CN117392226A - BGA element identification positioning method and system based on machine vision and storage medium - Google Patents
BGA element identification positioning method and system based on machine vision and storage medium Download PDFInfo
- Publication number
- CN117392226A CN117392226A CN202311689141.4A CN202311689141A CN117392226A CN 117392226 A CN117392226 A CN 117392226A CN 202311689141 A CN202311689141 A CN 202311689141A CN 117392226 A CN117392226 A CN 117392226A
- Authority
- CN
- China
- Prior art keywords
- contour
- blob
- electrode terminal
- bga
- 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 59
- 238000011156 evaluation Methods 0.000 claims abstract description 23
- 238000012216 screening Methods 0.000 claims abstract description 21
- 230000006870 function Effects 0.000 claims description 24
- 238000001914 filtration Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 abstract description 5
- 230000011218 segmentation Effects 0.000 abstract description 4
- 238000001514 detection method Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 7
- 238000000605 extraction Methods 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 5
- 238000005286 illumination Methods 0.000 description 4
- 241000519995 Stachys sylvatica Species 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000004806 packaging method and process Methods 0.000 description 3
- 230000002146 bilateral effect Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000001747 exhibiting effect Effects 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/64—Analysis of geometric attributes of convexity or concavity
-
- 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 invention relates to the technical field of component identification and positioning, and particularly discloses a BGA component identification and positioning method and system based on machine vision and a storage medium, wherein the method comprises the following steps: setting a Blob parameter according to the element parameter and the camera scale, screening the contours obtained by the target area image under different binarization thresholds, and setting the contours which all meet the screening conditions as candidate contours; classifying the candidate contours according to the contour centroid and the radius; integrating each type of contour by using an evaluation function to obtain the final outer contour of each electrode terminal; and calculating the center coordinates of each electrode terminal based on the final electrode terminal outer contour by using an iterative weighted least square fitting method, and identifying the pose information of the BGA element to be detected. The scheme is based on the combination of the improved multi-threshold segmentation Blob algorithm and the iterative weighted least square fitting, ensures the accuracy and stability of the extracted center coordinates of the electrode terminals of the BGA element, and solves the problem that stable feature points are difficult to obtain.
Description
Technical Field
The invention relates to the technical field of component identification and positioning, in particular to a BGA component identification and positioning method and system based on machine vision and a storage medium.
Background
With the increasing degree of integration of electronic products, the market has put higher demands on element packaging on integrated circuits, and miniaturization is becoming the mainstream, so BGA packaging elements with higher integration and better performance are beginning to be widely applied to electronic circuits. BGA (Ball Grid Array Package) is one of the most commonly used patch elements at present due to its packaging structure. BGA devices, also known as ball grid array packages, are a high density surface mount device. Compared with the traditional TSOP element, the BGA element package can be improved by 2-3 times under the same volume, and the heat dissipation and the electrical property are better, and the problem that the pins are easy to deform is avoided. BGA devices are therefore important in the field of chip mounting machines, which are highly integrated.
In the traditional method, rectangular fitting and template matching methods are mostly adopted for positioning detection of the BGA element. Although the rectangular fitting method is simple and quick, the number of characteristic points in the fitting process is often small, accuracy and stability of results are difficult to ensure, and the method is not applicable to small BGA elements or irregularly arranged BGA elements. Although the template matching method can solve the problem of stability of the detection result to a certain extent, the complex operation of the matching process consumes serious resources, and the detection precision is difficult to ensure.
At present, a point set registration method is mostly adopted for the positioning detection of the BGA element. The BGA component detection method using feature point set for registration still has the following problems: it is difficult to obtain stable feature points. Point set registration methods typically have contours or corner points as feature points. However, in the case of the BGA device, if the contour point set is directly used as the feature point set, there is a problem of poor stability and insufficient accuracy, and the outer contour of the electrode terminal in the BGA device is generally circular without fixed corner points, so that the corner points cannot be used as feature points.
Therefore, the existing point set registration method cannot accurately realize pose detection of the BGA element.
Disclosure of Invention
The invention aims to overcome the problems in the prior art and provides a BGA element identification positioning method, a system and a storage medium based on machine vision, which can accurately realize the pose positioning of a BGA element.
In order to achieve the above object, a first aspect of the present invention provides a BGA component positioning method based on machine vision, including the steps of:
acquiring a BGA element image target area;
setting a Blob parameter according to the element parameter and the camera scale, screening the contours obtained by the target region image under different binarization thresholds according to the Blob parameter, and setting all contours conforming to screening conditions as candidate contours;
classifying the candidate contours according to the contour centroid and the radius;
and integrating each type of contour by using an evaluation function, and obtaining the final outer contour of each electrode terminal, wherein the evaluation function is as follows:
the Radio is an output value of an evaluation function, and the smaller the output value is, the smaller the current contour is, the approximate ideal contour is approached;the method comprises the steps that S is the theoretical area of the outer contour of an electrode terminal to be detected, and S is the actual area of the current contour; hr is the actual convexity of the current contour, and Cr is the actual roundness of the current contour; α, β, γ are weight coefficients, α+β+γ=1;
and calculating the center coordinates of each electrode terminal based on the final electrode terminal outer contour by using an iterative weighted least square fitting method, and identifying the pose information of the BGA element to be detected according to the center coordinates of the electrode terminals.
A second aspect of the present invention provides a machine vision based BGA component identification and positioning system, comprising:
a target image acquisition module: acquiring a BGA element image target area and performing filtering treatment on the target area;
an electrode terminal candidate contour acquisition module: setting a Blob parameter according to the element parameter and the camera scale, screening the contours obtained by the target region image under different binarization thresholds according to the Blob parameter, and setting all contours conforming to screening conditions as candidate contours;
an electrode terminal candidate contour classification module: classifying the candidate contours according to the contour centroid and the radius;
electrode terminal outline integration module: and integrating each type of contour by using an evaluation function, and obtaining the final outer contour of each electrode terminal, wherein the evaluation function is as follows:
the Radio is an output value of an evaluation function, and the smaller the output value is, the smaller the current contour is, the approximate ideal contour is approached;the method comprises the steps that S is the actual area of a current contour and is the theoretical area of the outer contour of an electrode terminal to be detected, and the actual area is obtained through calculation of the contour; hr is the actual convexity of the current contour, and Cr is the actual roundness of the current contour; α, β, γ are weight coefficients, α+β+γ=1;
and (3) identifying and positioning module: and calculating the center coordinates of each electrode terminal based on the candidate contour by using an iterative weighted least square fitting method, and identifying the pose information of the BGA element according to the center coordinates of the electrode terminals.
A third aspect of the present invention provides a computer storage medium comprising:
a memory having a computer program stored thereon;
and a processor for executing the computer program in the memory to realize the steps of the machine vision-based BGA component identification positioning method.
Through the technical scheme, the Blob extraction and screening parameters are set pertinently according to the shape characteristics of the outer contour of the electrode terminal, candidate contours are obtained, evaluation function indexes comprehensively considering contour area, roundness and convexity are designed, and various candidate contours are further screened and integrated to obtain a final outer contour set of the electrode terminal. The mode can resist the interference of illumination, noise or boundary bulge and the like, so that the more stable and real electrode terminal outline is obtained. In addition, the Blob parameters set in the candidate contour extraction stage can screen out other structural interference or abnormal white spots and other interference; the invention further obtains the center coordinates of the electrode terminal by an iterative weighted least square fitting method for the outer contour of the electrode terminal, and can resist the problem of electrode terminal center calculation errors caused by the condition of electrode terminal center position deviation and contour protrusion due to contour fluctuation. The combination of the Blob algorithm based on improved multi-threshold segmentation and iterative weighted least square fitting ensures the accuracy and stability of the extracted center coordinates of the electrode terminals of the BGA element, and solves the problem that stable characteristic points are difficult to obtain.
Drawings
FIG. 1 is a raw image taken of a BGA component in some embodiments of the present disclosure;
FIG. 2 is a flow diagram of identifying a position fix in accordance with some embodiments of the present disclosure;
FIG. 3 is an image of a target area in an image of a BGA device in accordance with some embodiments of the present disclosure;
FIG. 4 is an external profile of an electrode terminal extracted and screened in accordance with some embodiments of the present disclosure;
FIG. 5 is a calculated electrode terminal center profile in some embodiments of the present disclosure;
fig. 6 is a pose recognition result image of a BGA component in some embodiments of the present disclosure.
Detailed Description
The following describes the detailed implementation of the embodiments of the present invention with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the invention, are not intended to limit the invention.
Fig. 1 shows an original image of a BGA device with electrode terminals for identification exhibiting circular bright spots under lateral light irradiation, and all terminals being distributed in a grid array. The simplest pose estimation method is to adopt a fitting method, but when elements are smaller, the number of feature points available for fitting is smaller, and the stability and accuracy of a fitting result cannot be guaranteed. If the template matching method is adopted, although the problems of accuracy and stability of the detection result can be improved, after the scaling factors of the angle, the horizontal direction and the vertical direction are considered, the consumption of time and computer resources by an algorithm is overlarge, and the requirement of quick positioning of the chip mounter cannot be well met. If the traditional feature point set registration mode is adopted, the requirement of template matching on resources can be improved to a certain extent, but the problem that stable feature points are difficult to obtain in practical application, a large number of iterations are required in the registration process, time consumption is serious when the feature points are more, and the like is solved, and the requirements of a chip mounter on high precision and high efficiency are difficult to meet at the same time. In this embodiment, the element shown in fig. 1 is taken as an object, and the embodiment is described with respect to the problem of rapid and accurate positioning of the BGA element.
A first aspect of the present invention provides a machine vision-based BGA component identifying and positioning method, as shown in fig. 2, including the following steps:
s1, acquiring a BGA element image target area.
Generally, the obtained original image is relatively large, the elements occupy only a part of the original image, and unnecessary resources (memory and time) are wasted when the whole image is directly used for processing, so that the region of interest (Region of Interest, ROI) needs to be extracted from the original image, so that the processing speed is increased, and the resource consumption is reduced. In addition, since the response of the camera sensor and the fluctuation of the electric signal interfere with the extraction of the boundary contour due to the presence of abnormal pixel points in the image, the extracted ROI image needs to be subjected to a filtering process. After comprehensively considering various factors such as processing effect, processing speed, boundary protection effect and the like, filtering by adopting a bilateral filter with the neighborhood size of 10 to obtain the BGA element image target area. The final BGA component target region image effect is described with reference to fig. 3.
Further, step S1 includes the following procedure:
s11, extracting a region of interest: firstly, extracting a region of interest from the obtained original image containing the BGA component by using the mounting head position information and the component size information to be detected. Generally, the position information of a mounting head of a chip mounter is known during mounting, and when the mounting head sucks a component, the distance between the center of the component and the center of the mounting head is small, so that the center of a region of interest can be determined as an image center by using the position information of the mounting head at the center of the image. In the mounting process, the chip mounter generally ensures that the component angle sucked for multiple times fluctuates in a small range around a specified 0-degree angle, so that the pixel-level length and width of the region of interest are calculated by using given theoretical size information of the component and the pixel size of the camera. The specific calculation mode of the pixel-level length and width of the region of interest is as follows:
wherein, rectW and RectH respectively represent the length and width of the region of interest, and the unit pixel; w (W) 0 、H 0 Respectively representing theoretical length and width of the BGA element to be detected, and unit mm; searchea represents a set detection range, given according to the range in which the element may fluctuate during suction, in mm, generally taking 2mm; scaleX, scaleY represents the pixel size in the camera lateral and longitudinal directions, i.e. the actual length in μm/pixel of a pixel in the horizontal and vertical directions, respectively.
And the calculated ROI information is utilized to intercept the ROI image on the original image, so that the size of the image to be processed can be reduced, and the subsequent processing speed is increased.
S12, filtering the region of interest: and denoising the extracted region-of-interest image by using a bilateral filter with the neighborhood size of 10, and removing part of noise on the premise of reserving boundary information as much as possible, thereby improving the accuracy of subsequent identification.
Through the operation, the size of the image in subsequent processing is reduced, and the speed of the subsequent processing is increased. On the premise of keeping boundary information as much as possible, noise interference in the image is weakened, and the extraction of the outer contour of the electrode terminal and the accurate calculation of the center are facilitated.
S2, setting a Blob parameter according to the element parameter and the camera scale, screening the contours obtained by the target area image under different binarization thresholds according to the Blob parameter, and setting all contours meeting screening conditions as candidate contours.
Further, step S2 includes the following procedure:
s21, calculating the Blob parameters according to the input element parameters and the images. The Blob parameters include: element surface type, binarization threshold range, binarization threshold variation step length, convexity minimum value, roundness minimum value, inertia minimum value, minimum Blob number, adjacent Blob minimum distance, blob area range, and the like. Wherein the element surface type is directly obtainable from the input element parameters; the binarization threshold range is that an intermediate threshold is obtained by carrying out OTSU automatic threshold search on the target area image, and the threshold range is the intermediate threshold + -30; the binarization threshold change step length is set to be 5; convexity minimum is set to 0.8; the roundness minimum value is set to 0.65; the minimum value of the inertia rate is set to 0.5; the minimum Blob number is set to 3; the minimum distance of the adjacent Blob is set to be the terminal diameter theoretical pixel length +1; the Blob area range calculates the theoretical terminal area S through the theoretical pixel length of the terminal diameter 0 Setting the area range to be 0.7-1.3 times。
S22, candidate contour acquisition. Binarizing the extracted target area image under different binarization thresholds, acquiring the Blob contours in the current binarization image by a connected domain searching method, and finally screening all the extracted Blob contours by using the convexity minimum value, the roundness minimum value, the inertia rate minimum value and the area range set in the step S21 to obtain a candidate contour set.
The adopted contour screening and extracting method can cope with adverse factors such as uneven illumination, uncertain illumination brightness, incomplete consistency of the sizes of the electrode terminals, protruding terminal boundaries and the like, and extracts proper terminal outer contours to be put into a candidate contour set. And the set Blob screening parameters can screen out other structural interference or abnormal white spots and other interference, so that the accuracy of extracting the contour is further ensured.
And S3, classifying the candidate contour set according to the candidate contour centroid and the radius.
The same electrode terminal may obtain a plurality of candidate contours meeting the conditions through step S2, and only the contours and the outer contour of the electrode terminal have a relation in the candidate contour set, so that the candidate contours belonging to the outer contour of the same electrode terminal need to be clustered. The candidate profiles belonging to the same electrode terminal have the following characteristics: the contour centers are close to each other and there is an intersection of the contours. Thus, candidate contours having an intersection with centroid distances less than the set minimum distance of adjacent blobs in the candidate contour set are classified as one class.
Wherein the determination of the intersection of the candidate wheel sets is typically accomplished by comparing the inter-centroid distance of the two candidate contours to the radius of the two candidate contours. If the inter-centroid distance of the two candidate contours is smaller than the radius of the two candidate contours, then the two candidate contours are considered to have an intersection.
In addition, the operation procedure of step S2 may obtain pseudo candidate contours not belonging to the electrode terminal under some binarized images, and they are characterized in that contours meeting the screening conditions can be extracted on only a few binarized images at the same position, so that the number of candidate contours belonging to the same class of contours can be counted for screening. If the number of candidate contours belonging to the same class of contours is smaller than the set minimum Blob number, all candidate contours in the set of candidate contours are screened out.
S4, integrating each type of candidate contour by using an evaluation function, and obtaining the final electrode terminal outer contour, wherein the evaluation function is as follows:
the Radio is an output value of an evaluation function, and the smaller the output value is, the smaller the current contour is, the approximate ideal contour is approached;the theoretical area of the outer contour of the electrode terminal is S, and the area of the outer contour of the electrode terminal is S; hr is the convexity of the outer contour, and Cr is the roundness of the outer contour; α, β, γ are weight coefficients, α+β+γ=1.
The evaluation function provided by the invention can extract the contour most meeting the actual requirement from a plurality of candidate contours belonging to the same class, and ensures the accuracy and stability of the extracted contour. The contour of the image in fig. 3 after the classification by Blob algorithm based on improved multi-threshold segmentation and the integration based on the above-mentioned evaluation function is shown in fig. 4.
S5, calculating center coordinates of each electrode terminal based on candidate contours by using an iterative weighted least square fitting method, and identifying the pose information of the BGA element according to the center coordinates of the electrode terminals.
After the outer contour of the electrode terminal is extracted, if the outer contour is directly used as a characteristic point, the problem that the contour appearance of different terminals is inconsistent possibly caused by size fluctuation exists, and the problems that the calculation complexity is greatly improved and the time consumption is seriously increased due to huge data volume also exist. Aiming at the problems, the method adopts an iterative weighted least square circle fitting mode to fit the outer contour, and obtains the center coordinate of the electrode terminal. In the iterative weighted least square circle fitting process, partial outlier contour points can be removed through weight adjustment, so that the fitting result is more in line with the actual situation. Therefore, the method not only greatly reduces the number of the characteristic points, but also ensures the stability and the accuracy of the characteristic point set.
The basic idea of the iterative weighted least square circle fitting method is to introduce a distance weight function on the basis of least square fitting for a data point set with outliers or other outliersThe contribution degree of abnormal points to fitting is weakened, and the optimal result is gradually approximated by a plurality of iterative modes. The weight function employed is typically a Tukey weight:
wherein,is the clipping factor, where the median of the distances from the points involved in the fitting in the last cycle to the center of the fitted circle is divided by 0.6755 and multiplied by 2,is the distance of point i from the center of the currently fitted circle.
Deviation sum of weighted least squares fittingThe method comprises the following steps:
and solving the minimum value of the deviation sum by solving a first derivative equation set of the parameters, thereby determining the best fit circle under the current cycle. In the cyclic iteration process, the influence of the outlier on the fitting result is weakened gradually in a weight updating mode, and the fitting circle is more in line with the actual situation.
The calculation result of the center of the electrode terminal in fig. 4 is shown in fig. 5. Compared with the method that the outer contour is directly used as the characteristic point, the terminal center is used as the characteristic point, so that the position is stable and accurate, and the data size is small. And in the iterative fitting process, partial outlier contour points can be removed through weight adjustment by utilizing iterative weighted least square circle fitting, so that the fitting result is more in line with the actual situation. Therefore, the method not only greatly reduces the number of the characteristic points, but also ensures the stability and the accuracy of the characteristic point set.
It should be noted that, in step S5, the pose information of the BGA device is identified according to the coordinates of the center of the electrode terminals, the center of the electrode terminals at the periphery of the BGA device may be used for performing point set registration, and the center of all the electrode terminals of the BGA device may be used for performing point set registration, so as to identify the pose information, and the identification result is shown in fig. 6.
Based on the same inventive concept, a second aspect of the embodiment of the present invention provides a BGA component recognition and positioning system based on machine vision, including
A target image acquisition module: acquiring a target area of the BGA element image and performing filtering processing on the target area image;
an electrode terminal candidate contour acquisition module: setting a Blob parameter according to the element parameter and the camera scale, screening the contours obtained by the target region image under different binarization thresholds according to the Blob parameter, and setting all contours conforming to screening conditions as candidate contours;
an electrode terminal candidate contour classification module: classifying the candidate contours according to the contour centroid and the radius;
electrode terminal outline integration module: and integrating each type of candidate contour by using an evaluation function, and obtaining the final outer contour of each electrode terminal, wherein the evaluation function is as follows:
the Radio is an output value of an evaluation function, and the smaller the output value is, the smaller the current contour is, the approximate ideal contour is approached;the theoretical area of the outer contour of the electrode terminal is S, and the area of the outer contour of the electrode terminal is S; hr is the convexity of the outer contour, and Cr is the roundness of the outer contour; α, β, γ are weight coefficients, α+β+γ=1;
and (3) identifying and positioning module: and calculating the center coordinates of each electrode terminal based on the candidate contour by using an iterative weighted least square fitting method, identifying the pose information of the BGA element according to the center coordinates of the electrode terminals, and preferentially using the point set of the center coordinates of the electrode terminals as a characteristic point set to perform point set registration to obtain the pose information of the BGA element to be detected.
Further, α is 0.3, β is 0.4, and γ is 0.4.
Further, the Blob parameters are: element surface type, binarization threshold range, binarization threshold change step length, convexity minimum value, roundness minimum value, inertia minimum value, minimum Blob number, adjacent Blob minimum distance, blob area range; the Blob parameter values are respectively: the element surface type is a reflector, and the binarization threshold range is a middle threshold value + -30; the binarization threshold change step length is set to be 5; convexity minimum is set to 0.8; the roundness minimum value is set to 0.65; the minimum value of the inertia rate is set to 0.5; the minimum Blob number is set to 3; the minimum distance of the adjacent Blob is set to be the theoretical pixel length of the electrode terminal diameter +1; the Blob area is set to be 0.7-1.3 times
Further, the acquiring the BGA component image target region specifically includes:
and extracting a region of interest (ROI image) from the BGA element image to be detected according to the mounting head position information and the size information of the element to be detected, and performing filtering noise reduction processing on the ROI image to obtain the target region of the BGA element image.
Based on the same inventive concept, a third aspect of an embodiment of the present invention provides a computer storage medium, comprising:
a memory having a computer program stored thereon;
and a processor for executing the computer program in the memory to implement the steps of the above method.
In summary, according to the technical scheme of the invention, blob extraction and screening parameters are set pertinently according to the shape characteristics of the outer contour of the electrode terminal, candidate contours are obtained, evaluation function indexes comprehensively considering contour area, roundness and convexity are designed, and various candidate contours are further screened and integrated to obtain a final outer contour set of the electrode terminal. The mode can resist the interference of illumination, noise or boundary bulge and the like, so that the more stable and real electrode terminal outline is obtained. In addition, the Blob parameters set in the candidate contour extraction stage can screen out other structural interference or abnormal white spots and other interference; the invention further obtains the center coordinates of the electrode terminal by an iterative weighted least square fitting method for the outer contour of the electrode terminal, and can resist the problem of electrode terminal center calculation errors caused by the condition of electrode terminal center position deviation and contour protrusion due to contour fluctuation. The combination of the Blob algorithm based on improved multi-threshold segmentation and iterative weighted least square fitting ensures the accuracy and stability of the extracted center coordinates of the electrode terminals of the BGA element, and solves the problem that stable characteristic points are difficult to obtain.
The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited thereto. Within the scope of the technical idea of the invention, a number of simple variants of the technical solution of the invention are possible, including the combination of the individual specific technical features in any suitable way. The various possible combinations of the invention are not described in detail in order to avoid unnecessary repetition. Such simple variations and combinations are likewise to be regarded as being within the scope of the present disclosure.
Claims (10)
1. The BGA component identification and positioning method based on machine vision is characterized by comprising the following steps of:
acquiring a BGA element image target area;
setting a Blob parameter according to the element parameter and the camera scale, screening the contours obtained by the target region image under different binarization thresholds according to the Blob parameter, and setting all contours conforming to screening conditions as candidate contours;
classifying the candidate contours according to the contour centroid and the radius;
and integrating each type of contour by using an evaluation function, and obtaining the final outer contour of each electrode terminal, wherein the evaluation function is as follows:
wherein Radio is an output value of the evaluation function, and smaller Radio represents that the current contour is closer to an ideal wheelA profile; s is S 0 The method comprises the steps that S is the theoretical area of the outer contour of an electrode terminal to be detected, and S is the actual area of the current contour; hr is the actual convexity of the current contour, and Cr is the actual roundness of the current contour; α, β, γ are weight coefficients, α+β+γ=1;
and calculating the center coordinates of each electrode terminal based on the final electrode terminal outer contour by using an iterative weighted least square fitting method, and identifying the pose information of the BGA element to be detected according to the center coordinates of the electrode terminals.
2. The method of claim 1, wherein α is 0.3, β is 0.4, and γ is 0.4.
3. The method of claim 1, wherein the Blob parameters comprise: element surface type, binarization threshold range, binarization threshold change step length, convexity minimum value, roundness minimum value, inertia minimum value, minimum Blob number, adjacent Blob minimum distance, blob area range.
4. A method according to claim 3, wherein the element surface type is a reflector and the binarization threshold range is a median threshold ± 30; the binarization threshold change step length is set to be 5; convexity minimum is set to 0.8; the roundness minimum value is set to 0.65; the minimum value of the inertia rate is set to 0.5; the minimum Blob number is set to 3; the minimum distance of the adjacent Blob is set to be the theoretical pixel length of the electrode terminal diameter +1; the Blob area is set to be 0.7-1.3 times S 0 。
5. The method according to any one of claims 1 to 4, wherein the acquiring the BGA component image target region specifically includes:
and extracting an ROI image from the BGA element image to be detected according to the mounting head position information and the size information of the element to be detected, and performing filtering noise reduction processing on the ROI image to obtain the target area of the BGA element image.
6. A BGA component identification positioning system based on machine vision is characterized by comprising
A target image acquisition module: acquiring a target area of the BGA element image and performing filtering processing on the target area image;
an electrode terminal candidate contour acquisition module: setting a Blob parameter according to the element parameter and the camera scale, screening the contours obtained by the target region image under different binarization thresholds according to the Blob parameter, and setting all contours conforming to screening conditions as candidate contours;
an electrode terminal candidate contour classification module: classifying the candidate contours according to the contour centroid and the radius;
electrode terminal outline integration module: and integrating each type of contour by using an evaluation function, and obtaining the final outer contour of each electrode terminal, wherein the evaluation function is as follows:
the Radio is an output value of an evaluation function, and the smaller the output value is, the smaller the current contour is, the approximate ideal contour is approached; s is S 0 The method comprises the steps that S is the theoretical area of the outer contour of an electrode terminal to be detected, and S is the actual area of the current contour; hr is the actual convexity of the current contour, and Cr is the actual roundness of the current contour; α, β, γ are weight coefficients, α+β+γ=1;
and (3) identifying and positioning module: and calculating the center coordinates of each electrode terminal based on the candidate contour by using an iterative weighted least square fitting method, and identifying the pose information of the BGA element according to the center coordinates of the electrode terminals.
7. The system of claim 6, wherein α is 0.3, β is 0.4, and γ is 0.4.
8. The system of claim 6, wherein the Blob parameters are: element surface type, binarization threshold range, binarization threshold change step length, convexity minimum value, roundness minimum value, inertia minimum value, minimum Blob number, adjacent Blob minimum distance, blob area range; the Blob parameter values are respectively: metaThe surface type of the piece is a reflector, and the range of the binarization threshold is a middle threshold + -30; the binarization threshold change step length is set to be 5; convexity minimum is set to 0.8; the roundness minimum value is set to 0.65; the minimum value of the inertia rate is set to 0.5; the minimum Blob number is set to 3; the minimum distance of the adjacent Blob is set to be the theoretical pixel length of the electrode terminal diameter +1; the Blob area is set to be 0.7-1.3 times S 0 。
9. The system according to any one of claims 6 to 8, wherein the acquiring the BGA component image target region is specifically:
extracting a region of interest (ROI image) from the BGA element image to be detected by using the mounting head position information and the size information of the element to be detected, and performing filtering noise reduction processing on the ROI image to obtain the target region of the BGA element image.
10. A computer storage medium, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to carry out the steps of the method according to any one of claims 1-5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311689141.4A CN117392226B (en) | 2023-12-11 | 2023-12-11 | BGA element identification positioning method and system based on machine vision and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311689141.4A CN117392226B (en) | 2023-12-11 | 2023-12-11 | BGA element identification positioning method and system based on machine vision and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117392226A true CN117392226A (en) | 2024-01-12 |
CN117392226B CN117392226B (en) | 2024-04-05 |
Family
ID=89463465
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311689141.4A Active CN117392226B (en) | 2023-12-11 | 2023-12-11 | BGA element identification positioning method and system based on machine vision and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117392226B (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109798844A (en) * | 2018-12-28 | 2019-05-24 | 北京交通大学 | A kind of rail exterior feature autoegistration method in rail wear dynamic measurement |
CN109886917A (en) * | 2019-01-09 | 2019-06-14 | 浙江舜宇光学有限公司 | A kind of wafer disks localization method and device |
CN110490847A (en) * | 2019-07-31 | 2019-11-22 | 浙江大学山东工业技术研究院 | The LED chip quality determining method of view-based access control model |
WO2021012370A1 (en) * | 2019-07-25 | 2021-01-28 | 深圳壹账通智能科技有限公司 | Pupil radius detection method and apparatus, computer device and storage medium |
US10916067B1 (en) * | 2019-11-14 | 2021-02-09 | Adobe Inc. | Intelligent alignment of graphical elements |
CN113129268A (en) * | 2021-03-19 | 2021-07-16 | 江苏航空职业技术学院 | Quality detection method for airplane riveting pier head |
CN114612550A (en) * | 2022-03-02 | 2022-06-10 | 深圳汇控智能技术有限公司 | Circle fitting algorithm based on multistage optimization |
CN114749006A (en) * | 2022-03-28 | 2022-07-15 | 浙江浙能兰溪发电有限责任公司 | Method for optimizing wet desulphurization slurry circulating pump |
WO2022250584A1 (en) * | 2021-05-24 | 2022-12-01 | Telefonaktiebolaget Lm Ericsson (Publ) | A method and an electronic device for analysing an image |
CN115578571A (en) * | 2022-10-08 | 2023-01-06 | 合肥安迅精密技术有限公司 | QFN element rapid and accurate identification and positioning method and device and storage medium |
CN115984211A (en) * | 2022-12-29 | 2023-04-18 | 深圳优艾智合机器人科技有限公司 | Visual positioning method, robot and storage medium |
-
2023
- 2023-12-11 CN CN202311689141.4A patent/CN117392226B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109798844A (en) * | 2018-12-28 | 2019-05-24 | 北京交通大学 | A kind of rail exterior feature autoegistration method in rail wear dynamic measurement |
CN109886917A (en) * | 2019-01-09 | 2019-06-14 | 浙江舜宇光学有限公司 | A kind of wafer disks localization method and device |
WO2021012370A1 (en) * | 2019-07-25 | 2021-01-28 | 深圳壹账通智能科技有限公司 | Pupil radius detection method and apparatus, computer device and storage medium |
CN110490847A (en) * | 2019-07-31 | 2019-11-22 | 浙江大学山东工业技术研究院 | The LED chip quality determining method of view-based access control model |
US10916067B1 (en) * | 2019-11-14 | 2021-02-09 | Adobe Inc. | Intelligent alignment of graphical elements |
CN113129268A (en) * | 2021-03-19 | 2021-07-16 | 江苏航空职业技术学院 | Quality detection method for airplane riveting pier head |
WO2022250584A1 (en) * | 2021-05-24 | 2022-12-01 | Telefonaktiebolaget Lm Ericsson (Publ) | A method and an electronic device for analysing an image |
CN114612550A (en) * | 2022-03-02 | 2022-06-10 | 深圳汇控智能技术有限公司 | Circle fitting algorithm based on multistage optimization |
CN114749006A (en) * | 2022-03-28 | 2022-07-15 | 浙江浙能兰溪发电有限责任公司 | Method for optimizing wet desulphurization slurry circulating pump |
CN115578571A (en) * | 2022-10-08 | 2023-01-06 | 合肥安迅精密技术有限公司 | QFN element rapid and accurate identification and positioning method and device and storage medium |
CN115984211A (en) * | 2022-12-29 | 2023-04-18 | 深圳优艾智合机器人科技有限公司 | Visual positioning method, robot and storage medium |
Non-Patent Citations (2)
Title |
---|
朱莉等: "基于OpenCV的光纤端面检测系统研究", 光通信研究, no. 01, 28 February 2015 (2015-02-28) * |
王志豪: ""基于显微视觉的微球定位与转移技术研究"", 《万方硕士论文》, 11 November 2022 (2022-11-11), pages 39 - 41 * |
Also Published As
Publication number | Publication date |
---|---|
CN117392226B (en) | 2024-04-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108921176B (en) | Pointer instrument positioning and identifying method based on machine vision | |
CN109242853B (en) | PCB defect intelligent detection method based on image processing | |
WO2021051604A1 (en) | Method for identifying text region of osd, and device and storage medium | |
CN109271937B (en) | Sports ground marker identification method and system based on image processing | |
CN106709500B (en) | Image feature matching method | |
CN115578571A (en) | QFN element rapid and accurate identification and positioning method and device and storage medium | |
CN113436212A (en) | Extraction method for inner contour of circuit breaker static contact meshing state image detection | |
US10643100B2 (en) | Object detection apparatus, object detection method, and storage medium | |
Said et al. | Robust automatic void detection in solder balls | |
CN111912846A (en) | Machine vision-based surface defect and edge burr detection method | |
CN111695373B (en) | Zebra stripes positioning method, system, medium and equipment | |
CN115019024B (en) | Visual recognition method of QFP | |
CN115439523A (en) | Method and equipment for detecting pin size of semiconductor device and storage medium | |
EP3510526A1 (en) | Particle boundary identification | |
CN117392226B (en) | BGA element identification positioning method and system based on machine vision and storage medium | |
CN108898584B (en) | Image analysis-based full-automatic veneered capacitor welding polarity discrimination method | |
CN111508017B (en) | Method and system for positioning mark center with weak contrast | |
CN111563883B (en) | Screen vision positioning method, positioning equipment and storage medium | |
CN111816579B (en) | Method and apparatus for detecting chips contaminated with flux residue | |
JP6580201B2 (en) | Subject detection apparatus, subject detection method, and program | |
JP2018109824A (en) | Electronic control device, electronic control system, and electronic control method | |
CN111914680A (en) | Component identification and positioning method based on frequency domain characteristics | |
Chao et al. | Edge Location and Identification Method for Electronic Components based on Improved Canny Algorithm | |
CN114943769B (en) | Positioning method, positioning device, electronic equipment and medium | |
Peng et al. | BGA void detection in X-ray images based on a new blob detector |
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 |