CN108122230B - Image block identification method and device and solder ball position identification system of flip chip - Google Patents
Image block identification method and device and solder ball position identification system of flip chip Download PDFInfo
- Publication number
- CN108122230B CN108122230B CN201810023180.3A CN201810023180A CN108122230B CN 108122230 B CN108122230 B CN 108122230B CN 201810023180 A CN201810023180 A CN 201810023180A CN 108122230 B CN108122230 B CN 108122230B
- Authority
- CN
- China
- Prior art keywords
- image
- sub
- value
- recognized
- pixel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 84
- 229910000679 solder Inorganic materials 0.000 title claims abstract description 29
- 238000013519 translation Methods 0.000 claims abstract description 101
- 230000008569 process Effects 0.000 claims abstract description 32
- 238000006243 chemical reaction Methods 0.000 claims abstract description 24
- 230000006870 function Effects 0.000 claims description 34
- 230000000694 effects Effects 0.000 claims description 22
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 description 12
- 238000005516 engineering process Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 3
- 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
- 238000010586 diagram Methods 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
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000000919 ceramic Substances 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000001125 extrusion Methods 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 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
- 230000010354 integration Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000004806 packaging method and process Methods 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
Images
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
Abstract
The embodiment of the invention discloses an image block identification method and device and a solder ball position identification system of a flip chip. The method comprises the steps of matching a translation initial point and an initialization parameter in advance; judging whether the current position of the subimage meets a preset condition or not in the process of adaptively translating the subimage to be recognized according to the translation speed value; if so, selecting minimum values of all dissimilarity values of the sub-images in the translation process, selecting target minimum values meeting the pixel spacing condition from the minimum values, and calculating the positions and the number of target image blocks in the image to be recognized; if not, calculating the dissimilarity value of the current position by using the dissimilarity function, if the dissimilarity value is not smaller than the pixel level conversion threshold value, acquiring a pixel level sub-image and continuing to translate the pixel level image to be recognized, otherwise, converting the pixel level image into a sub-pixel level image, updating the image size value of the converted sub-image, and adaptively translating the converted image to be recognized. The image block matching efficiency is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of image processing, in particular to an image block identification method and device and a solder ball position identification system of a flip chip.
Background
With the rapid development of computer technology, image processing technology has also been rapidly developed. In the field of image processing technology, a template matching algorithm uses an image as a template, which has almost the same shape as a target object in the image and has almost the same pixel value distribution by design. In the matching process, a translation pass is performed on the image by the template in units of distance of one pixel, and then a series of values of similarity or dissimilarity is obtained. When the similarity is maximum or the dissimilarity is minimum, the best matching effect is achieved, and the center of the position of the template in the image is the center of the position of the specific object in the image, namely the specific object in the image is identified.
For example, in the field of semiconductor chip manufacturing, the flip chip technology has become a favorite in the field of chip manufacturing because it solves the problems of intolerance of external force extrusion and low reliability caused by the fact that the electrical connection of the normal chip is realized through gold wires. The flip chip is formed by depositing tin lead balls on an I/O board, then turning and heating the chip, and combining the chip with a ceramic substrate by utilizing the molten tin lead balls, so that the positions of solder balls in the flip chip can be accurately positioned, and the flip chip is very necessary for subsequent packaging and other treatment of the chip.
In the process of identifying the solder balls of the flip chip, various sensors can be adopted for measurement in the prior art, but the installation of the sensors limits the improvement of the integration level of the whole equipment, and when microscopic vision is adopted for manual identification, the time is too long, and the identification efficiency is low. In addition, when some image matching methods are adopted, more matching time is needed, the matching efficiency is low, and the solder ball identification efficiency is low.
In view of this, how to shorten the time for image block matching, thereby improving the efficiency of image matching identification, is an urgent problem to be solved by those skilled in the art.
Disclosure of Invention
The embodiment of the invention aims to provide an image block identification method, an image block identification device and a flip chip solder ball position identification system, which not only ensure the high precision of image block matching, but also shorten the time of image block matching, thereby improving the efficiency of image matching identification.
In order to solve the above technical problems, embodiments of the present invention provide the following technical solutions:
an embodiment of the present invention provides a method for identifying an image block, including:
initializing a translation speed value, a threshold coefficient and a translation initial point of the sub-image, and calculating a dissimilarity value of the translation initial point according to a predefined dissimilarity function;
judging whether the current position of the subimage meets a preset condition or not in the process of adaptively translating the subimage to be recognized according to the translation speed value;
if so, selecting minimum values of all dissimilarity values of the sub-images and the image to be recognized in the translation process, selecting target minimum values meeting the pixel spacing condition from the minimum values, and calculating the position and the number of target image blocks in the image to be recognized according to the target minimum values;
if not, calculating the dissimilarity value of the sub-image and the image to be recognized at the current position by using the dissimilarity function and storing the dissimilarity value;
if the dissimilarity value of the current position is not smaller than the pixel level conversion threshold value, acquiring a sub-image of a pixel level, and continuing to adaptively translate the image to be identified of the pixel level according to the translation speed value; if the dissimilarity value of the current position is smaller than the pixel level conversion threshold value, converting the pixel level sub-image and the image to be recognized into a sub-pixel level image, updating the image size value of the converted sub-image, and adaptively translating the converted image to be recognized according to the translation speed value;
the sub-image is a target image block in the image to be recognized, the pixel level conversion threshold is the product of the threshold coefficient and the best matching effect mean value, and the best matching effect mean value is the mean value of the best matching effect of the sub-image and the image to be recognized calculated by utilizing a template matching algorithm in advance under the dissimilarity function.
Optionally, the dissimilarity function is:
in the formula, the image size of the sub-image is a × B (a is less than a, B is less than B), the image size of the image to be recognized is a × B, and f (x, y) is a dissimilarity value between the sub-image and the image to be recognized when the sub-image is at the (x, y) position.
Optionally, the converting the sub-image at the pixel level and the image to be recognized into the sub-pixel level image includes:
and inserting a preset number of pixel points between two adjacent original pixel points by utilizing cubic spline interpolation so as to convert the pixel-level sub-image and the pixel-level image to be identified into a sub-pixel-level image.
Optionally, the step of judging whether the position of the sub-image in the image to be recognized meets a preset condition is as follows:
when x + a is larger than A, executing subsequent yes operation;
when x + a < A and y + B > B, then y ═ y0When x is x +1, the image to be identified is translated in a self-adaptive mode according to the translation speed value;
when x + a is less than A and y + B is less than B, executing subsequent operation if not;
the image size of the sub-image is a multiplied by B (a is less than A, B is less than B), the image size of the image to be identified is A multiplied by B, the coordinates of the current position of the sub-image are (x, y), and the translation initial point is (x0，y0)。
Optionally, the pitch pixel condition is:
between each minimum value, the number of pixels with the transverse distance between two or more adjacent minimum values is less than b; and/or
Between each minimum value, the number of pixels with the longitudinal distance between two or more adjacent minimum values is less than a;
the image size of the sub-image is a multiplied by B (a is less than A, B is less than B), and the image size of the image to be recognized is A multiplied by B.
Optionally, the selecting a target minimum value satisfying the pixel pitch condition from among the minimum values includes:
selecting a first target minimum value meeting the pixel spacing condition from all minimum values;
and selecting the minimum value from the first target minimum values as the target minimum value in the current area.
Optionally, the calculating the positions and the numbers of the target image blocks in the image to be recognized according to the target minimum values includes:
acquiring matching position coordinates corresponding to the minimum values of the targets;
calculating the position of the corresponding target image block in the image to be identified according to the coordinates of each matched position
In the formula, the coordinate of the matching position is (x, y), and the image size of the sub-image is a multiplied by b;
and counting the number of the minimum values of each target to be used as the number of the target image blocks in the image to be recognized.
Optionally, the obtaining of the sub-image at the pixel level and continuing to adaptively translate the image to be identified at the pixel level according to the translation speed value includes:
judging whether the sub-image and the image to be recognized are pixel-level images or not;
when the sub-image is judged not to be the pixel level image, converting the sub-image into the pixel level image;
when the image to be recognized is judged not to be a pixel-level image, converting the image to be recognized into the pixel-level image;
when the image to be recognized and the sub-image are judged to be pixel-level images, reserving the image to be recognized and the sub-image;
and the converted sub-image or the reserved sub-image is adaptively translated into the image to be identified at the pixel level according to the translation speed value.
Another aspect of an embodiment of the present invention provides an apparatus for identifying an image block, including:
the preprocessing module is used for initializing a translation speed value, a threshold coefficient and a translation initial point of the sub-image and calculating a dissimilarity value of the translation initial point according to a predefined dissimilarity function;
the judging module is used for judging whether the current position of the subimage meets a preset condition or not in the process of adaptively translating the subimage to be recognized according to the translation speed value; the sub-images are target image blocks in the image to be recognized;
the target image block determining module is used for selecting minimum values of all dissimilarity values of the subimages and the image to be recognized in the translation process when the current positions of the subimages meet the preset conditions, selecting target minimum values meeting the space pixel conditions from all the minimum values, and calculating the positions and the number of the target image blocks in the image to be recognized according to all the target minimum values;
the dissimilarity value calculation module is used for calculating and storing dissimilarity values of the sub-images and the images to be recognized at the current positions by utilizing the dissimilarity function;
the pixel level self-adaptive switching module is used for acquiring a sub-image of a pixel level and continuing to self-adaptively translate the image to be identified of the pixel level according to the translation speed value if the dissimilarity value of the current position is not smaller than the pixel level conversion threshold; if the dissimilarity value of the current position is smaller than the pixel level conversion threshold value, converting the pixel level sub-image and the image to be recognized into a sub-pixel level image, updating the image size value of the converted sub-image, and adaptively translating the converted image to be recognized according to the translation speed value; the pixel level conversion threshold is the product of the threshold coefficient and the best matching effect mean value, and the best matching effect mean value is the mean value of the best matching effect of the sub-image and the image to be identified calculated by utilizing a template matching algorithm in advance under the dissimilarity function.
The embodiment of the invention finally provides a flip chip solder ball position identification system, which comprises a flip chip and a processor, wherein the processor is used for realizing the step of the image block identification method when executing the image block identification program stored in the memory; the subimages are solder ball images, the image to be identified is a flip chip image, and the target image block is a solder ball area in the image to be identified.
The embodiment of the invention provides an image block identification method, which comprises the steps of initializing a translation speed value, a threshold coefficient and a translation initial point of a sub-image, and calculating a dissimilarity value of the translation initial point according to a predefined dissimilarity function; judging whether the current position of the subimage meets a preset condition or not in the process of adaptively translating the subimage to be recognized according to the translation speed value; if so, selecting minimum values of all dissimilarity values of the subimages and the image to be recognized in the translation process, selecting target minimum values meeting the pixel spacing condition from the minimum values, and calculating the position and the number of target image blocks in the image to be recognized according to the target minimum values; if not, calculating the dissimilarity value of the sub-image and the image to be recognized at the current position by using the dissimilarity function and storing the dissimilarity value; if the dissimilarity value of the current position is not smaller than the pixel level conversion threshold value, acquiring a sub-image of the pixel level, and continuing to adaptively translate the image to be identified of the pixel level according to the translation speed value; if the dissimilarity value of the current position is smaller than the pixel level conversion threshold value, converting the pixel level sub-image and the image to be recognized into a sub-pixel level image, updating the image size value of the converted sub-image, and adaptively translating the converted image to be recognized according to the translation speed value.
The technical scheme provided by the application has the advantages that the dissimilarity value of the sub-image at the current position is calculated by utilizing the dissimilarity function, then the pixel recognition of the sub-image and the image to be recognized is switched in a self-adaptive manner according to the relationship between the dissimilarity value of the current position and the preset pixel level conversion threshold value, the rough matching is carried out by utilizing the sub-image at the pixel level and the image to be recognized, the matching speed is improved, and the relatively fine matching is carried out by utilizing the sub-image at the sub-pixel level and the image to be recognized, so that the matching precision is ensured; compared with the image matching algorithm in the prior art, the method has higher matching efficiency, and also ensures the image matching precision and robustness.
In addition, the embodiment of the invention also provides a corresponding realization device and a solder ball position identification system of the flip chip aiming at the image block identification method, so that the method has higher practicability, and the device and the solder ball position identification system of the flip chip have corresponding advantages.
Drawings
In order to more clearly illustrate the embodiments or technical solutions of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
Fig. 1 is a schematic flowchart of an image block identification method according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of another image block identification method according to an embodiment of the present invention;
fig. 3 is a structural diagram of an embodiment of an image block recognition apparatus according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the disclosure, the invention will be described in further detail with reference to the accompanying drawings and specific embodiments. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," "third," "fourth," and the like in the description and claims of this application and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements but may include other steps or elements not expressly listed.
Having described the technical solutions of the embodiments of the present invention, various non-limiting embodiments of the present application are described in detail below.
Referring to fig. 1, fig. 1 is a schematic flow chart of an image block identification method according to an embodiment of the present invention, where the embodiment of the present invention includes the following:
s101: initializing a translation speed value, a threshold coefficient and a translation initial point of the sub-image, and calculating a dissimilarity value of the translation initial point according to a predefined dissimilarity function.
The image size of the subimage is a x B (a < A, B < B), and the translation unit value h is equal to N+H e [1, b)), which is the translation speed of the sub-image for performing the adaptive translation in the image to be recognized, for example, when the value of the translation unit is 1, that is, the sub-image performs the adaptive translation on the image to be recognized with the distance unit of 1 pixel.
The pixel level translation threshold l δ is the product of the threshold coefficient l and the best match effect mean δ. The threshold coefficient l is any number which is not less than 1 and is preset, and the specific value is not limited in any way in the application. Delta is the average value of the optimal matching effect, and the average value of the optimal matching effect is the average value of the optimal matching effect of the subimages and the images to be recognized calculated under the dissimilarity function by utilizing the traditional template matching algorithm in advance. For example, for n sample pictures, the average value of the best matching effect of matching the sub-image and the image to be identified is calculated as the average value of the best matching effect by the traditional method of performing adaptive translation of the sub-image on the image to be identified by taking 1 pixel as a distance unit under the definition of the cross entropy measurement formula.
The translation initial point is a position pixel point at which the sub-image starts to translate on the image to be identified.
The dissimilarity function can be defined by using a distance metric formula, and the dissimilarity function after definition is:
in the formula, the image size of the sub-image is a × B (a < a, B < B), the image size of the image to be recognized is a × B, and f (x, y) is the dissimilarity value between the sub-image and the image to be recognized when the sub-image is at the (x, y) position.
The image size of the sub-image is a multiplied by B (a < A, B < B), and f (x, y) is the dissimilarity value of the sub-image and the image to be recognized when the sub-image is at the (x, y) position.
Of course, other defined dissimilarity functions may be used, and the present application does not limit this.
S102: and in the process of adaptively translating the image to be recognized according to the translation speed value of the subimage, judging whether the current position of the subimage meets a preset condition, if so, executing S105, and if not, executing S103.
The subimage is a target image block in the image to be recognized, that is, the subimage is an image of a specific object in the image to be recognized, that is, the image to be recognized includes the subimage, and an image area of the specific object is the target image block. And traversing the image to be recognized by utilizing the translation of the sub-image so as to obtain a target image block which is the same as the sub-image in the image to be recognized in a matching manner. For example, the sub-image is a solder ball image, the image to be recognized is a flip chip image, and the flip chip includes a plurality of solder balls, so that a plurality of areas exist in the flip chip image as the solder ball image, and the specific position of the solder ball image on the flip chip image can be determined by utilizing the translation and traversal of the sub-image on the flip chip, so that the position of the solder ball is recognized.
In the process of adaptively translating the image to be recognized according to the translation unit value of the subimage, the subimage can be adaptively translated in the y direction according to the translation unit value, also can be adaptively translated in the x direction according to the translation unit value, and can be adaptively translated in the y direction according to the translation unit value, when x + a is more than A, the subimage is described to have traversed the image to be recognized; when the adaptive translation is carried out according to the translation unit value in the x direction, when y + B is greater than B, the current sub-image is described to have traversed the image to be recognized.
Performing adaptive translation according to a translation unit value in the y direction, namely (x, y) ═ x, y + h; the specific process of judging whether the current position of the subimage meets the preset condition may be:
when x + a > A, executing S105;
when x + a < A and y + B > B, then y ═ y0When x is x +1, continuing to adaptively translate the image to be identified according to the current translation unit value;
when x + a is less than A and y + B is less than B, executing S103;
the image size of the sub-image is a × B (a < a, B < B), the image size of the image to be recognized is a × B, and the coordinates of the current position of the image are (x, y).
And y + B > B can be judged first, and then x + a > A can be judged, which does not influence the implementation of the application.
It should be noted that, when the sub-image is adaptively translated on the image to be recognized, each time a pixel point or an area passes through, it is necessary to determine whether the current position meets the condition, if not, adaptive translation is continued, and if so, the position of the target area is determined.
Performing adaptive translation according to a translation unit value in the x direction, namely (x, y) ═ x + h, y; the specific process of determining whether the current position of the sub-image meets the preset condition may refer to the above process, which is not described herein again.
S103: and calculating the dissimilarity value of the sub-image and the image to be recognized at the current position by using the dissimilarity function and storing the dissimilarity value.
S104: if the dissimilarity value of the current position is not smaller than the pixel level conversion threshold value, acquiring a sub-image of the pixel level, and continuing to adaptively translate the image to be identified of the pixel level according to the translation speed value; if the dissimilarity value of the current position is smaller than the pixel level conversion threshold value, converting the pixel level sub-image and the image to be recognized into a sub-pixel level image, updating the image size value of the converted sub-image, and adaptively translating the converted image to be recognized according to the translation speed value.
Obtaining the sub-image at the pixel level and continuing to adaptively translate the image to be identified at the pixel level according to the translation speed value may specifically include:
judging whether the sub-image and the image to be identified are pixel level images or not;
when the sub-image is judged not to be the pixel level image, converting the sub-image into the pixel level image;
when the image to be recognized is judged not to be the pixel-level image, converting the image to be recognized into the pixel-level image;
when the image to be recognized and the sub-image are judged to be pixel-level images, the image to be recognized and the sub-image are reserved;
and the converted sub-image or the reserved sub-image is adaptively translated into the image to be recognized at the pixel level according to the translation speed value.
Converting the sub-images at the pixel level and the image to be identified into the sub-pixel level image may specifically be:
judging whether the sub-images and the images to be identified are sub-pixel level images or not; when the sub-image is judged not to be in a sub-pixel level, converting the sub-image into a sub-pixel level image by utilizing cubic spline interpolation; and when the image to be recognized is judged not to be in the sub-pixel level, converting the image to be recognized into the sub-pixel level image by utilizing cubic spline interpolation.
Converting the subpixel level image using cubic spline interpolation may be:
and performing cubic spline interpolation on the gray value of the image, and converting the interpolation of the image at the pixel level into the sub-pixel level. In the interpolation process, a preset number of points are inserted between two adjacent original pixel points of the image to be recognized and the subimage. The number of insertion points can be customized according to the situation. The points used by the cubic spline interpolation are 4 continuous adjacent points in the original image. After the interpolation is finished, the gray value at the sub-pixel position (x, y) in the obtained sub-pixel level image is still recorded as q (x, y), and the gray value at the sub-pixel position (i, j) in the obtained sub-pixel level image is still recorded as p (i, j).
And (3) continuing to adaptively translate the image to be identified according to the translation unit value, namely, continuing to execute the translation and judgment process until x + a is greater than A (performing adaptive translation according to the translation unit value in the y direction) or y + B is greater than B (performing adaptive translation according to the translation unit value in the x direction), and ending the translation process.
S105: and selecting minimum values of all dissimilarity values of the subimages and the image to be recognized in the translation process, selecting target minimum values meeting the pixel spacing condition from the minimum values, and calculating the position and the number of target image blocks in the image to be recognized according to the target minimum values.
The pitch pixel condition may be any one or a combination of:
between each minimum value, the number of pixels with the transverse distance between two or more adjacent minimum values is less than b; between each minimum value, the number of pixels with the longitudinal distance between two or more adjacent minimum values is less than a; the image size of the sub-image is a multiplied by B (a is less than A, B is less than B), and the image size of the image to be recognized is A multiplied by B.
Selecting the target minimum value satisfying the pitch pixel condition from among the minimum values may specifically include:
selecting a first target minimum value satisfying the pixel spacing condition from all minimum values;
and selecting the minimum value from the first target minimum values as the target minimum value in the current area.
Calculating the positions and the number of target image blocks in the image to be recognized according to the target minimum values comprises the following steps:
acquiring matching position coordinates corresponding to the minimum values of the targets;
calculating the position of the corresponding target image block in the image to be identified according to the coordinates of each matched position
In the formula, the coordinate of the matching position is (x, y), and the image size of the sub-image is a × b;
and counting the number of the minimum values of each target to be used as the number of the target image blocks in the image to be identified.
For example, if the number of pixels in the lateral distance between two or more mutually close minimum values is less than b, or the number of pixels in the longitudinal distance is less than a, or the number of pixels in the lateral distance between two or more mutually close minimum values is less than b and the number of pixels in the longitudinal distance is less than a, the smallest one f (x, y) of the minimum values is taken as the minimum value of the dissimilarity degree in the current region, and the minimum values f (x, y) and the corresponding matching positions (x, y) are finally obtained. The target image block is located at the position
The number of the minimum values is the number of the target image blocks.
In the technical scheme provided by the embodiment of the invention, the dissimilarity value of the sub-image at the current position is calculated by utilizing a dissimilarity function, then the sub-image and the image to be recognized are subjected to pixel recognition in a self-adaptive mode according to the relationship between the dissimilarity value of the current position and a preset pixel level conversion threshold, the sub-image at the pixel level and the image to be recognized are subjected to rough matching so as to improve the matching speed, and the sub-image at the sub-pixel level and the image to be recognized are subjected to relatively fine matching so as to ensure the matching precision; compared with the image matching algorithm in the prior art, the method has higher matching efficiency, and also ensures the image matching precision and robustness.
Based on the foregoing embodiment, the present application further provides another embodiment, please refer to fig. 2, and fig. 2 is a schematic flowchart of another method for identifying an image block according to an embodiment of the present invention, which, for example, in the field of solder ball position identification of a flip chip, specifically includes the following steps:
s201: consistent with the description of S101 in the above embodiment, further description is omitted here.
S202: and calling the sub-image to adaptively translate the image to be recognized according to the translation unit value in the y direction.
That is, (x, y) ═ x, y + h.
S203: judging that x + a is more than A; if yes, executing S204; if not, go to S205.
S204: and selecting minimum values of all dissimilarity values of the subimages and the image to be recognized in the translation process, selecting target minimum values meeting the pixel spacing condition from the minimum values, and calculating the position and the number of target image blocks in the image to be recognized according to the target minimum values.
S205: judging that y + B is more than B; if so, y ═ y0X is x +1, and returns to S203; if not, go to S206.
S206: and calculating the dissimilarity value of the sub-image and the image to be recognized at the current position by using the dissimilarity function and storing the dissimilarity value.
S207: judging that f (x, y) is not less than l delta; if yes, go to step S208; if not, S209 is executed.
f (x, y) is not less than the pixel level conversion threshold value, wherein the delta is not less than the difference value of the current position.
S208: judging whether the sub-images and the images to be recognized are pixel-level images or not; if so, keeping the sub-image and the image to be identified; if not, the non-pixel level image is converted into a pixel level image, and the process returns to S202.
S209: judging whether the sub-images and the images to be identified are sub-pixel level images or not; if so, keeping the sub-image and the image to be identified; if not, converting the non-sub-pixel level image into a sub-pixel level image, updating the image size value of the converted sub-image, and returning to S202.
Therefore, the embodiment of the invention not only ensures the matching precision of the images, but also improves the matching efficiency of the images through the self-adaptive translation speed of the sub-images.
The embodiment of the invention also provides a corresponding implementation device for the image block identification method, so that the method has higher practicability. The following describes an image block recognition apparatus according to an embodiment of the present invention, and the image block recognition apparatus described below and the image block recognition method described above may be referred to correspondingly.
Referring to fig. 3, fig. 3 is a structural diagram of an image block identification apparatus according to an embodiment of the present invention in a specific implementation, where the apparatus may include:
the preprocessing module 301 is configured to initialize a translation velocity value, a threshold coefficient, and a translation initial point of the sub-image, and calculate a dissimilarity value of the translation initial point according to a predefined dissimilarity function.
The judging module 302 is configured to judge whether a current position of the subimage meets a preset condition in a process of adaptively translating the image to be recognized according to the translation speed value; the subimages are target image blocks in the image to be recognized.
And the target image block determining module 303 is configured to, when it is determined that the current position of the sub-image satisfies the preset condition, select a minimum value from all dissimilarity values of the sub-image and the image to be recognized during the translation process, select a target minimum value satisfying a pitch pixel condition from among the minimum values, and calculate the position and number of the target image blocks in the image to be recognized according to each target minimum value.
The dissimilarity value calculating module 304 calculates the dissimilarity values of the sub-image and the image to be recognized at the current position by using the dissimilarity function and stores the dissimilarity values.
A pixel level adaptive switching module 305, configured to, if the disparity value of the current position is not smaller than the pixel level conversion threshold, obtain a to-be-identified image in which the sub-image at the pixel level continues to adaptively translate the pixel level according to the translation speed value; if the dissimilarity value of the current position is smaller than the pixel level conversion threshold value, converting the pixel level sub-image and the image to be recognized into a sub-pixel level image, updating the image size value of the converted sub-image, and adaptively translating the converted image to be recognized according to the translation speed value; the pixel level conversion threshold is the product of a threshold coefficient and the best matching effect mean value, and the best matching effect mean value is the mean value of the best matching effect of the sub-image and the image to be identified, which is calculated in advance by using a template matching algorithm under the dissimilarity function.
Optionally, in some embodiments of this embodiment, the pixel-level adaptive switching module 305 may be a module that inserts a preset number of pixel points between two adjacent original pixel points by using cubic spline interpolation to convert both a sub-image at a pixel level and an image to be recognized at the pixel level into a sub-pixel-level image.
Optionally, the preprocessing module 301 may be a module with the dissimilarity function of the following formula:
in the formula, the image size of the sub-image is a × B (a < a, B < B), the image size of the image to be recognized is a × B, and f (x, y) is the dissimilarity value between the sub-image and the image to be recognized when the sub-image is at the (x, y) position.
In a specific embodiment, the determining module 302 may perform the operation in the target image block determining module 303 when x + a > a; when x + a < A and y + B > B, then y ═ y0When x is x +1, the image to be identified is translated in a self-adaptive mode according to the translation speed value; when x + a is less than A and y + B is less than B, executing the operation in the dissimilarity value calculation module 304; the image size of the sub-image is a multiplied by B (a is less than A, B is less than B), the image size of the image to be identified is A multiplied by B, the coordinates of the current position of the sub-image are (x, y), and the translation initial point is (x)0，y0) The module of (1).
In addition to this, the present invention is,
optionally, the target image block determining module 303 may condition the pixels of the pitch as follows: between each minimum value, the number of pixels with the transverse distance between two or more adjacent minimum values is less than b; and/or the number of pixels, between each minimum value, for which the longitudinal distance between two or more adjacent minimum values is less than a; and the image size of the sub-image is a multiplied by B (a is less than A, B is less than B), and the image size of the image to be recognized is A multiplied by B.
The target image block determining module 303 may further select a first target minimum value satisfying the pitch pixel condition from among the minimum values; and selecting the minimum value from the first target minimum values as a module of the target minimum values in the current area.
The target image block determination module 304 may further include, for example:
the acquisition unit is used for acquiring the matching position coordinates corresponding to the minimum values of the targets;
a calculating unit for calculating the position of the corresponding target image block in the image to be recognized according to the coordinates of each matched position
In the formula, the coordinate of the matching position is (x, y), and the image size of the sub-image is a × b;
and the calculating unit is used for counting the number of the minimum values of each target to be used as the number of the target image blocks in the image to be identified.
In addition, the pixel level adaptive switching module 305 may further include:
the judging unit is used for judging whether the sub-image and the image to be identified are pixel-level images or not;
the converting unit is used for converting the sub-image into the pixel level image when the sub-image is judged not to be the pixel level image; when the image to be recognized is judged not to be a pixel-level image, converting the image to be recognized into the pixel-level image;
the retention unit is used for retaining the image to be recognized and the sub-image when the image to be recognized and the sub-image are judged to be pixel-level images;
and the translation unit is used for adaptively translating the converted sub-image or the reserved sub-image into the image to be identified at the pixel level according to the translation speed value.
The functions of the functional modules of the image block identification apparatus according to the embodiment of the present invention may be specifically implemented according to the image block identification method in the above method embodiment, and the specific implementation process may refer to the related description of the above method embodiment, which is not described herein again.
As can be seen from the above, in the embodiment of the present invention, the dissimilarity value of the sub-image at the current position is calculated by using the dissimilarity function, then the pixel identification of the sub-image and the image to be identified is adaptively switched according to the relationship between the dissimilarity value at the current position and the preset pixel level conversion threshold, the coarse matching is performed by using the sub-image at the pixel level and the image to be identified, so as to improve the matching speed, and the relatively fine matching is performed by using the sub-image at the sub-pixel level and the image to be identified, so as to ensure the matching accuracy; compared with the image matching algorithm in the prior art, the method has higher matching efficiency, and also ensures the image matching precision and robustness.
The embodiment of the present invention further provides an image block identification device, which specifically includes:
a memory for storing a computer program for image block identification;
a processor for executing a computer program to implement the steps of the image block identification method according to any of the above embodiments.
The functions of the functional modules of the image block identification device according to the embodiments of the present invention may be specifically implemented according to the method in the foregoing method embodiments, and the specific implementation process may refer to the related description of the foregoing method embodiments, which is not described herein again.
Therefore, the embodiment of the invention not only ensures the high precision of image block matching, but also shortens the time of image block matching, thereby improving the efficiency of image matching identification.
The embodiment of the present invention further provides a computer-readable storage medium, in which an identification program of an image block is stored, where the identification program of the image block is executed by a processor, and the steps of the identification method of the image block are as described in any one of the above embodiments.
The functions of the functional modules of the computer-readable storage medium according to the embodiment of the present invention may be specifically implemented according to the method in the foregoing method embodiment, and the specific implementation process may refer to the related description of the foregoing method embodiment, which is not described herein again.
Therefore, the embodiment of the invention not only ensures the high precision of image block matching, but also shortens the time of image block matching, thereby improving the efficiency of image matching identification.
The embodiment of the invention finally provides a solder ball position identification system of the flip chip, which comprises the flip chip and a processor, wherein the processor is used for realizing the embodiment of the identification method of any image block when executing the identification program of the image block stored in the memory; the subimage is a solder ball image, the image to be identified is a flip chip image, and the target image block is a solder ball area in the image to be identified.
The functions of the functional modules of the solder ball position identification system of the flip chip according to the embodiment of the present invention can be specifically implemented according to the method in the embodiment of the method, and the specific implementation process may refer to the description related to the embodiment of the method, which is not described herein again.
Therefore, the embodiment of the invention not only ensures the high precision of the solder ball position identification, but also shortens the time of the solder ball position identification, thereby improving the efficiency of image matching identification.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The method and the device for identifying an image block and the system for identifying the position of the solder ball of the flip chip provided by the invention are described in detail above. The principles and embodiments of the present invention are explained herein using specific examples, which are presented only to assist in understanding the method and its core concepts. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Claims (9)
1. A method for recognizing an image block, comprising:
initializing a translation speed value, a threshold coefficient and a translation initial point of the sub-image, and calculating a dissimilarity value of the translation initial point according to a predefined dissimilarity function;
judging whether the current position of the subimage meets a preset condition or not in the process of adaptively translating the subimage to be recognized according to the translation speed value;
if so, selecting minimum values of all dissimilarity values of the sub-images and the image to be recognized in the translation process, selecting target minimum values meeting the pixel spacing condition from the minimum values, and calculating the position and the number of target image blocks in the image to be recognized according to the target minimum values;
if not, calculating the dissimilarity value of the sub-image and the image to be recognized at the current position by using the dissimilarity function and storing the dissimilarity value;
if the dissimilarity value of the current position is not smaller than the pixel level conversion threshold value, acquiring a sub-image of a pixel level, and continuing to adaptively translate the image to be identified of the pixel level according to the translation speed value; if the dissimilarity value of the current position is smaller than the pixel level conversion threshold value, converting the pixel level sub-image and the image to be recognized into a sub-pixel level image, updating the image size value of the converted sub-image, and adaptively translating the converted image to be recognized according to the translation speed value;
the sub-image is a target image block in the image to be recognized, the pixel level conversion threshold is the product of the threshold coefficient and the best matching effect mean value, and the best matching effect mean value is the mean value of the best matching effect of the sub-image and the image to be recognized calculated by utilizing a template matching algorithm in advance under the dissimilarity function; the judgment of whether the position of the sub-image in the image to be recognized meets the preset condition is as follows:
when x + a is larger than A, executing subsequent yes operation;
when x + a < A and y + B > B, then y ═ y0When x is x +1, the image to be identified is translated in a self-adaptive mode according to the translation speed value;
when x + a is less than A and y + B is less than B, executing subsequent operation if not;
the image size of the sub-image is a multiplied by B (a is less than A, B is less than B), the image size of the image to be identified is A multiplied by B, the coordinates of the current position of the sub-image are (x, y), and the translation initial point is (x0，y0)。
2. The image block identification method according to claim 1, wherein the dissimilarity function is:
in the formula, the image size of the sub-image is a × B (a is less than a, B is less than B), the image size of the image to be recognized is a × B, and f (x, y) is a dissimilarity value between the sub-image and the image to be recognized when the sub-image is at the (x, y) position.
3. The method for identifying image blocks according to claim 1, wherein said converting the sub-image at pixel level and the image to be identified into the sub-pixel level image comprises:
and inserting a preset number of pixel points between two adjacent original pixel points by utilizing cubic spline interpolation so as to convert the pixel-level sub-image and the pixel-level image to be identified into a sub-pixel-level image.
4. The image block identification method according to any of claims 1 to 3, wherein the pitch pixel condition is:
between each minimum value, the number of pixels with the transverse distance between two or more adjacent minimum values is less than b; and/or
Between each minimum value, the number of pixels with the longitudinal distance between two or more adjacent minimum values is less than a;
the image size of the sub-image is a multiplied by B (a is less than A, B is less than B), and the image size of the image to be recognized is A multiplied by B.
5. The method for identifying an image block according to claim 4, wherein said selecting the target minimum value satisfying the pitch pixel condition from among the minimum values comprises:
selecting a first target minimum value meeting the pixel spacing condition from all minimum values;
and selecting the minimum value from the first target minimum values as the target minimum value in the current area.
6. The image block identification method according to any one of claims 1 to 3, wherein said calculating the position and number of target image blocks in the image to be identified according to each target minimum value comprises:
acquiring matching position coordinates corresponding to the minimum values of the targets;
calculating the position of the corresponding target image block in the image to be identified according to the coordinates of each matched position
Wherein, the coordinate of the matching position is (x, y), and the image size of the sub-image is a multiplied by b;
and counting the number of the minimum values of each target to be used as the number of the target image blocks in the image to be recognized.
7. The method for identifying image blocks according to claim 6, wherein said obtaining of sub-images at pixel level to continue to adaptively translate images to be identified at pixel level according to the translation velocity value comprises:
judging whether the sub-image and the image to be identified are pixel-level images or not;
when the sub-image is judged not to be the pixel level image, converting the sub-image into the pixel level image;
when the image to be recognized is judged not to be a pixel-level image, converting the image to be recognized into the pixel-level image;
when the image to be recognized and the sub-image are judged to be pixel-level images, reserving the image to be recognized and the sub-image;
and the converted sub-image or the reserved sub-image is adaptively translated into the image to be identified at the pixel level according to the translation speed value.
8. An apparatus for recognizing an image block, comprising:
the preprocessing module is used for initializing a translation speed value, a threshold coefficient and a translation initial point of the sub-image and calculating a dissimilarity value of the translation initial point according to a predefined dissimilarity function;
the judging module is used for judging whether the current position of the subimage meets a preset condition or not in the process of adaptively translating the subimage to be recognized according to the translation speed value; the sub-images are target image blocks in the image to be recognized;
the target image block determining module is used for selecting minimum values of all dissimilarity values of the subimages and the image to be recognized in the translation process when the current positions of the subimages meet the preset conditions, selecting target minimum values meeting the space pixel conditions from all the minimum values, and calculating the positions and the number of the target image blocks in the image to be recognized according to all the target minimum values;
the dissimilarity value calculation module is used for calculating and storing dissimilarity values of the sub-images and the images to be recognized at the current positions by utilizing the dissimilarity function;
the pixel level self-adaptive switching module is used for acquiring a sub-image of a pixel level and continuing to self-adaptively translate the image to be identified of the pixel level according to the translation speed value if the dissimilarity value of the current position is not smaller than the pixel level conversion threshold; if the dissimilarity value of the current position is smaller than the pixel level conversion threshold value, converting the pixel level sub-image and the image to be recognized into a sub-pixel level image, updating the image size value of the converted sub-image, and self-adaptively translating the converted image to be recognized according to the translation speed value; the pixel level conversion threshold is the product of the threshold coefficient and the best matching effect mean value, and the best matching effect mean value is the mean value of the best matching effect of the sub-image and the image to be identified calculated by utilizing a template matching algorithm in advance under the dissimilarity function;
the determining module is further configured to:
when x + a is larger than A, executing subsequent yes operation;
when x + a < A, and y + B > B, then y ═ y0When the image to be identified is translated, the image to be identified is translated in a self-adaptive mode according to the translation speed value;
when x + a is less than A and y + B is less than B, executing subsequent operation if not;
the image size of the sub-image is a multiplied by B (a is less than A, B is less than B), the image size of the image to be identified is A multiplied by B, the coordinates of the current position of the sub-image are (x, y), and the translation initial point is (x0，y0)。
9. A flip-chip solder ball position recognition system comprising a flip chip and a processor for implementing the steps of the image block recognition method according to any one of claims 1 to 7 when executing an image block recognition program stored in a memory; the subimages are solder ball images, the image to be identified is a flip chip image, and the target image block is a solder ball area in the image to be identified.
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 CN108122230A (en) | 2018-06-05 |
| CN108122230B true 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) |
Citations (8)
| 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 |
| CN104408722A (en) * | 2014-11-26 | 2015-03-11 | 南京工业大学 | Detection method for PCB (printed circuit board) 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 |
| CN105930858A (en) * | 2016-04-06 | 2016-09-07 | 吴晓军 | Fast high-precision geometric template matching method enabling rotation and scaling functions |
| CN106600600A (en) * | 2016-12-26 | 2017-04-26 | 华南理工大学 | Wafer defect detection method based on characteristic matching |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101901334B (en) * | 2009-05-31 | 2013-09-11 | 汉王科技股份有限公司 | Static object detection method |
| CN101996398B (en) * | 2009-08-12 | 2012-07-04 | 睿励科学仪器（上海）有限公司 | Image matching method and equipment for wafer alignment |
| CN104463890B (en) * | 2014-12-19 | 2017-05-24 | 北京工业大学 | Stereoscopic image significance region detection method |
| CN107301651A (en) * | 2016-04-13 | 2017-10-27 | 索尼公司 | Object tracking apparatus and method |
| CN106056586B (en) * | 2016-05-25 | 2019-08-09 | 湖南拓视觉信息技术有限公司 | A kind of sub-pixel positioning method and device |
| CN106778541B (en) * | 2016-11-28 | 2019-08-13 | 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 |
-
2018
- 2018-01-10 CN CN201810023180.3A patent/CN108122230B/en not_active Expired - Fee Related
Patent Citations (8)
| 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 |
| 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 (printed circuit board) visual positioning |
| 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 |
| 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 (6)
| Title |
|---|
| " Auto-tracking single point diamond cutting on non-planar brittle material substrates by a high-rigidity force controlled fast tool servo";Chen Y L 等;《Precision Engineering》;20170731;第49卷;253-261 * |
| "Novel template matching method with sub-pixel accuracy based on correlation and Fourier-Mellin transform";Guangjun Zhang等;《Optical Engineering》;20090501;第48卷(第5期);1-8 * |
| "PCB基准点的探针式鲁棒定位方法";曾友 等;《组合机床与自动化加工技术》;20160620(第06期);30-34 * |
| "一种基于图像坐标检测的目标定位方法";梅鸿翔;《计算机与数字工程》;20160320;第44卷(第03期);438-444 * |
| "基于机器视觉的液晶屏幕坏点检测";窦兆玉 等;《北京信息科技大学学报(自然科学版) 网络首发》;20151030;1-5 * |
| "基于机器视觉的齿轮检测与测量系统的研究";尹红敏;《中国优秀硕士学位论文全文数据库 (工程科技Ⅰ辑)》;20170815(第（2017）08期);B022-281 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108122230A (en) | 2018-06-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6577565B2 (en) | Method and apparatus for depth image processing | |
| US10430951B2 (en) | Method and device for straight line detection and image processing | |
| CN109785291B (en) | Lane line self-adaptive detection method | |
| JP4516516B2 (en) | Person detection device, person detection method, and person detection program | |
| CN102970548B (en) | Image depth sensing device | |
| TWI489418B (en) | Parallax Estimation Depth Generation | |
| US8199202B2 (en) | Image processing device, storage medium storing image processing program, and image pickup apparatus | |
| CN108470356B (en) | Target object rapid ranging method based on binocular vision | |
| CN104182974B (en) | A speeded up method of executing image matching based on feature points | |
| US9406140B2 (en) | Method and apparatus for generating depth information | |
| CN102428497B (en) | Method and device for determining shape congruence in three dimensions | |
| CN111563908B (en) | Image processing method and related device | |
| CN108665495B (en) | Image processing method and device and mobile terminal | |
| CN108229500A (en) | A kind of SIFT Mismatching point scalping methods based on Function Fitting | |
| JP4649559B2 (en) | 3D object recognition apparatus, 3D object recognition program, and computer-readable recording medium on which the same is recorded | |
| CN109003307B (en) | Underwater binocular vision measurement-based fishing mesh size design method | |
| CN114693760A (en) | Image correction method, device and system and electronic equipment | |
| CN105320930A (en) | Object recognition apparatus | |
| CN116503462A (en) | Method and system for quickly extracting circle center of circular spot | |
| CN108122230B (en) | Image block identification method and device and solder ball position identification system of flip chip | |
| CN113034666B (en) | Stereo matching method based on pyramid parallax optimization cost calculation | |
| CN108257174A (en) | Image block matching method and soldered ball position-recognizing system based on sub-pixel level image | |
| CN115456945A (en) | Chip pin defect detection method, detection device and equipment | |
| CN111243009B (en) | Decision-based laser stripe center extraction method | |
| CN110443777A (en) | A kind of PCB image alignment method, device and computer storage medium |
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 |