CN116977721A - Automatic teaching element classification method for chip mounter - Google Patents
Automatic teaching element classification method for chip mounter Download PDFInfo
- Publication number
- CN116977721A CN116977721A CN202310864914.1A CN202310864914A CN116977721A CN 116977721 A CN116977721 A CN 116977721A CN 202310864914 A CN202310864914 A CN 202310864914A CN 116977721 A CN116977721 A CN 116977721A
- Authority
- CN
- China
- Prior art keywords
- contour
- image
- pin
- point
- chip mounter
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000001914 filtration Methods 0.000 claims description 14
- 230000007704 transition Effects 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 239000004020 conductor Substances 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000013519 translation Methods 0.000 claims description 5
- 230000000877 morphologic effect Effects 0.000 claims description 4
- 230000000149 penetrating effect Effects 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 9
- 229910000679 solder Inorganic materials 0.000 description 7
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05K—PRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS
- H05K13/00—Apparatus or processes specially adapted for manufacturing or adjusting assemblages of electric components
- H05K13/04—Mounting of components, e.g. of leadless components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05K—PRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS
- H05K13/00—Apparatus or processes specially adapted for manufacturing or adjusting assemblages of electric components
- H05K13/08—Monitoring manufacture of assemblages
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Manufacturing & Machinery (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The application discloses an element classification method for automatic teaching of a chip mounter, which comprises the following steps of S10: preprocessing an image; s20: extracting a target contour; s30: pose adjustment; s40: distinguishing element types; s50: the component types are classified. The beneficial effects of the application are as follows: according to the method, the self-classification of the elements automatically taught by the chip mounter is realized through the geometric features of the surface-mounted elements, the types of the elements required to be established in the element library are reduced, and the recognition efficiency is improved.
Description
Technical Field
The application relates to the technical field of image recognition, in particular to an element classification method for automatic teaching of a chip mounter.
Background
Along with the development of electronic manufacturing industry, the development of surface mounting technology is faster and faster, wherein the positioning accuracy and speed of the mounting components are important indexes for influencing the performance of the mounting machine. The electronic component positioning method based on the computer has the characteristics of high speed, high precision and intellectualization, not only increases the flexibility and the automation degree of production, but also greatly improves the intelligence and the universality of production, so that the high-performance chip mounter adopts the computer vision detection technology to improve the chip mounting efficiency of the chip mounter.
The surface mounting device of the chip mounter can be used for mounting and producing is rich in types, mainly comprises chip elements, pin elements, BGA elements and the like, before a certain type of elements are mounted, the types of the elements which are classified in advance are selected from an element library to write a teaching program, the types of the elements are multiple, the elements of the same type are subdivided into multiple types due to different geometric characteristics, and therefore the types of the elements which need to be built in the element library are many. The identification by manpower is not only time-consuming and labor-consuming and has low precision, but also is relatively easy to make mistakes.
Disclosure of Invention
In order to overcome the defects of the prior art, the application provides the element classification method for the automatic teaching of the chip mounter, which realizes the automatic element classification of the automatic teaching of the chip mounter through the geometric characteristics of the surface-mounted elements, reduces the element types required to be established by the element library and improves the recognition efficiency.
The technical scheme adopted for solving the technical problems is as follows: an element classification method for automatic teaching of a chip mounter, the method comprises the following steps:
s10: preprocessing an image; sequentially carrying out smoothing filtering, binarization threshold segmentation and interference point filtering on the image;
s20: extracting a target contour; performing contour searching on the processed image, classifying contours with contour areas in the same interval, and respectively calculating contour area average values of the contours, wherein the contours with the largest quantity of contours in the same interval and the largest contour area average value are target contours;
s30: pose adjustment; acquiring a minimum circumscribed rectangle rect of a target contour, calculating a center coordinate and a deflection angle of the minimum circumscribed rectangle rect, and correcting the target contour and placing the target contour in the center of an image by utilizing image translation and image rotation;
s40: distinguishing element types; performing polygon fitting on the target contours to obtain the number of endpoints of the element, then averaging the fitting endpoint numbers of all the target contours, and distinguishing the element types through endpoint number difference;
s50: classifying the element types; firstly, moving a target element to an image center with an angle of 0 DEG, taking the image center as a reference, making scanning lines penetrating through pins of element arrangement in the left, upper, right and lower directions of a minimum circumscribed rectangle rect of an element profile, obtaining the number of gray transition points on the scanning lines, then determining the number of the pins, and then classifying the element types.
In the above step, in the step S30, the image width is set to width, the image height is set to height, and the element constraint angle Φ;
the offset of the element pixel point to the center of the image is:
Δx＝rect.center.x–width/2；
Δy＝rect.center.y–height/2；
the image center offset formula is:
the image rotation matrix formula is:
the centre offset matrix is multiplied by the rotation matrix, i.e. M AT ×M AR The formula is corrected for the element pose:
where x and y are the pixel locations of the original image,and->And correcting the position of the pixel point for the pose.
In the above step, in the step S40, the polygon fitting is performed on the element profile by modifying the Douglas-Peucker algorithm;
in the above steps, the step of improving the Douglas-Peucker algorithm includes:
s401: firstly, finding a point A at the upper left corner of the polygonal contour, traversing and calculating another point B on the contour farthest from the point A, taking the point A and the point B as two initial end points, dividing the polygonal contour into two curves AB and BA, and taking a straight line AB as the chord of the curves AB and BA;
s402: respectively processing the two curves AB and BA; firstly, obtaining a point C with the largest distance from a straight line segment AB on a curve AB, and calculating the distance d between the point C and the straight line AB; the curve BA is also processed as described above;
s403: comparing the relation between the distance d and a preset distance threshold value threshold, and if the relation is smaller than the threshold value threshold, taking the straight line segment as an approximation of a curve, and finishing the curve processing;
s404: if the distance d is greater than the threshold value threshold, taking C as the other end point of the curve AB, dividing the curve into two sections of AC and CB, and repeating the steps for the two sections of curves respectively;
s405: and performing iterative processing for a plurality of times until all curves are processed, and obtaining the number of fitting endpoints of the polygonal contour.
In the above step, in the step S403: threshold=0.03×arclength (conductors [ i ], true), arcLength (conductors [ i ], true) being the circumference of the current contour (true representing a closed curve).
In the above steps, the specific step of determining the pin number in the step S50 is: the number of gray transition points on the scanning line is obtained by utilizing a gradient algorithm, then one scanning line is taken by five pixel units, three scanning lines are taken in each direction, the number of the gray transition points is an even number and the number is the largest, and half of the number is the pin number of the element in the direction.
In the above steps, the specific steps of element classification in step S50 are:
s501: firstly, judging whether the contour number of the element is 1 and the endpoint number is 4, if so, the element is a sheet element, otherwise, the step S502 is entered;
s502: judging whether the contour number of the element is more than or equal to 3 and whether the end point average number is more than or equal to 7, if so, the element is a BGA element; otherwise, step S503 is entered;
s503: judging whether the contour number of the element is more than or equal to 3 and whether the end point average number is 4, if so, the element is a pin element.
In the above steps, if the pin element is determined in the step S503, the pin element is subdivided, which specifically includes the following steps:
s5301: judging whether the four-side pin number of the element is equal and whether the pin number is more than or equal to 4, if so, the element is a QFP element; otherwise, go to step S5302;
s5302: judging whether the opposite side pin numbers are equal and whether the pin numbers are more than or equal to 2, if so, the element is an SOP element; otherwise, enter step S5303;
s5303: judging whether the pin numbers at the two sides of the opposite sides are 1 and 2, if so, the element is an SOT element, and finishing the element classification of the pin class.
In the above step, in the step S10, the image is smoothed by using a gaussian convolution kernel, the image is binarized and thresholded by using the OTSU method, and the image is filtered by using morphological processing-open operation.
In the above step, in the step S20, a clustering algorithm is used to classify the contours with contour areas in the same section.
The beneficial effects of the application are as follows: according to the method, the self-classification of the elements automatically taught by the chip mounter is realized through the geometric features of the surface-mounted elements, the types of the elements required to be established in the element library are reduced, and the recognition efficiency is improved.
Drawings
Fig. 1-2 are original diagrams of SOP24 and BGA.
Fig. 3 to 4 are images of SOP24 and BGA binarized.
Fig. 5-6 are complete images of SOP24 and BGA after image pre-processing.
Fig. 7 is a schematic diagram of SOP24 extracting a pin foot profile and adjusting a pose.
Fig. 8 is a schematic diagram of BGA extracting solder ball contours and adjusting pose.
Fig. 9-11 are schematic diagrams of polygon fitting endpoints.
Fig. 12 is a schematic diagram of a pin of an SOP element.
FIG. 13 is a flow chart of component classification.
Detailed Description
The application will be further described with reference to the drawings and examples.
The conception, specific structure, and technical effects produced by the present application will be clearly and completely described below with reference to the embodiments and the drawings to fully understand the objects, features, and effects of the present application. It is apparent that the described embodiments are only some embodiments of the present application, but not all embodiments, and that other embodiments obtained by those skilled in the art without inventive effort are within the scope of the present application based on the embodiments of the present application. In addition, all the coupling/connection relationships referred to in the patent are not direct connection of the single-finger members, but rather, it means that a better coupling structure can be formed by adding or subtracting coupling aids depending on the specific implementation. The technical features in the application can be interactively combined on the premise of no contradiction and conflict.
The application discloses an element classification method for automatic teaching of a chip mounter, which realizes the automatic classification of elements for automatic teaching of the chip mounter through the geometric features of surface-mounted elements, reduces the types of elements required to be established in an element library and improves the recognition efficiency.
Specifically, the method comprises the following steps:
s10: image preprocessing, namely sequentially carrying out smoothing filtering, binarization threshold segmentation and interference point filtering on the image;
in this embodiment, the gaussian convolution is used to check the image to perform smoothing filtering, then the OTSU method is used to perform binary threshold segmentation on the image, and then the morphological processing-open operation is used to perform interference point filtering on the image, and at the same time, the foot and the root of the pin element can be disconnected, so that the foot area of the pin of the element can be conveniently extracted as the target contour, and the contour extraction of the chip element and the BGA element can not be affected. Referring to fig. 1 to 2, which are original views of SOP24 and BGA, respectively, fig. 3 to 4 are binarized images, and fig. 5 to 6 are complete images after image preprocessing.
S20: extracting a target contour, searching the contour of the processed image, classifying the contour of the contour area in the same section, and respectively calculating the average value of the contour areas, wherein the contour with the largest contour quantity in the same section and the maximum average value of the contour area is the target contour;
in this embodiment, since the root size of the pin is generally half of the foot size, and the Mark point size of the BGA type element is smaller than the bottom solder ball size, the profiles with the profile areas in the same section can be classified by a clustering algorithm, and then the average value of the areas of each profile in the respective classifications is calculated, and the profile with the largest number of profiles in the same section and the largest average value of the profile areas is satisfied, namely the required target profile.
S30: pose adjustment, namely acquiring a minimum circumscribed rectangle rect of a target contour, calculating a center coordinate and a deflection angle of the minimum circumscribed rectangle rect, and correcting the target contour and placing the target contour in the center of an image by utilizing image translation and image rotation;
in the embodiment, firstly, four vertexes of a target contour circumscribed rectangle are obtained, then the four vertexes are contained in a point set, a target contour minimum circumscribed rectangle rect is calculated through the point set, and then the center coordinate and the deflection angle of the minimum circumscribed rectangle rect are calculated, which are also the center coordinate and the deflection angle of the element; then, the target contour is aligned and placed in the center of the image through image translation and image rotation;
further, setting the width of the image to width, the height of the image to height, and the element constraint angle Φ, the offset from the pixel point of the element to the center of the image is:
Δx＝rect.center.x–width/2；
Δy＝rect.center.y–height/2；
further, the image center offset formula is:
the image rotation matrix formula is:
the centre offset matrix is multiplied by the rotation matrix, i.e. M AT ×M AR The complete element pose correction formula can be obtained:
where x and y are the pixel locations of the original image,and->And correcting the position of the pixel point for the pose. Referring to fig. 7 to 8, fig. 7 is a schematic diagram of adjusting the pose after the SOP24 extracts the outline of the foot of the pin, and fig. 8 is a schematic diagram of adjusting the pose after the BGA extracts the outline of the solder ball.
S40: distinguishing the types of the elements, performing polygon fitting on the contours of the elements by improving a Douglas-Peucker algorithm to obtain the number of endpoints of the elements, and distinguishing pin elements and BGA elements according to the number of endpoints;
in this embodiment, because the foot profile of the pin-like element obtained in step S30 is rectangular-like, the solder ball profile of the BGA-like element is circular-like, and then the modified Douglas-Peucker algorithm is used to perform polygon fitting on the profile of the element, so as to obtain a majority of 4 pin foot end points of the pin-like element, wherein a minority of the pin foot end points of the pin-like element are 5 pin foot end points; the number of the solder ball contour end points of the BGA type element is 7 or 8.
The step of improving the Douglas-Peucker algorithm is as follows:
s401: firstly, finding a point A at the upper left corner of the polygonal contour, traversing and calculating another point B on the contour farthest from the point A, taking the point A and the point B as two initial end points, dividing the polygonal contour into two curves AB and BA, and taking a straight line AB as the chord of the curves AB and BA;
s402: two curves AB and BA were treated separately, taking curve AB as an example: firstly, obtaining a point C with the largest distance from a straight line segment AB on a curve AB, and calculating the distance d between the point C and the straight line AB;
s403: comparing the relation between the distance d and a preset distance threshold value threshold, and if the relation is smaller than the threshold value threshold, taking the straight line segment as an approximation of a curve, and finishing the curve processing;
s404: if the distance d is greater than the threshold value threshold, taking C as the other end point of the curve AB, dividing the curve into two sections of AC and CB, and repeating the steps for the two sections of curves respectively;
s405: and performing iterative processing for multiple times until all curves are processed, obtaining the number of fitting endpoints of the polygonal contour, and effectively distinguishing the rectangular-like pin contour of the pin element from the circular-like solder ball contour of the BGA element according to the difference of the number of fitting polygonal endpoints.
In the above steps, threshold=0.03×arclength (conductors [ i ], true), arcLength (conductors [ i ], true) is the perimeter of the current contour (true represents a closed curve), and then an average value is calculated for the number of fitting endpoints of all target contours. Then, the pin type elements and the BGA type elements can be distinguished according to the difference of the number of the terminals, and fig. 9 to 11 are schematic diagrams of polygonal fitting terminals.
S50: classifying the element types; firstly, moving a target element to an image center with an angle of 0 DEG, and taking the image center as a reference, and making scanning lines penetrating through element arrangement pins in the left, upper, right and lower directions of a minimum circumscribed rectangle rect of an element profile; and then obtaining the number of gray transition points on the current scanning line by using a gradient algorithm, taking one scanning line by 5 pixel units, respectively taking 3 scanning lines in each direction, and taking the numerical value with the number of gray transition points being even and the maximum number, wherein half of the numerical value is the pin number of the element in the direction.
The specific steps of the element classification in step S50 are:
s501: firstly, judging whether the contour number of the element is 1 and the endpoint number is 4, if so, the element is a sheet element, otherwise, the step S502 is entered;
s502: judging whether the contour number of the element is more than or equal to 3 and whether the end point average number is more than or equal to 7, if so, the element is a BGA element; otherwise, step S503 is entered;
s503: judging whether the contour number of the element is more than or equal to 3 and whether the end point average number is 4, if so, the element is a pin element.
In this embodiment, after the previous steps, the target element is moved to the image center and the angle is 0 °, at this time, the image center is the element center, so, based on the image center, scanning lines penetrating through pins of the element are respectively made in four directions of the left upper right lower side of the minimum circumscribed rectangle rect surrounding the element, the number of gray transition points (i.e. the point with gray value 0- >255 or 255- >0, 0 is the gray value of the black background, 255 is the gray value of the white outline) on the current scanning line can be obtained by using the gray gradient algorithm, then one scanning line is taken every 5 pixel units, 3 scanning lines are taken in each direction, the number of gray transition points is even and the number is the number of pins of the element in the direction is half of the number of pins of the element in the direction. The pin numbers which do not meet the conditions can be filtered out by utilizing the clustering operation of the pin spacing and the pin width, and referring to fig. 12, the pin numbers on the left and right sides of the SOP element are the correct pin numbers, while the pin spacing obviously does not meet the normal judgment category when the pins on the upper and lower sides are detected, and then the normal judgment category is filtered out.
Meanwhile, if the pin element is determined in step S503, the pin element is subdivided, which specifically includes the following steps:
s5301: judging whether the four-side pin number of the element is equal and whether the pin number is more than or equal to 4, if so, the element is a QFP element; otherwise, go to step S5302;
s5302: judging whether the opposite side pin numbers are equal and whether the pin numbers are more than or equal to 2, if so, the element is an SOP element; otherwise, enter step S5303;
s5303: judging whether the pin numbers at the two sides of the opposite sides are 1 and 2, if so, the element is an SOT element, and finishing the element classification of the pin class.
Reference is made to fig. 13, which is a schematic diagram of a self-classifying complete flow.
The application can automatically classify the surface mounting device (Surface Mounted Devices) commonly used by the SMT chip mounter based on geometric characteristics, firstly, image preprocessing including image filtering smoothing, binarization, morphological operation and contour filling is carried out; then extracting the target, namely searching the image contour, filtering non-target contours through a clustering algorithm, namely filtering root areas through pin elements, reserving foot contours, filtering Mark points of corners through BGA elements, and reserving solder ball contours with basically consistent areas; then, pose adjustment is carried out, a minimum circumscribed rectangle rect surrounding all the target contours is utilized to obtain a center coordinate and a deflection angle, and then the target is aligned and placed in the center of the image through translation and rotation; then utilizing an improved Douglas-Peucker algorithm to carry out polygon fitting on a target contour, firstly screening out sheet elements (resistance and capacitance) by combining the number of the contour, and distinguishing pin elements and BGA elements according to the number difference of the end points of the fitted contour; the number of pins in the four directions of the left, the upper, the right, the lower and the upper of the element is calculated by using a gray jump algorithm aiming at the pin element, SOT, SOP, QFP is distinguished according to the pin distribution type, and finally, the element self-classifying flow of automatic teaching is completed.
While the preferred embodiment of the present application has been described in detail, the present application is not limited to the embodiments, and those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present application, and the equivalent modifications or substitutions are included in the scope of the present application as defined in the appended claims.
Claims (10)
1. The component classification method for automatic teaching of the chip mounter is characterized by comprising the following steps:
s10: preprocessing an image; sequentially carrying out smoothing filtering, binarization threshold segmentation and interference point filtering on the image;
s20: extracting a target contour; performing contour searching on the processed image, classifying contours with contour areas in the same interval, and respectively calculating contour area average values of the contours, wherein the contours with the largest quantity of contours in the same interval and the largest contour area average value are target contours;
s30: pose adjustment; acquiring a minimum circumscribed rectangle rect of a target contour, calculating a center coordinate and a deflection angle of the minimum circumscribed rectangle rect, and correcting the target contour and placing the target contour in the center of an image by utilizing image translation and image rotation;
s40: distinguishing element types; performing polygon fitting on the target contours to obtain the number of endpoints of the element, then averaging the fitting endpoint numbers of all the target contours, and distinguishing the element types through endpoint number difference;
s50: classifying the element types; firstly, moving a target element to an image center with an angle of 0 DEG, taking the image center as a reference, making scanning lines penetrating through pins of element arrangement in the left, upper, right and lower directions of a minimum circumscribed rectangle rect of an element profile, obtaining the number of gray transition points on the scanning lines, then determining the number of the pins, and then classifying the element types.
2. The method for classifying elements according to claim 1, wherein in the step S30, the image width is set to width, the image height is height, and the element constraint angle Φ;
the offset of the element pixel point to the center of the image is:
Δx＝rect.center.x–width/2；
Δy＝rect.center.y–height/2；
the image center offset formula is:
the image rotation matrix formula is:
the centre offset matrix is multiplied by the rotation matrix, i.e. M AT ×M AR The formula is corrected for the element pose:
where x and y are the pixel locations of the original image,and->And correcting the position of the pixel point for the pose.
3. The automatic teaching component classifying method of chip mounter according to claim 1, wherein said step S40 is to perform polygon fitting on the component contour by modifying Douglas-Peucker algorithm.
4. The automatic teaching component classifying method for chip mounter according to claim 3, wherein said step of improving Douglas-Peucker algorithm comprises:
s401: firstly, finding a point A at the upper left corner of the polygonal contour, traversing and calculating another point B on the contour farthest from the point A, taking the point A and the point B as two initial end points, dividing the polygonal contour into two curves AB and BA, and taking a straight line AB as the chord of the curves AB and BA;
s402: respectively processing the two curves AB and BA; firstly, obtaining a point C with the largest distance from a straight line segment AB on a curve AB, and calculating the distance d between the point C and the straight line AB; the curve BA is also processed as described above;
s403: comparing the relation between the distance d and a preset distance threshold value threshold, and if the relation is smaller than the threshold value threshold, taking the straight line segment as an approximation of a curve, and finishing the curve processing;
s404: if the distance d is greater than the threshold value threshold, taking C as the other end point of the curve AB, dividing the curve into two sections of AC and CB, and repeating the steps for the two sections of curves respectively;
s405: and performing iterative processing for a plurality of times until all curves are processed, and obtaining the number of fitting endpoints of the polygonal contour.
5. The automatic teaching component sorting method of the chip mounter according to claim 4, wherein in said step S403: threshold=0.03×arclength (conductors [ i ], true), arcLength (conductors [ i ], true) being the circumference of the current contour (true representing a closed curve).
6. The automatic teaching component classifying method of the chip mounter according to claim 1, wherein the specific step of determining the number of pins in step S50 is: the number of gray transition points on the scanning line is obtained by utilizing a gradient algorithm, then one scanning line is taken by five pixel units, three scanning lines are taken in each direction, the number of the gray transition points is an even number and the number is the largest, and half of the number is the pin number of the element in the direction.
7. The automatic teaching component classifying method of the chip mounter according to claim 6, wherein the specific steps of component classification in step S50 are as follows:
s501: firstly, judging whether the contour number of the element is 1 and the endpoint number is 4, if so, the element is a sheet element, otherwise, the step S502 is entered;
s502: judging whether the contour number of the element is more than or equal to 3 and whether the end point average number is more than or equal to 7, if so, the element is a BGA element; otherwise, step S503 is entered;
s503: judging whether the contour number of the element is more than or equal to 3 and whether the end point average number is 4, if so, the element is a pin element.
8. The automatic teaching component classifying method of the chip mounter according to claim 7, wherein the step S503 is characterized in that the pin components are subdivided if the pin components are determined to be pin components, and the method specifically comprises the following steps:
s5301: judging whether the four-side pin number of the element is equal and whether the pin number is more than or equal to 4, if so, the element is a QFP element; otherwise, go to step S5302;
s5302: judging whether the opposite side pin numbers are equal and whether the pin numbers are more than or equal to 2, if so, the element is an SOP element; otherwise, enter step S5303;
s5303: judging whether the pin numbers at the two sides of the opposite sides are 1 and 2, if so, the element is an SOT element, and finishing the element classification of the pin class.
9. The automatic teaching component classifying method of the chip mounter according to claim 1, wherein in the step S10, a gaussian convolution is used to check the image for smoothing filtering, an OTSU method is used to perform binarization threshold segmentation on the image, and a morphological processing-open operation is used to perform interference point filtering on the image.
10. The method for classifying elements according to claim 1, wherein in step S20, a clustering algorithm is used to classify the contours with contour areas in the same interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310864914.1A CN116977721A (en) | 2023-07-13 | 2023-07-13 | Automatic teaching element classification method for chip mounter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310864914.1A CN116977721A (en) | 2023-07-13 | 2023-07-13 | Automatic teaching element classification method for chip mounter |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116977721A true CN116977721A (en) | 2023-10-31 |
Family
ID=88470540
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310864914.1A Pending CN116977721A (en) | 2023-07-13 | 2023-07-13 | Automatic teaching element classification method for chip mounter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116977721A (en) |
-
2023
- 2023-07-13 CN CN202310864914.1A patent/CN116977721A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109839385B (en) | Self-adaptive PCB defect visual positioning detection and classification system | |
| US9965847B2 (en) | Multi-type BGA chip visual recognition method using line based clustering | |
| CN109785316B (en) | Method for detecting apparent defects of chip | |
| CN105184770B (en) | A kind of soldered ball positioning and its parameter identification method for ball grid array pin chip | |
| Zhong et al. | Blob analyzation-based template matching algorithm for LED chip localization | |
| CN110334433B (en) | Automatic generation method for PCB (printed circuit board) packaging file | |
| CN109615609A (en) | A kind of solder joint flaw detection method based on deep learning | |
| CN109540925B (en) | Complex ceramic tile surface defect detection method based on difference method and local variance measurement operator | |
| CN114693610A (en) | Welding seam surface defect detection method, equipment and medium based on machine vision | |
| CN112115948A (en) | Chip surface character recognition method based on deep learning | |
| CN115019024B (en) | Visual recognition method of QFP | |
| CN112991283A (en) | Flexible IC substrate line width detection method based on super-pixels, medium and equipment | |
| CN112233116A (en) | Concave-convex mark visual detection method based on neighborhood decision and gray level co-occurrence matrix description | |
| CN114972575A (en) | Linear fitting algorithm based on contour edge | |
| CN112419260A (en) | PCB character area defect detection method | |
| CN111539429A (en) | Automatic circulation box positioning method based on image geometric features | |
| CN113393447B (en) | Needle tip true position detection method and system based on deep learning | |
| CN112419225B (en) | SOP type chip detection method and system based on pin segmentation | |
| CN108898584B (en) | Image analysis-based full-automatic veneered capacitor welding polarity discrimination method | |
| CN116977721A (en) | Automatic teaching element classification method for chip mounter | |
| CN111553885B (en) | SOT type chip pin parameter detection method based on rollback tree | |
| CN109977946B (en) | Hazelnut axial recognition method based on machine vision | |
| CN112418210B (en) | Intelligent classification method for tower inspection information | |
| CN112926589A (en) | Annular character segmentation and recognition method and system | |
| CN115908412B (en) | Bamboo strip defect detection method and terminal based on line laser image |
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 |