CN115187587A - Detection method and imaging system for continuous tin detection - Google Patents

Detection method and imaging system for continuous tin detection Download PDF

Info

Publication number
CN115187587A
CN115187587A CN202211087941.4A CN202211087941A CN115187587A CN 115187587 A CN115187587 A CN 115187587A CN 202211087941 A CN202211087941 A CN 202211087941A CN 115187587 A CN115187587 A CN 115187587A
Authority
CN
China
Prior art keywords
tin
area
image
detection
threshold
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
Application number
CN202211087941.4A
Other languages
Chinese (zh)
Other versions
CN115187587B (en
Inventor
冀伟
宫海坤
陈辉
查进
马腾
谢佩
王磊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Changzhou Mingseal Robotic Technology Co Ltd
Original Assignee
Changzhou Mingseal Robotic Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Changzhou Mingseal Robotic Technology Co Ltd filed Critical Changzhou Mingseal Robotic Technology Co Ltd
Priority to CN202211087941.4A priority Critical patent/CN115187587B/en
Publication of CN115187587A publication Critical patent/CN115187587A/en
Application granted granted Critical
Publication of CN115187587B publication Critical patent/CN115187587B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/15—Correlation function computation including computation of convolution operations
    • G06F17/153—Multidimensional correlation or convolution
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/20—Image enhancement or restoration by the use of local operators
    • G06T5/90—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
    • 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

Abstract

The invention discloses a detection method and an imaging system for continuous tin detection, which are used for imaging a background part of a bottom plate of a product in a defocusing mode while focusing a solder paste part to be detected; firstly, manually drawing a matching positioning area and a continuous tin detection area; performing affine matching and positioning on the tin connection detection area in the operation process, calculating the entropy and the contrast of the image area, substituting the entropy and the contrast into a formula to obtain an evaluation index, comparing the evaluation index with a preset threshold value for judgment, performing secondary judgment if the condition is met, otherwise, considering that the tin connection defect does not exist in the tin paste surface image; the secondary judgment method is to process the image by using a convolution filter, so that the solder paste is effectively distinguished from the background part, and then the detection result is obtained by threshold segmentation and calculation of area and roundness characteristic judgment. The invention can effectively extract the solder paste part and reduce the false detection rate.

Description

Detection method and imaging system for continuous tin detection
Technical Field
The invention relates to the technical field of visual detection, in particular to a detection method and an imaging system for continuous tin detection.
Background
In the MEMS thin plate manufacturing industry, strict quality control needs to be carried out on different processes, and the tin paste is detected as one ring of the process, so that the phenomenon of tin connection on the background part of a product bottom plate is not allowed. The image-based solder paste detection method is common, but the condition that the imaging characteristics of the solder paste and the background of the product bottom plate are similar exists, and the condition of false extraction exists in the traditional image processing, so that the higher false judgment rate is caused.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art.
Therefore, the invention provides a detection method and an imaging system for continuous tin detection, which can effectively extract a tin paste part and reduce the false detection rate.
The detection method for continuous tin detection according to the embodiment of the invention comprises the following steps: step 1, collecting images: acquiring a clearly imaged solder paste surface image by using a camera lens, wherein the solder paste surface image comprises a bottom plate background and a solder paste part; step 2, image processing, matching and positioning: manually drawing a continuous tin detection area on the tin paste surface image; meanwhile, drawing a corresponding characteristic area as a matching positioning template area; step 3, executing detection and simulationAnd (3) jetting a continuous tin detection area: searching a matching positioning template area, and carrying out affine transformation on the drawn continuous tin detection area according to the position of the searched matching positioning template area; step 4, solving the entropy of the image area and calculating the contrast of the image area: after affine to the continuous tin detection area, solving entropy of the continuous tin detection area; and calculating the contrast of the image of the continuous tin detection area; step 5 of calculating an evaluation index
Figure 184550DEST_PATH_IMAGE001
And manually presetting a first threshold value
Figure 792249DEST_PATH_IMAGE002
: comprehensively considering two indexes of contrast and entropy of the continuous tin detection area image, and simultaneously judging the weight of the entropy to be larger than the contrast; will evaluate the index
Figure 375677DEST_PATH_IMAGE001
And a first threshold value
Figure 828655DEST_PATH_IMAGE002
And comparing to judge whether the solder paste surface image has the continuous solder defect.
The invention also provides an imaging system, which comprises a camera lens for acquiring the tin paste image on the bottom plate of the product; in the focusing process of the camera lens, a focusing plane is set to be a tin paste surface, and a background area of a product bottom plate is adjusted to be in a defocusing state; setting the depth of field of the imaging system between a first plane and a second plane, wherein the first plane is a depth of field near boundary close to the camera lens, and the second plane is a depth of field far boundary far away from the camera lens; the second plane is higher than the lowest plane of the product base plate, and the second plane is lower than the highest plane of the solder paste; when the solder paste surface is imaged clearly, the solder paste exists on the corresponding position of the product bottom plate; when the image is in the out-of-focus state, no solder paste exists on the corresponding position of the bottom plate of the product.
The method has the advantages that the method images the background part of the bottom plate of the product in a defocusing mode while focusing the solder paste part to be detected; firstly, manually drawing a matching positioning area and a continuous tin detection area; performing affine matching and positioning on the tin connection detection area in the operation process, calculating the entropy and contrast of the image area, substituting the entropy and contrast into a formula to obtain an evaluation index, comparing the evaluation index with a preset threshold value for judgment, performing secondary judgment if the condition is met, and otherwise, determining that the tin connection defect does not exist in the tin paste surface image; the secondary judgment method is that a convolution filter is used for processing the image, so that the solder paste and the background part are effectively distinguished, and then the detection result is obtained through threshold segmentation and calculation of area and roundness characteristic judgment; the invention can effectively extract the solder paste part and reduce the false detection rate.
According to an embodiment of the present invention, in the step 5, when the index is evaluated
Figure 813928DEST_PATH_IMAGE003
Less than a first threshold
Figure 592528DEST_PATH_IMAGE004
And if so, determining that the tin connection defect does not exist in the tin paste surface image.
According to an embodiment of the present invention, in the step 5, when the index is evaluated
Figure 663253DEST_PATH_IMAGE003
Greater than or equal to a first threshold value
Figure 919922DEST_PATH_IMAGE004
And preliminarily judging that the tin-connected defect exists in the tin paste surface image, and entering secondary judgment.
According to one embodiment of the invention, the secondary judgment method is as follows: first, the
Figure 759702DEST_PATH_IMAGE005
Designing a convolution filter for processing a tin paste surface image based on the imaging characteristics of the tin paste surface, wherein the convolution filter is used for extracting the texture characteristics of the tin paste, so that the tin paste is effectively distinguished from a background area; first, the
Figure 959737DEST_PATH_IMAGE006
Performing convolution operation on the solder paste surface image and a convolution kernel of a convolution filter to obtain a convolution image; first, the
Figure 252178DEST_PATH_IMAGE007
When the color characteristic change of a solder paste area of the convolution image is obvious and the convolution image is effectively distinguished from a product bottom plate background part, extracting a white area through threshold segmentation, and meanwhile, calculating an area characteristic value of a threshold segmentation result area
Figure 578117DEST_PATH_IMAGE008
Characteristic value of degree of roundness
Figure 272404DEST_PATH_IMAGE009
By counting the area characteristic values
Figure 127227DEST_PATH_IMAGE008
And characteristic value of roundness
Figure 172544DEST_PATH_IMAGE009
The two characteristic values are respectively set as second threshold values
Figure 36595DEST_PATH_IMAGE010
And a third threshold value
Figure 585388DEST_PATH_IMAGE011
To perform the second determination.
According to an embodiment of the invention, in said first step
Figure 876692DEST_PATH_IMAGE007
In the step, the area characteristic value is set
Figure 612567DEST_PATH_IMAGE008
Second threshold value
Figure 545887DEST_PATH_IMAGE010
For characteristic value of roundness
Figure 916564DEST_PATH_IMAGE009
Setting a third threshold value
Figure 175507DEST_PATH_IMAGE011
。
According to an embodiment of the invention, in said first step
Figure 133098DEST_PATH_IMAGE007
In the step, when the area characteristic value
Figure 135689DEST_PATH_IMAGE008
Greater than a second threshold
Figure 862337DEST_PATH_IMAGE010
And a characteristic value of roundness
Figure 26602DEST_PATH_IMAGE009
Greater than a third threshold
Figure 471490DEST_PATH_IMAGE011
And judging that the tin-connected defect exists in the tin paste surface image.
According to an embodiment of the invention, in said first step
Figure 12193DEST_PATH_IMAGE007
In the step, when the area characteristic value
Figure 858926DEST_PATH_IMAGE008
Less than or equal to the second threshold value
Figure 459672DEST_PATH_IMAGE010
And judging that the tin paste surface image does not have the tin connection defect.
According to an embodiment of the invention, in said first step
Figure 126276DEST_PATH_IMAGE007
In the step, when the roundness characteristic value
Figure 470670DEST_PATH_IMAGE009
Less than or equal to a third threshold value
Figure 936024DEST_PATH_IMAGE012
And judging that the tin paste surface image does not have the tin connection defect.
According to an embodiment of the invention, the first plane is arranged parallel to the second plane.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
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 introduced below, it is obvious that the drawings in the description below are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic structural view of an imaging system of the present invention;
FIG. 2 is a picture of an image of a solder paste surface;
FIG. 3 is a schematic view of a drawing of a wicking detection zone on a solder paste side imaging image;
FIG. 4 is a schematic illustration of a matching location template region;
FIG. 5 is an image before convolution with a convolution kernel in a quadratic decision method;
FIG. 6 is an image after convolution operation with a convolution kernel in a quadratic decision method;
FIG. 7 is a flow chart of the detection method of the present invention.
The reference numbers in the figures are: 1. a product base plate; 2. tin paste; 3. a camera lens; A. a first plane; B. a second plane; 4. a floor background; 5. a solder paste portion; 6. a continuous tin detection area; 7. and matching and positioning the template area.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present 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.
In the description of the present invention, it is to be understood that the terms "one side", "the other side", "both sides", "between", "middle", "upper", "lower", etc., indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element referred to must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, should not be construed as limiting the present invention.
In the description of the present invention, it should be noted that unless otherwise explicitly stated or limited, the terms "disposed" and "connected" should be interpreted broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected, directly connected, or indirectly connected through an intermediate medium. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
The following describes a detection method and an imaging system for detecting continuous tin according to an embodiment of the present invention with reference to the drawings.
Referring to fig. 1, the imaging system for continuous tin inspection according to the present invention images the background of the product substrate by defocusing the background of the product substrate while focusing the solder paste to be inspected, and includes a camera lens 3 for capturing the image of the solder paste 2 on the product substrate 1; in the focusing process of the camera lens 3, a focusing plane is set to be a tin paste surface, and the background area of the product base plate 1 is adjusted to be in a defocusing state. Setting the depth of field of the imaging system to be between a first plane A and a second plane B, wherein the first plane A and the second plane B are distributed in parallel, namely the product bottom plate can clearly image between the first plane A and the second plane B, the first plane A is a depth of field near boundary close to the camera lens 3, and the second plane B is a depth of field far boundary far away from the camera lens 3; the second plane B is higher than the lowest plane of the product base plate 1 and lower than the highest plane of the solder paste 2; when the solder paste surface is imaged clearly, the solder paste 2 exists on the corresponding position of the product base plate 1; when the imaging is in the out-of-focus state, the solder paste 2 does not exist on the corresponding position of the product base plate 1.
Referring to fig. 7, a detection method for continuous tin detection includes the following steps:
step 1, collecting images: a clearly imaged solder paste surface image is captured using the camera lens 3, which includes the backplane background 4 and the solder paste portion 5, as shown in fig. 2.
Step 2, image processing, matching and positioning: manually drawing a continuous tin detection area 6 on the tin paste surface image, as shown in fig. 3; meanwhile, a corresponding feature region (usually, one feature region is drawn) is drawn as a matching positioning template region 7, as shown in fig. 4.
And 3, executing detection: searching the matching positioning template area 7, and carrying out affine transformation on the drawn continuous tin detection area 6 according to the position of the matching positioning template area 7 obtained by searching, namely limiting the continuous tin detection area 6, so that the detection range is reduced, the detection efficiency can be improved, and the interference of other areas is reduced.
In the step 2, the matched positioning template area 7 contains a coordinate point set of a continuous tin detection area before affine transformation
Figure 442092DEST_PATH_IMAGE013
In the detection process executed in the step 3, matching the positioning template area 7 to obtain a continuous tin detection area coordinate point set after affine transformation
Figure 861572DEST_PATH_IMAGE014
Affine transformation matrix
Figure 744077DEST_PATH_IMAGE015
Calculated by the following formula:
Figure 565403DEST_PATH_IMAGE016
（1）
step 4, solving entropy and calculating contrast: after the continuous tin detection area 6 is affine, the entropy of the continuous tin detection area 6 is obtained; and the contrast of the image of the wicking detection zone 6 is calculated.
The calculation formula of the entropy H of the continuous tin detection area is as follows:
Figure 242372DEST_PATH_IMAGE017
（2）
wherein, the meaning represented by each symbol in the formula (2) is specifically as follows:
Figure 883569DEST_PATH_IMAGE018
and expressing the evaluation index of the gray value of the pixel point in the continuous tin detection area image and the gray value distribution of the adjacent pixel.
Figure 569765DEST_PATH_IMAGE018
The calculation formula of (a) is as follows:
Figure 245597DEST_PATH_IMAGE019
（3）
wherein, the meaning represented by each symbol in the formula (3) is specifically as follows:
i represents the gray value of the pixel;
j represents a domain gray level mean value;
n represents the scale of the image of the continuous tin detection area;
f represents oneDimension array
Figure 359046DEST_PATH_IMAGE020
The frequency of occurrence.
Contrast of continuous tin detection area
Figure 487539DEST_PATH_IMAGE021
The calculation formula of (a) is as follows:
Figure 711847DEST_PATH_IMAGE022
（4）
wherein, the meaning represented by each symbol in the formula (4) is specifically as follows:
Figure 740721DEST_PATH_IMAGE023
express a gray difference between adjacent pixels, and
Figure 25072DEST_PATH_IMAGE024
；
Figure 640861DEST_PATH_IMAGE025
representing a gray level difference between adjacent pixels of
Figure 872122DEST_PATH_IMAGE026
The probability of pixel distribution.
Step 5, calculating an evaluation index T and manually presetting a first threshold value
Figure 53705DEST_PATH_IMAGE027
: comprehensively considering two indexes of contrast and entropy of the image of the continuous tin detection area 6, simultaneously setting the proportionality coefficients to be 0.4 and 0.6 respectively according to human experience, wherein the judgment weight of the entropy is greater than the contrast; the evaluation index T is compared with a first threshold value
Figure 977798DEST_PATH_IMAGE027
And comparing to judge whether the solder paste surface image has the tin connection defect.
Wherein the first threshold value
Figure 877621DEST_PATH_IMAGE027
The setting method comprises the following steps: calculating the evaluation index T of a plurality of products without continuous tin defects, and calculating the average value of the evaluation indexes T
Figure 646994DEST_PATH_IMAGE028
(ii) a The user obtains the judgment allowable deviation according to the process requirement and the control range
Figure 683083DEST_PATH_IMAGE029
Determining the allowable deviation
Figure 778078DEST_PATH_IMAGE029
Is in the value range of
Figure 899618DEST_PATH_IMAGE030
，
The first threshold value
Figure 472682DEST_PATH_IMAGE031
The calculation formula of (a) is as follows:
Figure 628857DEST_PATH_IMAGE032
（5）
the calculation formula of the evaluation index T is as follows:
Figure 133568DEST_PATH_IMAGE033
（6）
first threshold value
Figure 742404DEST_PATH_IMAGE034
Preliminary determination of the image of the continuous tin detection area, the first threshold value
Figure 119159DEST_PATH_IMAGE034
The method is open to the user, and the user can set the method by himself.
When the evaluation index T is smaller than the first threshold value
Figure 129840DEST_PATH_IMAGE034
And if so, determining that the tin connection defect does not exist in the tin paste surface image.
When the evaluation index T is greater than or equal to the first threshold value
Figure 301058DEST_PATH_IMAGE034
And preliminarily judging that the tin-connected defect exists in the tin paste surface image, and entering secondary judgment.
The secondary judgment method comprises the following steps:
designing a convolution filter for processing a tin paste surface image based on the imaging characteristics of the tin paste surface, wherein the convolution filter is used for extracting the texture characteristics of the tin paste 2, so that the tin paste 2 is effectively distinguished from a background area; the convolution kernel K of the convolution filter is a matrix as follows:
Figure 397190DEST_PATH_IMAGE035
（7）
and (2) carrying out convolution operation on the solder paste surface image and a convolution kernel of a convolution filter to obtain a convolution image. The specific calculation formula of the convolution operation is as follows:
Figure 577636DEST_PATH_IMAGE036
（8）
wherein, the meaning represented by each symbol in the formula (8) is specifically as follows:
Figure 708403DEST_PATH_IMAGE037
coordinates representing an image of the solder paste surface;
Figure 50523DEST_PATH_IMAGE038
representing the solder paste surface image after convolution operation;
Figure 368372DEST_PATH_IMAGE039
representing a solder paste surface image before convolution operation;
Figure 352508DEST_PATH_IMAGE040
representing the convolution operator.
And (3) when the color characteristic of the solder paste area of the convolution image is obviously changed and is effectively distinguished from the background part of the bottom plate of the product, extracting a white area by threshold segmentation, simultaneously calculating an area characteristic value S and a roundness characteristic value C of a threshold segmentation result area, and respectively setting second threshold values for the area characteristic value S and the roundness characteristic value C
Figure 337782DEST_PATH_IMAGE041
And a third threshold value
Figure 349338DEST_PATH_IMAGE042
To perform the second determination.
The calculation formula of the area characteristic value S is as follows:
Figure 154483DEST_PATH_IMAGE043
（9）
the meaning of each symbol in the formula (9) is specifically as follows:
r represents a segmentation result region to be calculated;
Figure 676731DEST_PATH_IMAGE044
representing the coordinates within region R.
The calculation formula of the roundness characteristic value C is as follows:
Figure 516511DEST_PATH_IMAGE045
（10）
the meaning of each symbol in the formula (10) is specifically as follows:
s represents an area characteristic value of the region R;
Figure 200433DEST_PATH_IMAGE046
representing the maximum from the center of the region R to the region contour point.
Setting a second threshold value for the area characteristic value S
Figure 758453DEST_PATH_IMAGE047
Setting a third threshold value for the roundness characteristic value C
Figure 553234DEST_PATH_IMAGE048
。
Second threshold value
Figure 981941DEST_PATH_IMAGE047
Is set up in an interval of
Figure 633503DEST_PATH_IMAGE049
The calculation method for setting the standard is as follows: when the user provides the upper limit area according to the product process requirement
Figure 616502DEST_PATH_IMAGE050
Upper limit of area
Figure 11711DEST_PATH_IMAGE050
Is in the value range of
Figure 826084DEST_PATH_IMAGE049
Then the interval is set to
Figure 615923DEST_PATH_IMAGE051
。
Third threshold value
Figure 882956DEST_PATH_IMAGE048
Is set in an interval of
Figure 285119DEST_PATH_IMAGE052
Setting up a standard meterThe calculation method comprises the following steps: when the user provides an upper limit according to the product process requirement
Figure 422839DEST_PATH_IMAGE053
And lower limit
Figure 416203DEST_PATH_IMAGE054
Upper limit of
Figure 373794DEST_PATH_IMAGE055
Is in the value range of
Figure 376385DEST_PATH_IMAGE056
Lower limit of
Figure 368612DEST_PATH_IMAGE057
Is in a range of values
Figure 532877DEST_PATH_IMAGE049
Then the interval is set to
Figure 977765DEST_PATH_IMAGE058
。
When the area characteristic value S is larger than the second threshold value
Figure 518468DEST_PATH_IMAGE059
And the roundness characteristic value C is larger than a third threshold value
Figure 598157DEST_PATH_IMAGE060
And judging that the tin-connected defect exists in the tin paste surface image.
When the area characteristic value S is less than or equal to the second threshold value
Figure 198903DEST_PATH_IMAGE059
And judging that the tin paste surface image does not have the tin connection defect.
When the roundness characteristic value C is less than or equal to a third threshold value
Figure 131087DEST_PATH_IMAGE060
If so, it is determined that the solder paste surface image does not existAnd (4) tin connection defects.
Because the reject ratio of production operation is generally lower, and a large amount of qualified products can obtain results only through primary judgment, the overall efficiency of equipment can be improved by adopting a secondary judgment method, and meanwhile, the misjudgment rate can be effectively reduced by secondary judgment.
The image of fig. 5 is convolved with a convolution kernel to obtain a resultant image as shown in fig. 6. It can be seen from fig. 5 and 6 that the color feature of the solder paste area is obviously changed and can be effectively distinguished from the background part of the product base plate. And subsequently, extracting a white region by threshold segmentation, calculating an area characteristic value and a roundness characteristic value of a region of a threshold segmentation result, respectively setting thresholds for the two characteristic values to perform secondary judgment, and judging that the picture has the continuous tin defect if the judgment condition is met.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.

Claims (10)

1. A detection method for continuous tin detection is characterized by comprising the following steps:
step 1, collecting images: a camera lens (3) is used for collecting a clearly imaged solder paste surface image, and the solder paste surface image comprises a bottom plate background (4) and a solder paste part (5);
step 2, image processing, matching and positioning: manually drawing a continuous tin detection area (6) on the tin paste surface image; meanwhile, drawing a corresponding characteristic region as a matching positioning template region (7);
step 3, detection is executed, and an affine continuous tin detection area: searching a matching positioning template area (7), and carrying out affine transformation on the drawn continuous tin detection area (6) according to the position of the matching positioning template area (7) obtained by searching;
step 4, solving the entropy of the image area and calculating the contrast of the image area: after the continuous tin detection area (6) is affine, the entropy of the continuous tin detection area (6) is obtained; and calculating the contrast of the image of the tin-connecting detection area (6);
step 5, calculating an evaluation index T and manually presetting a first threshold Tthresh: two indexes of contrast and entropy of the image of the continuous tin detection area (6) are comprehensively considered, and meanwhile, the judgment weight of the entropy is larger than the contrast; and comparing the evaluation index T with a first threshold Tthresh to judge whether the tin-connecting defect exists in the tin paste surface image.
2. The detection method according to claim 1, characterized in that: in the step 5, when the evaluation index T is smaller than the first threshold Tthresh, the tin-connected defect does not exist in the tin paste surface image.
3. The detection method according to claim 1, characterized in that: in the step 5, when the evaluation index T is greater than or equal to the first threshold Tthresh, the tin-connecting defect of the tin paste surface image is preliminarily determined, and secondary determination is carried out.
4. The detection method according to claim 3, wherein the secondary determination method is:
first, the
Figure 260197DEST_PATH_IMAGE001
Designing a convolution filter for processing a tin paste surface image based on the imaging characteristics of the tin paste surface, wherein the convolution filter is used for extracting the texture characteristics of the tin paste (2), so that the tin paste (2) is effectively distinguished from a background area;
first, the
Figure 337874DEST_PATH_IMAGE002
Performing convolution operation on the solder paste surface image and a convolution kernel of a convolution filter to obtain a convolution image;
first, the
Figure 511367DEST_PATH_IMAGE003
And when the color characteristic of a solder paste area of the convolution image is obviously changed and effectively distinguished from a background part of a product bottom plate, extracting a white area through threshold segmentation, meanwhile, calculating an area characteristic value S and a roundness characteristic value C of a threshold segmentation result area, and respectively setting a second threshold Sthresh and a third threshold Cthresh for the area characteristic value S and the roundness characteristic value C to carry out secondary judgment.
5. The detection method according to claim 4, characterized in that: at the first stage
Figure 725311DEST_PATH_IMAGE004
In the step, a second threshold Sthresh is set for the area characteristic value S, and a third threshold Cthresh is set for the roundness characteristic value C.
6. The detection method according to claim 5, characterized in that: at the first stage
Figure 693267DEST_PATH_IMAGE004
In the step, when the area characteristic value S is larger than a second threshold value Sthresh and the roundness characteristic value C is larger than a third threshold value Cthresh, the tin-connecting defect of the tin paste surface image is judged.
7. The detection method according to claim 4, characterized in that: at the first place
Figure 258240DEST_PATH_IMAGE004
In the step, when the area characteristic value S is less than or equal to the second threshold value Sthresh, the tin-connecting defect of the tin paste surface image is judged to be absent.
8. The detection method according to claim 4, characterized in that: at the first place
Figure 907527DEST_PATH_IMAGE004
In the step, when the roundness characteristic value C is less than or equal to a third threshold Cthresh, the tin-connecting defect of the tin paste surface image is judged to be absent.
9. An imaging system implementing the detection method of any one of claims 1-8, characterized by: comprises a camera lens (3) used for collecting the image of the tin paste (2) on the product bottom plate (1); in the focusing process of the camera lens (3), a focusing plane is set to be a tin paste surface, and a background area of the product base plate (1) is adjusted to be in a defocusing state;
setting the depth of field of the imaging system between a first plane (A) and a second plane (B), wherein the first plane (A) is a depth of field near boundary close to the camera lens (3), and the second plane (B) is a depth of field far boundary far away from the camera lens (3); the second plane (B) is higher than the lowest plane of the product base plate (1) and lower than the highest plane of the solder paste (2);
when the tin paste surface is imaged clearly, the tin paste (2) exists on the corresponding position of the product base plate (1);
when the imaging is in the out-of-focus state, the solder paste (2) does not exist on the corresponding position of the product base plate (1).
10. The imaging system of claim 9, wherein: the first plane (A) and the second plane (B) are distributed in parallel.
CN202211087941.4A 2022-09-07 2022-09-07 Detection method and imaging system for continuous tin detection Active CN115187587B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211087941.4A CN115187587B (en) 2022-09-07 2022-09-07 Detection method and imaging system for continuous tin detection

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211087941.4A CN115187587B (en) 2022-09-07 2022-09-07 Detection method and imaging system for continuous tin detection

Publications (2)

Publication Number Publication Date
CN115187587A true CN115187587A (en) 2022-10-14
CN115187587B CN115187587B (en) 2022-11-29

Family

ID=83523659

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211087941.4A Active CN115187587B (en) 2022-09-07 2022-09-07 Detection method and imaging system for continuous tin detection

Country Status (1)

Country Link
CN (1) CN115187587B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103824904A (en) * 2014-01-28 2014-05-28 深圳市九洲光电科技有限公司 Manufacturing method of LED package substrate
CN204514827U (en) * 2015-03-24 2015-07-29 青岛歌尔声学科技有限公司 A kind of even tin pick-up unit
CN106626758A (en) * 2016-12-24 2017-05-10 大连日佳电子有限公司 Method for intelligently detecting residual amount of solder paste of soldering paste printer
CN108960306A (en) * 2018-06-22 2018-12-07 西安电子科技大学 Tin cream detection threshold value optimization method based on SMT big data

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103824904A (en) * 2014-01-28 2014-05-28 深圳市九洲光电科技有限公司 Manufacturing method of LED package substrate
CN204514827U (en) * 2015-03-24 2015-07-29 青岛歌尔声学科技有限公司 A kind of even tin pick-up unit
CN106626758A (en) * 2016-12-24 2017-05-10 大连日佳电子有限公司 Method for intelligently detecting residual amount of solder paste of soldering paste printer
CN108960306A (en) * 2018-06-22 2018-12-07 西安电子科技大学 Tin cream detection threshold value optimization method based on SMT big data

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
苏珊 等: "基于机器视觉的SMT元件引脚连锡自动检测", 《组合机床与自动化加工技术》 *

Also Published As

Publication number Publication date
CN115187587B (en) 2022-11-29

Similar Documents

Publication Publication Date Title
CN108460757B (en) Mobile phone TFT-LCD screen Mura defect online automatic detection method
US20080075385A1 (en) Detection and Correction of Flash Artifacts from Airborne Particulates
Zakaria et al. Object shape recognition in image for machine vision application
CN110648330B (en) Defect detection method for camera glass
CN111932490B (en) Visual system grabbing information extraction method for industrial robot
CN111667475A (en) Machine vision-based Chinese date grading detection method
CN115274486B (en) Semiconductor surface defect identification method
CN111242888A (en) Image processing method and system based on machine vision
CN107170002B (en) Automatic image focusing method and device
CN112308843A (en) Camera overexposure abnormity adjusting method and system for photovoltaic cell panel image acquisition
CN115272350A (en) Method for detecting production quality of computer PCB mainboard
KR102242996B1 (en) Method for atypical defects detect in automobile injection products
CN112200790A (en) Cloth defect detection method, device and medium
CN111638218A (en) Method for detecting surface defects of coating
CN114359251A (en) Automatic identification method for concrete surface damage
CN115187587B (en) Detection method and imaging system for continuous tin detection
WO2018068414A1 (en) Detection method and device for resistor having color bands, and automated optical inspection system
CN115131250A (en) Intelligent machine tool component identification method for machine tool assembly
CN114913071A (en) Underwater image splicing method integrating feature point matching of brightness region information
CN114354631A (en) Valve blank surface defect detection method based on vision
CN114638807A (en) Metal plate surface defect detection method based on deep learning
CN114240920A (en) Appearance defect detection method
CN111563869B (en) Stain test method for quality inspection of camera module
CN109272540B (en) SFR automatic extraction and analysis method of image of graphic card
CN108335296B (en) Polar plate identification device and method

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