CN111415327B - PCB image block sampling device and method based on correlation analysis - Google Patents
PCB image block sampling device and method based on correlation analysis Download PDFInfo
- Publication number
- CN111415327B CN111415327B CN202010104106.1A CN202010104106A CN111415327B CN 111415327 B CN111415327 B CN 111415327B CN 202010104106 A CN202010104106 A CN 202010104106A CN 111415327 B CN111415327 B CN 111415327B
- Authority
- CN
- China
- Prior art keywords
- pcb
- sampling
- image
- module
- correlation analysis
- 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.)
- Active
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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G06T7/70—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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30141—Printed circuit board [PCB]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a PCB image block sampling device and method based on correlation analysis, wherein the device mainly comprises: the device comprises a projection module, a correlation analysis module, a threshold calculation module and a partition module; the projection module is used for projecting the gray level image to a two-dimensional coordinate system to generate a projection array; the correlation analysis module is used for carrying out data correlation analysis on the projection array to generate an autocorrelation coefficient sequence; the threshold calculation module is used for calculating the autocorrelation coefficient sequence by using a correlation threshold algorithm to obtain a partition threshold; the partition module is used for processing the PCB gray level image by utilizing the autocorrelation coefficient sequence and the partition threshold value to generate an area coordinate list of the PCB daughter board; the sampling module is used for sampling image blocks of the PCB gray level image according to the area coordinate list of the PCB daughter board and determining the coordinates of the sampling frame. The device reduces the calculated amount, improves the detection speed and the detection precision of the PCB defects, and is suitable for partitioning and sampling other images.
Description
Technical Field
The invention relates to the technical field of computer software engineering, in particular to a PCB image block sampling device and method based on correlation analysis.
Background
When a Printed Circuit Board (PCB) is detected by using a Convolutional Neural network, it is usually necessary to load a PCB image to be detected into a GPU (Graphics Processing Unit), and then perform inference by using a CNN (Convolutional Neural network). However, in an actual production process, each complete PCB in the production line includes several identical small PCBs due to process flow and efficiency considerations. The image obtained by the camera is very large, on the order of 1 hundred million pixels. Due to the capacity limitation, such a large picture cannot be loaded into the GPU for detection at one time, and therefore, a suitable segmentation method needs to be found to segment the large picture into small pictures for detection.
The traditional method is to directly divide the image into a plurality of adjacent rectangular areas or a plurality of rectangular areas with overlapped areas. The two methods need to equally detect a large number of hollow areas and PCB areas in the middle, and a large amount of calculation force is wasted. Therefore, a new technique for PCB image segmentation is urgently needed.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the related art.
To this end, an object of the present invention is to provide a PCB image block sampling apparatus based on correlation analysis.
Another objective of the present invention is to provide a PCB image block sampling method based on correlation analysis, which reduces the amount of computation and improves the detection speed and detection accuracy of PCB defects.
In order to achieve the above object, an embodiment of the present invention provides a PCB image block sampling apparatus based on correlation analysis, including: the image acquisition module is used for acquiring a gray level image of the PCB; the projection module is connected with the image acquisition module and is used for projecting the gray level image to a two-dimensional coordinate system to obtain a projection array; the correlation analysis module is connected with the projection module and is used for performing data correlation analysis on the projection array to generate an autocorrelation coefficient sequence; the threshold calculation module is connected with the correlation analysis module and is used for processing the autocorrelation coefficient sequence by utilizing a correlation threshold algorithm to obtain a classification region division threshold; the partitioning module is respectively connected with the threshold value calculating module, the correlation analyzing module and the image acquisition module, and processes the gray level image by utilizing the autocorrelation coefficient sequence and the classification region partitioning threshold value to obtain a region coordinate list of the PCB daughter board; and the sampling module is respectively connected with the partitioning module and the image acquisition module and is used for sampling image blocks in the gray level image according to the area coordinate list of the PCB daughter board and determining the position coordinates of the sampling frame.
According to the PCB image block sampling device based on correlation analysis, purposefully sampling is carried out on the image by utilizing the correlation of the gray value of the PCB image, the detection is focused on the functional area instead of the non-functional area, so that the calculation is concentrated on the PCB attention area, the calculation amount is reduced, and the detection speed and the detection precision of the PCB defects are improved.
In addition, the PCB image block sampling device based on correlation analysis according to the above embodiment of the present invention may further have the following additional technical features:
further, in one embodiment of the present invention, the self-similarity at the distance of the offset of the elements in the autocorrelation coefficient sequence is determined by the size of the element value.
Further, in an embodiment of the present invention, the partitioning module is specifically configured to:
judging in the autocorrelation coefficient sequence by utilizing the classification region division threshold, separating each peak value of which the gray level image coordinate projection is larger than the classification region division threshold, and determining each peak value coordinate;
when the representative image of each peak value coordinate is repeated after moving for a certain distance in the corresponding direction, calculating the deviation value of the sampling frame according to the area size of the daughter board, the size of the sampling frame and the repetition rate, and then obtaining the area coordinate list of the PCB daughter board according to the deviation value of the sampling frame and the size of the sampling frame.
Further, in an embodiment of the present invention, the sampling module is specifically configured to:
acquiring the height and width of each PCB sub-board area;
determining the size of a sampling frame and the sampling repetition rate according to the area coordinate list of the PCB daughter board;
and processing the size of the sampling frame, the sampling repetition rate, the height of each PCB sub-board area and the width of each PCB sub-board area, and solving the coordinates of the sampling frame.
Further, in one embodiment of the present invention, the size of the sampling box is determined by calculation.
In order to achieve the above object, another embodiment of the present invention provides a PCB image block sampling method based on correlation analysis, which includes the following steps: collecting a gray level image of the PCB; projecting the gray level image to a two-dimensional coordinate system to obtain a projection array; performing data correlation analysis on the projection array to generate an autocorrelation coefficient sequence; processing the autocorrelation coefficient sequence by using a correlation threshold algorithm to obtain a classification region division threshold; processing the gray level image by utilizing the autocorrelation coefficient sequence and the classification region division threshold value to obtain a region coordinate list of the PCB daughter board; and sampling image blocks in the gray images according to the area coordinate list of the PCB daughter boards, and determining the position coordinates of a sampling frame.
According to the PCB image block sampling method based on correlation analysis, purposeful sampling is carried out on the image by utilizing the correlation of the gray value of the PCB image, the detection is focused on the functional area instead of the non-functional area, so that the calculation is concentrated in the PCB attention area, the calculation amount is reduced, and the detection speed and the detection precision of the PCB defects are improved.
In addition, the PCB image block sampling method based on correlation analysis according to the above embodiment of the present invention may further have the following additional technical features:
further, in one embodiment of the present invention, the self-similarity at the distance of the offset of the elements in the autocorrelation coefficient sequence is determined by the size of the element value.
Further, in an embodiment of the present invention, the processing the grayscale image, the autocorrelation coefficient sequence, and the classification region division threshold to obtain a region coordinate list of a PCB sub-board includes:
judging in the autocorrelation coefficient sequence by utilizing the classification region division threshold, separating each peak value of which the gray level image coordinate projection is larger than the classification region division threshold, and determining each peak value coordinate;
and when the representative image of each peak value coordinate is repeated after moving for a certain distance in the corresponding direction, calculating the deviation value of the sampling frame according to the area size of the daughter board, the size of the sampling frame and the repetition rate, and then obtaining the area coordinate list of the PCB daughter board according to the deviation value of the sampling frame and the size of the sampling frame.
Further, in an embodiment of the present invention, the sampling an image block in the grayscale image according to the area coordinate list of the PCB daughter board, and determining coordinates of a sampling frame include:
acquiring the height and width of each PCB sub-board area;
determining the size of a sampling frame and the sampling repetition rate according to the area coordinate list of the PCB daughter board;
and processing the size of the sampling frame, the sampling repetition rate, the height of each PCB sub-board area and the width of each PCB sub-board area, and solving the coordinates of the sampling frame.
Further, in one embodiment of the present invention, the size of the sample box is determined by calculation.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic structural diagram of a PCB image block sampling device based on correlation analysis according to an embodiment of the invention;
FIG. 2 is a flowchart illustrating an implementation of a PCB image block sampling apparatus based on correlation analysis according to an embodiment of the present invention;
FIG. 3 is a perspective view of a coordinate axis generated in a projection module according to one embodiment of the present invention;
FIG. 4 is a sequence diagram of autocorrelation coefficients generated in a correlation analysis module in accordance with one embodiment of the present invention;
FIG. 5 is a plot of the zone coordinates of all PCB daughter boards in a partitioned module according to one embodiment of the present invention;
FIG. 6 is a schematic diagram of PCB area sampling in a sampling module according to one embodiment of the present invention;
FIG. 7 is a flowchart of a PCB image block sampling method based on correlation analysis according to an embodiment of the invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
The PCB image block sampling apparatus and method based on correlation analysis according to an embodiment of the present invention will be described with reference to the accompanying drawings, and first, the PCB image block sampling apparatus based on correlation analysis according to an embodiment of the present invention will be described with reference to the accompanying drawings.
Fig. 1 is a schematic structural diagram of a PCB image block sampling device based on correlation analysis according to an embodiment of the present invention.
As shown in fig. 1, the apparatus 10 includes: an image acquisition module 101, a projection module 102, a correlation analysis module 103, a threshold calculation module 104, a partitioning module 105, and a sampling module 106.
The image acquisition module 101 is configured to acquire a grayscale image of the PCB. The projection module 102 is connected to the image acquisition module 101, and is configured to project the grayscale image to a two-dimensional coordinate system to obtain a projection array.
That is, the projection module 102 is configured to project the grayscale image to the X-axis and the Y-axis, respectively, to obtain a two-dimensional projection array.
Specifically, as shown in fig. 2 and 3, the grayscale image is input into the projection module 102, projection arrays in the X-axis and Y-axis directions of the image are output, and then the image is averaged (or summed, squared error, median) in the X-axis and Y-axis directions, that is, information of each row or column of the image is represented by one element, so as to obtain a two-dimensional projection array.
And the correlation analysis module 103, wherein the correlation analysis module 103 is connected to the projection module 102, and is configured to perform data correlation analysis on the projection array to generate an autocorrelation coefficient sequence.
Specifically, as shown in fig. 2, the one-dimensional projection array obtained in the projection module 102 is input into the correlation analysis module 103 for data correlation analysis, so as to obtain an autocorrelation coefficient sequence R (k). The k-th order autocorrelation coefficients of the array are shown in fig. 2: for each projection array X, assuming a length L, the autocorrelation coefficient sequence is [ R (0), R (1), \8230;, R (L-1) ].
It should be noted that, the distance of the offset of the element in the autocorrelation coefficient sequence is determined by the size of the element value in the autocorrelation coefficient sequence, and a larger value of the element in the autocorrelation coefficient sequence represents a higher self-similarity at the corresponding offset distance.
The threshold calculation module 104 is connected to the correlation analysis module 103, and is configured to process the autocorrelation coefficient sequence by using a correlation threshold algorithm, so as to obtain a classification region partition threshold.
Specifically, the autocorrelation coefficient sequence is input into the threshold calculation module 104, a discrimination algorithm (i.e., autocorrelation analysis and algorithm) is established, and the classification region division threshold T is calculated using the autocorrelation coefficient sequence.
The partitioning module 105 is respectively connected with the threshold calculation module 104, the correlation analysis module 103 and the image acquisition module 101, and divides the threshold processing gray level image by using the autocorrelation coefficient sequence and the classification region to generate a region coordinate list of the PCB daughter board.
Further, in an embodiment of the present invention, the partition module 105 is specifically configured to:
judging in the autocorrelation coefficient sequence by utilizing a classification region division threshold, separating each peak value of which the gray level image coordinate projection is larger than the classification region division threshold, and determining each peak value coordinate;
when the representative image of each peak value coordinate is repeated after moving for a certain distance in the corresponding direction, calculating the deviation value of the sampling frame according to the area size of the daughter board, the size of the sampling frame and the repetition rate, and obtaining an area coordinate list of the PCB daughter board according to the deviation value of the sampling frame and the size of the sampling frame.
Specifically, as shown in fig. 2, the grayscale image, the autocorrelation coefficient sequence, and the classification region division threshold are input into the partitioning module 105, the separated PCB coordinates project all peak values larger than the threshold T, and the coordinates of each peak value represent that the image moves for a certain distance and then is repeated, so that each peak value is the coordinates of the PCB daughter board edge. As shown in FIG. 5, if the peak sequence is obtained as [ X ] for the X-axis 1 ,x 2 ]The Y-axis yields a sequence of peaks as [ Y ] 1 ,y 2 ,y 3 ,y 4 ]. The corresponding permutation and combination is the area coordinates of all the PCB daughter boards, and the image width is recorded as W, and the height is recorded as H. Then all regions are (x) 1 ,x 2 ；y 1 ,y 2 )，(x 1 ,x 2 ；y 2 ,y 3 )，(x 1 ,x 2 ；y 3 ,y 4 )，(x 1 ,x 2 ；y 4 H) and (x) 2 ,W；y 1 ,y 2 )，(x 2 ,W；y 2 ,y 3 )，(x 2 ,W；y 3 ,y 4 )，(x 2 ,W；y 4 ,H)。
The sampling module 106 is connected to the partitioning module 105 and the image acquisition module 101, respectively, and is configured to perform image block sampling on the grayscale image according to the area coordinate list of the PCB daughter board, and calculate a position coordinate of the sampling frame.
Further, in an embodiment of the present invention, the sampling module is specifically configured to:
acquiring the height and width of each PCB sub-board area;
determining the size of a sampling frame and the sampling repetition rate according to the area coordinate list of the PCB daughter board;
and processing the size of the sampling frame, the sampling repetition rate, the height of each PCB sub-board area and the width of each PCB sub-board area, and solving the coordinates of the sampling frame.
Specifically, as shown in fig. 2, the grayscale image and the area coordinate list of the PCB daughter board are input into the acquisition module 106, each daughter board area of the PCB is sampled, the size D of the sampling frame and the repetition rate R of the sampling frame are calculated (or manually specified), and then the corresponding offsets dx and dy of the sampling frame are obtained according to these two values and the size pH and pW of the daughter board area, as shown in fig. 6, the specific calculation formula is as follows: the minimum number of sample boxes satisfying repetition rate R and sample size D is nx = ceil ((1 + R) × pW/D), thereby deriving dx = (pW-D)/(nx-1). Similarly, ny = ceil ((1 + R) × pH/D), dy = (pH-D)/(ny-1). All the sample boxes can be obtained by traversing the area according to dx, dy and D.
According to the PCB image block sampling device based on the correlation analysis, purposefully sampling is carried out on the image by utilizing the correlation of the gray value of the PCB image, the detection is focused on the functional area instead of the non-functional area, so that the calculation is concentrated on the PCB attention area, the calculation amount is reduced, and the detection speed and the detection precision of the PCB defects are improved.
Next, a PCB image block sampling method based on correlation analysis proposed according to an embodiment of the present invention will be described with reference to the accompanying drawings.
Fig. 7 is a flowchart of a PCB image block sampling method based on correlation analysis according to an embodiment of the present invention.
As shown in fig. 7, the PCB image block sampling method based on correlation analysis includes the following steps:
in step S701, a grayscale image of the PCB is acquired.
In step S702, the gray image is projected to a two-dimensional coordinate system to obtain a projection array.
In step S703, the projection array is subjected to data correlation analysis to generate an autocorrelation coefficient sequence.
Further, in one embodiment of the present invention, the distance of the element offset is determined by the size of the element value in the autocorrelation coefficient sequence, and a larger value of an element in the autocorrelation coefficient sequence represents a higher self-similarity at the corresponding offset distance.
In step S704, the autocorrelation coefficient sequence is processed by using a correlation threshold algorithm, so as to obtain a classification region division threshold.
In step S705, the grayscale image is processed using the autocorrelation coefficient sequence and the classification region division threshold to obtain a region coordinate list of the PCB daughter board.
Further, in an embodiment of the present invention, processing the grayscale image, the autocorrelation coefficient sequence, and the classification region division threshold to obtain a region coordinate list of the PCB daughter board includes:
judging in the autocorrelation coefficient sequence by utilizing a classification region division threshold, separating each peak value of which the gray level image coordinate projection is larger than the classification region division threshold, and determining each peak value coordinate;
and when the representative image of each peak value coordinate is repeated after moving for a certain distance in the corresponding direction, calculating the deviation value of the sampling frame according to the area size of the daughter board, the size of the sampling frame and the repetition rate, and obtaining the area coordinate lists of all the sampling frames of the daughter board and the PCB daughter board according to the deviation value of the sampling frame and the size of the sampling frame.
In step S706, sampling an image block in the grayscale image according to the area coordinate list of the PCB daughter board, and determining a position coordinate of the sampling frame.
Further, in an embodiment of the present invention, step S706 includes:
acquiring the height and width of each PCB sub-board area;
determining the size of a sampling frame and the sampling repetition rate according to the area coordinate list of the PCB daughter board;
and processing the size of the sampling frame, the sampling repetition rate, the height of each PCB sub-board area and the width of each PCB sub-board area, and solving the coordinates of the sampling frame.
According to the PCB image block sampling method based on the correlation analysis, purposefully sampling is carried out on the image by utilizing the correlation of the gray value of the PCB image, the detection is focused on the functional area instead of the non-functional area, so that the calculation is concentrated on the PCB attention area, the calculation amount is reduced, and the detection speed and the detection precision of the PCB defects are improved.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or to implicitly indicate the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are exemplary and not to be construed as limiting the present invention, and that changes, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A PCB image block sampling device based on correlation analysis is characterized by comprising:
the image acquisition module is used for acquiring a gray level image of the PCB;
the projection module is connected with the image acquisition module and is used for projecting the gray level image to a two-dimensional coordinate system to obtain a projection array;
the correlation analysis module is connected with the projection module and is used for performing data correlation analysis on the projection array to generate an autocorrelation coefficient sequence;
the threshold calculation module is connected with the correlation analysis module and is used for processing the autocorrelation coefficient sequence by using a correlation threshold algorithm to obtain a classification region division threshold;
the partitioning module is respectively connected with the threshold value calculating module, the correlation analyzing module and the image acquisition module, and processes the gray level image by utilizing the autocorrelation coefficient sequence and the classification region partitioning threshold value to obtain a region coordinate list of the PCB daughter board; and
and the sampling module is respectively connected with the partitioning module and the image acquisition module and is used for sampling image blocks in the gray level image according to the area coordinate list of the PCB daughter board and determining the position coordinates of a sampling frame.
2. The PCB image partitioning sampling apparatus based on correlation analysis of claim 1, wherein the distance of shifting the elements in the autocorrelation coefficient sequence is determined by element value size.
3. The PCB image block sampling device based on correlation analysis of claim 1, wherein the partitioning module is specifically configured to:
judging in the autocorrelation coefficient sequence by utilizing the classification region division threshold, separating each peak value of which the gray level image coordinate projection is larger than the classification region division threshold, and determining each peak value coordinate;
when the representative image of each peak value coordinate is repeated after moving for a certain distance in the corresponding direction, calculating the deviation value of the sampling frame according to the area size of the daughter board, the size of the sampling frame and the repetition rate, and then obtaining the area coordinate list of the PCB daughter board according to the deviation value of the sampling frame and the size of the sampling frame.
4. The PCB image block sampling device based on correlation analysis of claim 1, wherein the sampling module is specifically configured to:
acquiring the height and width of each PCB sub-board area;
determining the size of a sampling frame and the sampling repetition rate according to the area coordinate list of the PCB daughter board;
and processing the size of the sampling frame, the sampling repetition rate, the height of each PCB sub-board area and the width of each PCB sub-board area, and solving the coordinates of the sampling frame.
5. The PCB image partitioning sampling apparatus based on correlation analysis of claim 4, wherein the size of the sampling frame is determined by calculation.
6. A PCB image block sampling method based on correlation analysis is characterized by comprising the following steps:
collecting a gray level image of the PCB;
projecting the gray level image to a two-dimensional coordinate system to obtain a projection array;
performing data correlation analysis on the projection array to generate an autocorrelation coefficient sequence;
processing the autocorrelation coefficient sequence by using a correlation threshold algorithm to obtain a classification region division threshold;
processing the gray level image by utilizing the autocorrelation coefficient sequence and the classification region division threshold to obtain a region coordinate list of the PCB daughter board; and
and sampling image blocks in the gray images according to the area coordinate list of the PCB daughter boards, and determining the position coordinates of a sampling frame.
7. The PCB image partitioning sampling method based on correlation analysis of claim 6, wherein the distance of the offset of the elements in the autocorrelation coefficient sequence is determined by the size of the element value.
8. The PCB image block sampling method based on correlation analysis of claim 6, wherein the processing the gray image, the autocorrelation coefficient sequence and the classification region division threshold to obtain a region coordinate list of PCB daughter boards comprises:
judging in the autocorrelation coefficient sequence by utilizing the classification region division threshold, separating each peak value of which the gray level image coordinate projection is larger than the classification region division threshold, and determining each peak value coordinate;
when the representative image of each peak value coordinate is repeated after moving for a certain distance in the corresponding direction, calculating the deviation value of the sampling frame according to the area size of the daughter board, the size of the sampling frame and the repetition rate, and then obtaining the area coordinate list of the PCB daughter board according to the deviation value of the sampling frame and the size of the sampling frame.
9. The PCB image blocking sampling method based on correlation analysis of claim 6, wherein the sampling of the image blocks in the gray scale image according to the area coordinate list of the PCB daughter board and the determination of the coordinates of the sampling frame comprise:
acquiring the height and width of each PCB sub-board area;
determining the size of a sampling frame and the sampling repetition rate according to the area coordinate list of the PCB daughter board;
and processing the size of the sampling frame, the sampling repetition rate, the height of each PCB sub-board area and the width of each PCB sub-board area, and solving the coordinates of the sampling frame.
10. The correlation analysis based PCB image partitioning sampling method of claim 9, wherein the size of the sampling frame is determined by calculation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010104106.1A CN111415327B (en) | 2020-02-20 | 2020-02-20 | PCB image block sampling device and method based on correlation analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010104106.1A CN111415327B (en) | 2020-02-20 | 2020-02-20 | PCB image block sampling device and method based on correlation analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111415327A CN111415327A (en) | 2020-07-14 |
| CN111415327B true CN111415327B (en) | 2023-02-28 |
Family
ID=71490949
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010104106.1A Active CN111415327B (en) | 2020-02-20 | 2020-02-20 | PCB image block sampling device and method based on correlation analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111415327B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111855701A (en) * | 2020-07-29 | 2020-10-30 | 深圳芯通互联科技有限公司 | AOI system detection method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1932838A (en) * | 2005-09-12 | 2007-03-21 | 电子科技大学 | Vehicle plate extracting method based on skiagraphy and mathematical morphology |
| CN104794491A (en) * | 2015-04-28 | 2015-07-22 | 重庆大学 | Fuzzy clustering steel plate surface defect detection method based on pre classification |
| CN106447649A (en) * | 2016-08-25 | 2017-02-22 | 凌云光技术集团有限责任公司 | Detection method and device of bead body position defect |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4038356B2 (en) * | 2001-04-10 | 2008-01-23 | 株式会社日立製作所 | Defect data analysis method and apparatus, and review system |
-
2020
- 2020-02-20 CN CN202010104106.1A patent/CN111415327B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1932838A (en) * | 2005-09-12 | 2007-03-21 | 电子科技大学 | Vehicle plate extracting method based on skiagraphy and mathematical morphology |
| CN104794491A (en) * | 2015-04-28 | 2015-07-22 | 重庆大学 | Fuzzy clustering steel plate surface defect detection method based on pre classification |
| CN106447649A (en) * | 2016-08-25 | 2017-02-22 | 凌云光技术集团有限责任公司 | Detection method and device of bead body position defect |
Non-Patent Citations (1)
| Title |
|---|
| sing convolutional neural networks for character verification on integrated circuit components of printed circuit boards;ChunHui Lin等;《Applied Intelligence 49》;20190521;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111415327A (en) | 2020-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4429298B2 (en) | Object number detection device and object number detection method | |
| CN111369495B (en) | Panoramic image change detection method based on video | |
| JP2005128619A (en) | Object measurement apparatus, object measurement method, and program | |
| CN111489337B (en) | Automatic optical detection pseudo defect removal method and system | |
| JPH07167649A (en) | Distance measuring equipment | |
| US7221789B2 (en) | Method for processing an image captured by a camera | |
| EP2293243A2 (en) | Image processing apparatus, image capture apparatus, image processing method, and program | |
| US11030478B1 (en) | System and method for correspondence map determination | |
| JP3333721B2 (en) | Area detection device | |
| US8164633B2 (en) | Calibration apparatus and method for imaging devices and computer program | |
| JP6423314B2 (en) | Corresponding point search method and distance measuring device | |
| US20110085026A1 (en) | Detection method and detection system of moving object | |
| CN111415327B (en) | PCB image block sampling device and method based on correlation analysis | |
| JP4681592B2 (en) | Speed measurement method | |
| CN110689554B (en) | Background motion estimation method and device for infrared image sequence and storage medium | |
| KR101870700B1 (en) | A fast key frame extraction method for 3D reconstruction from a handheld video | |
| KR100792172B1 (en) | Apparatus and method for estimating fundamental matrix using robust correspondence point | |
| CN111257346B (en) | PCB positioning device and method based on projection filtering | |
| JP2016099932A (en) | Distance detection apparatus | |
| JP4918615B2 (en) | Object number detection device and object number detection method | |
| JP3066137B2 (en) | Pattern matching method | |
| JP4674920B2 (en) | Object number detection device and object number detection method | |
| CN111473944B (en) | PIV data correction method and device for observing complex wall surface in flow field | |
| JP2018112527A (en) | Distance measurement device, distance measurement method and distance measurement program | |
| JP2006113738A (en) | Device and method for detecting object |
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 |