2017-04-26 | 华南理工大学 | Wafer defect detection method based on characteristic matching |
| CN106778541A (en) * | 2016-11-28 | 2017-05-31 | 华中科技大学 | A kind of identification in the multilayer beam China and foreign countries beam hole of view-based access control model and localization method |
| US20170300778A1 (en) * | 2016-04-13 | 2017-10-19 | Sony Corporation | Object tracking device and method |
-
2018
- 2018-01-10 CN CN201810023180.3A patent/CN108122230B/en not_active Expired - Fee Related
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8457411B2 (en) * | 2009-03-30 | 2013-06-04 | Carl Zeiss Sms Gmbh | Method and device for determining the position of an edge of a marker structure with subpixel accuracy in an image, having a plurality of pixels, of the marker structure |
| CN101901334A (en) * | 2009-05-31 | 2010-12-01 | 汉王科技股份有限公司 | Static object detection method |
| CN101996398A (en) * | 2009-08-12 | 2011-03-30 | 睿励科学仪器（上海）有限公司 | Image matching method and equipment for wafer alignment |
| EP2958054A2 (en) * | 2014-06-18 | 2015-12-23 | Mobileye Vision Technologies Ltd. | Hazard detection in a scene with moving shadows |
| WO2016076400A1 (en) * | 2014-11-13 | 2016-05-19 | オリンパス株式会社 | Calibration device, calibration method, optical device, imaging device, projection device, measurement system, and measurement method |
| CN105701492A (en) * | 2014-11-25 | 2016-06-22 | 宁波舜宇光电信息有限公司 | Machine vision identification system and implementation method thereof |
| CN104408722A (en) * | 2014-11-26 | 2015-03-11 | 南京工业大学 | Detection method for PCB visual positioning |
| US20160180188A1 (en) * | 2014-12-19 | 2016-06-23 | Beijing University Of Technology | Method for detecting salient region of stereoscopic image |
| CN105069790A (en) * | 2015-08-06 | 2015-11-18 | 潍坊学院 | Rapid imaging detection method for gear appearance defect |
| CN105930858A (en) * | 2016-04-06 | 2016-09-07 | 吴晓军 | Fast high-precision geometric template matching method enabling rotation and scaling functions |
| US20170300778A1 (en) * | 2016-04-13 | 2017-10-19 | Sony Corporation | Object tracking device and method |
| CN106056586A (en) * | 2016-05-25 | 2016-10-26 | 湖南拓视觉信息技术有限公司 | Sub-pixel location method and sub-pixel location device |
| CN106778541A (en) * | 2016-11-28 | 2017-05-31 | 华中科技大学 | A kind of identification in the multilayer beam China and foreign countries beam hole of view-based access control model and localization method |
| CN106600600A (en) * | 2016-12-26 | 2017-04-26 | 华南理工大学 | Wafer defect detection method based on characteristic matching |
Non-Patent Citations (10)
| Title |
|---|
| CHEN Y L 等: "" Auto-tracking single point diamond cutting on non-planar brittle material substrates by a high-rigidity force controlled fast tool servo"", 《PRECISION ENGINEERING》 * |
| GUANGJUN ZHANG等: ""Novel template matching method with sub-pixel accuracy based on correlation and Fourier-Mellin transform"", 《OPTICAL ENGINEERING》 * |
| RTYGBWWWERR: "交叉熵（Cross-Entropy）", 《HTTPS://BLOG.CSDN.NET/RTYGBWWWERR/ARTICLE/DETAILS/50778098?OPS_REQUEST_MISC=&REQUEST_ID=&BIZ_ID=102&UTM_TERM=%E4%BA%A4%E5%8F%89%E7%86%B5&UTM_MEDIUM=DISTRIBUTE.PC_SEARCH_RESULT.NONE-TASK-BLOG-2~ALL~SOBAIDUWEB~DEFAULT-7-50778098.FIRST_RANK_V2_PC_RANK_ * |
| 吴晓: "LED 芯片粗精定位系统", 《红外与激光工程》 * |
| 尹红敏: ""基于机器视觉的齿轮检测与测量系统的研究"", 《中国优秀硕士学位论文全文数据库 (工程科技Ⅰ辑)》 * |
| 曾友 等: ""PCB基准点的探针式鲁棒定位方法"", 《组合机床与自动化加工技术》 * |
| 梅鸿翔: ""一种基于图像坐标检测的目标定位方法"", 《计算机与数字工程》 * |
| 王履程 等: "《 多媒体通信技术》", 31 January 2011 * |
| 窦兆玉 等: ""基于机器视觉的液晶屏幕坏点检测"", 《北京信息科技大学学报(自然科学版) 网络首发》 * |
| 胡小唐 等编著: "《微纳检测技术》", 31 October 2009, 天津大学出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112200864A (en) * | 2019-07-08 | 2021-01-08 | 深圳中科飞测科技有限公司 | Image processing method, positioning method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108122230B (en) | 2022-06-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5969460B2 (en) | Nail region detection method, program, storage medium, and nail region detection device | |
| CN107633526B (en) | Image tracking point acquisition method and device and storage medium | |
| CN110838126B (en) | Cell image segmentation method, cell image segmentation device, computer equipment and storage medium | |
| CN104657936B (en) | Method and electronic installation for percentage regulation value | |
| KR101881243B1 (en) | Method and apparatus for processing a depth image | |
| CN108629343B (en) | License plate positioning method and system based on edge detection and improved Harris corner detection | |
| CN107818290B (en) | Heuristic finger detection method based on depth map | |
| CN109903331A (en) | A kind of convolutional neural networks object detection method based on RGB-D camera | |
| CN103903280B (en) | Subblock weight Mean-Shift tracking method with improved level set target extraction | |
| CN104504723B (en) | Image registration method based on remarkable visual features | |
| CN108010123A (en) | A kind of three-dimensional point cloud acquisition methods for retaining topology information | |
| CN107679512A (en) | A kind of dynamic gesture identification method based on gesture key point | |
| CN105335952B (en) | Matching power flow computational methods and device and parallax value calculating method and equipment | |
| CN106875359B (en) | A kind of sample block image repair method based on layering boot policy | |
| CN109977831A (en) | A kind of knob recognition methods based on Digital Image Processing | |
| CN112734747B (en) | Target detection method and device, electronic equipment and storage medium | |
| CN108229500A (en) | A kind of SIFT Mismatching point scalping methods based on Function Fitting | |
| CN109033989A (en) | Target identification method, device and storage medium based on three-dimensional point cloud | |
| CN109492576A (en) | Image-recognizing method, device and electronic equipment | |
| CN107369176A (en) | A kind of flexible IC substrates oxidation area detection system and method | |
| CN112712860B (en) | Grain finite element model modeling method based on real metallographic structure | |
| CN108257174A (en) | Image block matching method and soldered ball position-recognizing system based on sub-pixel level image | |
| CN108122230A (en) | The soldered ball position-recognizing system of the recognition methods of image block, device and flip-chip | |
| CN102509072A (en) | Method for detecting salient object in image based on inter-area difference | |
| CN113435266A (en) | FCOS intelligent target detection method based on extreme point feature enhancement |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220624 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |