CN114882028A - Multi-camera-based welding terminal detection method, device and system - Google Patents
Multi-camera-based welding terminal detection method, device and system Download PDFInfo
- Publication number
- CN114882028A CN114882028A CN202210797147.2A CN202210797147A CN114882028A CN 114882028 A CN114882028 A CN 114882028A CN 202210797147 A CN202210797147 A CN 202210797147A CN 114882028 A CN114882028 A CN 114882028A
- Authority
- CN
- China
- Prior art keywords
- view
- rivet
- qualified
- top view
- corresponding relation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000003466 welding Methods 0.000 title claims abstract description 62
- 238000001514 detection method Methods 0.000 title claims abstract description 50
- 230000001502 supplementing effect Effects 0.000 claims abstract description 18
- 238000000034 method Methods 0.000 claims description 21
- 229910000679 solder Inorganic materials 0.000 claims description 19
- 238000010586 diagram Methods 0.000 claims description 13
- 230000005855 radiation Effects 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000005476 soldering Methods 0.000 claims description 2
- 238000007689 inspection Methods 0.000 claims 2
- 239000000047 product Substances 0.000 description 40
- 238000004590 computer program Methods 0.000 description 12
- 238000004458 analytical method Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 238000003860 storage Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 239000013589 supplement Substances 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to the technical field of image generation and processing, in particular to a multi-camera-based welding terminal detection method, a device and a system, which comprises the following steps: supplementing light from the upper side to obtain a top view of the welding terminal; supplementing light from the lower side to obtain a bottom view of the welding terminal; closing the supplementary lighting to obtain a side view of the welding terminal; performing decoloring treatment on the acquired top view, bottom view and side view to obtain a gray-scale image; judging whether the flatness of the upper surface of the welding terminal is qualified or not according to the top view and the side view, if so, executing the next step, otherwise, discarding; judging whether the center distance of the rivet is qualified or not according to the top view and the bottom view, if so, executing the next step, otherwise, discarding; and judging whether the verticality of the rivet is qualified or not according to the top view, the side view and the bottom view, if so, judging that the product is qualified, and otherwise, judging that the product is unqualified and discarding. According to the invention, clear images can be obtained by controlling the supplementary lighting, and whether the product is qualified or not can be comprehensively judged by combining and analyzing different images.
Description
Technical Field
The invention relates to the technical field of image generation and processing, in particular to a multi-camera-based welding terminal detection method, device and system.
Background
The power battery is used for providing power for a power part of the equipment, the power part is mainly a motor, and the power of the motor is higher, so that the requirements on the capacity and the voltage of the power battery are higher.
The power battery is installed and connected by using a specific welding terminal, the welding terminal comprises a support and two parts of a rivet fixed on the support, and a threaded hole connected with the outside is formed in the upward end of the rivet; the downward end of the support is provided with four support legs connected with the circuit board. Rivet and support are through compressing tightly fixed, compress tightly fixedly and utilize the interference fit realization in shaft hole, and certain damage or deformation may be produced to counter shaft or hole, and welded terminal itself is higher to the requirement of precision, so in process of production, still need whether qualified to detect welded terminal after rivet compresses tightly fixed.
The detected items comprise the flatness of the support, the center distance between the rivet and the support, the verticality and the like. The existing detection methods are based on respectively collecting images in different directions, and obtaining the detection result of one or a plurality of items from the image in one direction, so that the information contained in the images in different directions is still insufficient for mutual use and comprehensive analysis, and whether the product is really qualified cannot be accurately detected.
Disclosure of Invention
In view of the above, it is desirable to provide a method, an apparatus and a system for detecting a solder terminal by multiple cameras.
The embodiment of the invention is realized in such a way that a multi-camera-based welding terminal detection method comprises the following steps:
supplementing light from the upper side to obtain a top view of the welding terminal; supplementing light from the lower side to obtain a bottom view of the welding terminal; closing the supplementary lighting to obtain a side view of the welding terminal;
performing decoloring treatment on the acquired top view, bottom view and side view to obtain a gray-scale image;
judging whether the flatness of the upper surface of the welding terminal is qualified or not according to the top view and the side view, if so, executing the next step, otherwise, discarding;
judging whether the center distance of the rivet is qualified or not according to the top view and the bottom view, if so, executing the next step, otherwise, discarding;
and judging whether the verticality of the rivet is qualified or not according to the top view, the side view and the bottom view, if so, judging that the product is qualified, and otherwise, judging that the product is unqualified and discarding.
In one embodiment, the present invention provides a multi-camera based solder terminal detection apparatus comprising:
the image acquisition module is used for supplementing light from the upper side and acquiring a top view of the welding terminal; supplementing light from the lower side to obtain a bottom view of the welding terminal; closing the supplementary lighting to obtain a side view of the welding terminal;
the preprocessing module is used for performing decoloring processing on the acquired top view, bottom view and side view to obtain a gray-scale image;
the flatness judging module is used for judging whether the flatness of the upper surface of the welding terminal is qualified or not according to the top view and the side view, if so, executing the next step, and otherwise, discarding;
the center distance judging module is used for judging whether the center distance of the rivet is qualified or not according to the top view and the bottom view, if so, executing the next step, and if not, discarding;
and the verticality judging module is used for judging whether the verticality of the rivet is qualified or not according to the top view, the side view and the bottom view, if so, the product is qualified, and if not, the product is unqualified and is discarded.
In one embodiment, the present invention provides a multi-camera based weld terminal detection system comprising:
the image acquisition device is used for acquiring an image of a product;
and the image detection module is used for executing the image processing in the multi-camera-based welding terminal detection method and judging whether the product is qualified according to the product image acquired by the image acquisition device.
According to the multi-camera-based welding terminal detection method, a clearer image can be obtained by controlling the supplementary lighting, the image quality is controlled from a data source, and the accuracy of later analysis processing is improved conveniently; on the basis, the invention judges whether the upper surface of the product is qualified or not from the top view and the side view, judges whether the center distance of the product is qualified or not from the top view and the bottom view, and judges whether the verticality of the product is qualified or not from the top view, the side view and the bottom view. In the method provided by the invention, the judgment of the product shape or position deviation is combined with the information of different views, so that the accuracy of visual detection and analysis is improved. The invention is applied to automatic production, can realize on-line continuous detection, and has good accuracy and high efficiency.
Drawings
FIG. 1 is a perspective view of a welded terminal for a power battery according to the present invention;
FIG. 2 is a flow diagram of a multi-camera based weld terminal detection method in one embodiment;
FIG. 3 is a block diagram of a multi-camera based weld terminal detection apparatus in one embodiment;
FIG. 4 is a block diagram of a multi-camera based weld terminal detection system in one embodiment;
FIG. 5 is a block diagram showing an internal configuration of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
It will be understood that, as used herein, the terms "first," "second," and the like may be used herein to describe various elements, but these elements are not limited by these terms unless otherwise specified. These terms are only used to distinguish one element from another. For example, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script, without departing from the scope of the present disclosure.
Fig. 1 is a perspective view of a welding terminal for a power battery, which is a product according to the present invention, and the welding terminal includes a support and a rivet fixed on the support, wherein the support is Jiong-shaped as a whole, four support legs for connecting with a circuit board are provided, a through hole is provided in the center of the top of the support, and the rivet is pressed and fixed on the through hole. In the invention, whether the flatness of the top plane of the support is qualified or not is detected, and the plane is in contact with other structures when in use and needs to maintain enough flatness; secondly, detecting whether the center of the rivet is superposed with the center of the through hole after the rivet is pressed into the support; in addition, whether the perpendicularity of the rivet and the support is qualified or not needs to be detected, so that the rivet is perpendicular to the top surface of the support.
As shown in fig. 2, in an embodiment, a method for detecting a solder terminal based on multiple cameras is provided, which may specifically include the following steps:
s100, supplementing light from the upper side, and acquiring a top view of the welding terminal; supplementing light from the lower side to obtain a bottom view of the welding terminal; closing the supplementary lighting to obtain a side view of the welding terminal;
s200, performing decoloring processing on the acquired top view, bottom view and side view to obtain a gray-scale image;
s300, judging whether the flatness of the upper surface of the welding terminal is qualified or not according to the top view and the side view, if so, executing the next step, otherwise, discarding;
s400, judging whether the center distance of the rivet is qualified or not according to the top view and the bottom view, if so, executing the next step, otherwise, discarding;
and S500, judging whether the verticality of the rivet is qualified or not according to the top view, the side view and the bottom view, if so, judging that the product is qualified, and otherwise, judging that the product is unqualified and discarding.
In this embodiment, the light used for light supplement is red light, the red light can improve the contrast of each part of the image collected by the CCD, and meanwhile, a relatively clear image can also be collected at a relatively dark part of the product. In this embodiment, light is required to be supplemented to both the top view and the bottom view, and light is not required to be supplemented to the side view.
In this embodiment, a gray scale image can be obtained by performing a decoloring process on an image; in this embodiment, a color CCD is used to obtain more information of the product, and the process of calculation processing can be simplified and the calculation speed can be increased by the decoloring processing.
In this embodiment, the items detected include flatness, center distance and perpendicularity, and the three detections are obtained by performing comprehensive analysis through image combination, so that the detection accuracy is improved, and the problem of inaccurate detection of a single image is avoided.
According to the multi-camera-based welding terminal detection method, a clearer image can be obtained by controlling the supplementary lighting, the image quality is controlled from a data source, and the accuracy of later analysis processing is improved conveniently; on the basis, the invention judges whether the upper surface of the product is qualified or not from the top view and the side view, judges whether the center distance of the product is qualified or not from the top view and the bottom view, and judges whether the verticality of the product is qualified or not from the top view, the side view and the bottom view. In the method provided by the invention, the judgment of the product shape or position deviation is combined with the information of different views, so that the accuracy of visual detection and analysis is improved. The invention is applied to automatic production, can realize on-line continuous detection, and has good accuracy and high efficiency.
As a preferred embodiment of the present invention, the decolorizing the acquired top view, bottom view and side view to obtain a gray scale image includes:
reading the numerical value of each pixel point in the Lab space in each view;
representing the contrast and the gray scale difference of any two pixels in each image;
constructing an objective function;
and solving a gray value representation method for minimizing the objective function value to obtain parameters for converting the RGB mode into gray scale, and converting each view into a gray scale image according to the obtained parameters.
In the present embodiment, as for the image C, any two points thereof
And
the method comprises the following steps:
wherein: in Lab mode, the L component represents the luminance of the pixel and has a value in the range of [0, 100 ]]From pure black to pure white; a represents the range from red to green, and the value range is [127, -128 ]](ii) a b represents the range from yellow to blue, and the value range is [127 to 128 ]]；
Is a pixel point
Gray scale difference of
And pixel point
Gray scale of
A difference of (d); for any pixel, its gray level is represented by a linear combination of RGB, where,
and
are coefficients of R term, G term and B term, respectively, and
and at the same time,
。
in the present embodiment, the objective function is represented by the following equation:
wherein,
and
satisfies the following conditions:
wherein,
is a parameter of the gaussian distribution and,
not equal to 0.
The goal is to solve for the coefficients of the R, G, and B terms that minimize the value of the objective function.
As a further priority, it is possible to,
and
are all taken from [0,1 ]]The middle interval is 0.1, and the combination of the three coefficients is less than 100; one of them can be selected by comparing the effects of each combination.
In this embodiment, through the above processing, the contrast of each part of the obtained grayscale image is high, and the probability that the original part with different colors has the same grayscale after being decolored is reduced.
As a preferred embodiment of the present invention, in the RGB mode grayscale conversion parameters, when the fill-in color is a single color, the fill-in color has a maximum parameter; when the fill-in color is mixed, the fill-in color has a set of maximum parameters.
In this embodiment, for a single color, red is taken as an example
And
in the process of
The gray-scale image processing method has the maximum value, the influence of red light on the gray-scale value can be improved, the color of light supplement is more fully reflected in the gray-scale image, and the contrast is improved by fully utilizing the effect of the light supplement.
In the present embodiment, for a mixed color light, such as a color light with RGB value (60, 120, 100),
and
the proportion of 120: 100, and the maximum value is taken on the premise that the ratio is satisfied.
As a preferred embodiment of the present invention, the determining whether the flatness of the upper surface of the solder terminal is acceptable from the top view and the side view includes:
acquiring the gray value of each pixel point of the top view;
constructing a position-gray map according to the positions of the pixel points and the corresponding gray values;
determining a peak and a trough according to the position-gray scale image;
in a side view, a boundary start pixel is determined from top to bottom;
expanding the boundary starting pixel to the left side and the right side to obtain a boundary pixel chain;
determining a boundary line of an upper surface of the soldering terminal by the boundary pixel chain;
determining the corresponding relation between the wave crest and the wave trough and the corresponding relation between the wave crest and the corresponding relation between the wave trough and the corresponding relation between the wave crest and the corresponding relation between the wave trough and the corresponding relation between the corresponding relation and the corresponding relation between the corresponding relation and the corresponding relation between the corresponding relation of the corresponding relation of the corresponding relation of the corresponding;
for the bulges, if the maximum value of the bulges is smaller than a set first set threshold value and the quantity of the bulges is smaller than a second set threshold value, the bulges are qualified;
for the depressions, if the number of the depressions is smaller than a third set threshold value, the depressions are qualified;
and if the bulges and the depressions are qualified, judging that the flatness of the upper surface of the welding terminal is qualified, otherwise, judging that the flatness of the upper surface of the welding terminal is unqualified.
In this embodiment, a corner point is selected as an origin, and a corresponding gray value is provided for any point (x, y) (where x and y are the order of pixels in two mutually perpendicular directions), so that a position-gray map in three-dimensional coordinates can be constructed. In the position-gray scale image, the pixels at different positions have respective gray scale values, and the gray scale values of the pixels are connected by a smooth curved surface to obtain a gray scale surface. The wave crests and wave troughs are formed on the gray surface and correspond to the bulges and the depressions on the surface of the product.
In this embodiment, in order to determine whether the protrusions correspond to peaks or valleys (for different colors of light, different product surfaces, coefficients)
And
such correspondence may vary), using a side view for analysis.
In this embodiment, the boundary start pixel is determined from top to bottom, a vertical straight line may be drawn from the center of the pixel, the gray value of the passing pixel is calculated from top to bottom, when the gray value of the pixel is not 255 and is significantly reduced (for example, equal to 0, or less than 10, etc.), the point is used as the boundary start pixel, the gray value of the adjacent pixel is calculated by expanding the point in four directions, i.e., up, down, left, and right, with the pixel as a starting point, and if the difference between the gray value of the adjacent pixel and the gray value of the current pixel is less than 20%, the boundary pixel is determined. This process is repeated to find all boundary pixels.
For the convex part in the upper surface, the convex part of the boundary in the side view can be positioned by combining a position-gray scale map, and the rest is concave, so that the corresponding relation between the peak and the trough and the convex and the concave parts can be determined.
In this embodiment, the first set threshold is the flatness tolerance of the upper surface, and it is also limited that the number of protrusions needs to be smaller than the second set threshold, and the second set threshold may take an empirical value of 5, 10, 12, etc.
In this embodiment, the number of depressions is required to be smaller than a third set threshold, which may take an empirical value of 5, 10, or the like.
As a preferred embodiment of the present invention, the determining whether the center distance of the rivet is acceptable from the top view and the bottom view includes:
acquiring gray values of all pixel points of the top view and the bottom view;
constructing a position-gray map according to the positions of the pixel points and the corresponding gray values;
for the top view, positioning the excircle and the circle center of the rivet in a top view state according to a position-gray scale diagram, determining the coordinate of the circle center on the upper surface, and recording as a first coordinate;
for the bottom view, positioning the excircle and the circle center of the rivet in an upward view state according to the position-gray scale diagram, and determining the coordinate of the circle center on the lower surface and recording as a second coordinate;
and calculating the distance between the first coordinate and the second coordinate, and judging whether the calculated distance is smaller than a fourth set threshold value, if so, judging whether the center distance of the rivet is qualified, otherwise, judging that the rivet is unqualified.
In this embodiment, please refer to the previous embodiment for the description of the position-gray scale diagram.
In the present embodiment, the center distance is the deviation of the center point of the upper side of the rivet from the center point of the lower side of the rivet in the bottom view, in the top view, which is related to the straightness of the rivet itself and also to whether the rivet is perpendicular or not at the time of assembly.
In the present embodiment, the fourth set threshold is the coaxiality tolerance of the through hole and the rivet.
As a preferred embodiment of the present invention, the positioning of the outer circle and the center of the rivet according to the position-gray scale diagram for the top view or the bottom view includes:
making a plurality of radiation line segments which are arranged at equal angles and have equal length from the center of the image;
calculating the product of the difference value of the gray values of two adjacent pixel points through which the radiation line segment passes and the length proportion of the corresponding position of the radiation line from the center to the outside;
making a circle center, and obtaining the circle center of the rivet by minimizing the sum of the distances from the circle center to the point with the maximum product on each radiation line;
and determining the excircle radius of the rivet, and obtaining the excircle of the rivet through the pair with the largest product of the excircle number of the rivet.
In this embodiment, the position corresponding to the radiation line herein refers to a boundary position of two adjacent pixels; the difference between the gray values of the two pixels is the gray value of the pixel inside and outside the boundary position. Whether the background is gray or white, through the algorithm, the position of the sharp change of the gray can be determined, and the maximum excircle can be further positioned by binding the changed value with the length proportion of the radiant line.
As a preferred embodiment of the present invention, the judging whether the verticality of the rivet is qualified from the top view, the side view and the bottom view includes:
judging whether the center distance of the rivet meets a set verticality threshold value, if so, executing the next step, otherwise, judging that the verticality is unqualified;
identifying, in a side view, a lower sideline and an upper sideline of the rivet;
determining the middle points of the identified lower edge line and the upper edge line;
and determining the deviation of the center of the lower line and the center of the upper line in the horizontal direction, and judging whether the deviation meets a set verticality threshold value, wherein if the deviation meets the set verticality threshold value, the verticality of the rivet is qualified, and if the deviation does not meet the set verticality threshold value, the rivet is unqualified.
In the present embodiment, the perpendicularity refers to the perpendicularity between the axis of the rivet and the top of the support, and the top surface of the support is a reference surface. Therefore, the theoretical maximum deviation can be calculated through the center distance, and whether the verticality is qualified or not is judged. Perpendicularity needs to be given in a given direction, and the direction is ignored, so that obviously unqualified products can be quickly screened out through calculation of the deviation between the top surface and the bottom surface of the rivet. On the basis, whether the deviation in the specific direction meets the requirement is further judged by using the side view, so that the detection accuracy of the perpendicularity is improved. In the whole implementation, the direction of the side view is selected as the direction which has the highest requirement on the verticality when the product is used.
As a preferred embodiment of the present invention, the determining the midpoint of the identified bottom edge and the midpoint of the top edge includes:
generating a horizontal line at the bottom of the side view;
translating the horizontal line upwards by a set step distance, and calculating the gray value average value of pixel points through which the horizontal line passes;
selecting three positions with the maximum gray value mean value;
from bottom to top, the first position is the position of the lower sideline, and the second position is the position of the upper sideline;
determining pixels with continuous gray values from the center of the image to two sides at the determined position of the lower edge line to obtain a lower edge line;
and determining pixels with continuous gray values from the center of the image to two sides at the determined position of the upper edge line to obtain the upper edge line.
In this embodiment, pixels with connected gray values are determined from the center of the image to both sides, where the gray value connection means that the deviation of the gray values of the adjacent pixel points is less than 20%. The lower line resulting from the pixel is typically a long and narrow rectangular area, with the center of the edge taking the center point of the resulting rectangular area.
As shown in fig. 3, an embodiment of the present invention further provides a device for detecting a solder terminal based on multiple cameras, where the device for detecting a solder terminal based on multiple cameras includes:
the image acquisition module is used for supplementing light from the upper side and acquiring a top view of the welding terminal; supplementing light from the lower side to obtain a bottom view of the welding terminal; closing the supplementary lighting to obtain a side view of the welding terminal;
the preprocessing module is used for performing decoloring processing on the acquired top view, bottom view and side view to obtain a gray-scale image;
the flatness judging module is used for judging whether the flatness of the upper surface of the welding terminal is qualified or not according to the top view and the side view, if so, executing the next step, and otherwise, discarding;
the center distance judging module is used for judging whether the center distance of the rivet is qualified or not according to the top view and the bottom view, if so, executing the next step, and if not, discarding;
and the verticality judging module is used for judging whether the verticality of the rivet is qualified or not according to the top view, the side view and the bottom view, if so, the product is qualified, and if not, the product is unqualified and is discarded.
In this embodiment, the multi-camera based solder terminal detection apparatus is a modularization of the method portion of the present invention, and for the explanation of each module, please refer to the contents of the method components of the present invention, which is not described again in this embodiment.
As shown in fig. 4, an embodiment of the present invention further provides a multi-camera based welding terminal detection system, where the multi-camera based welding terminal detection system includes:
the image acquisition device is used for acquiring an image of a product;
and the image detection module is used for executing the image processing in the multi-camera-based welding terminal detection method and judging whether the product is qualified according to the product image acquired by the image acquisition device.
In the embodiment, the multi-camera-based welding terminal detection method provided by the embodiment of the invention is executed through the image detection module, a clearer image can be obtained by controlling the supplementary lighting, the image quality is controlled from a data source, and the accuracy of the post-analysis processing is improved conveniently; on the basis, the invention judges whether the upper surface of the product is qualified or not from the top view and the side view, judges whether the center distance of the product is qualified or not from the top view and the bottom view, and judges whether the verticality of the product is qualified or not from the top view, the side view and the bottom view. The system provided by the invention combines the information of different views for judging the shape or position deviation of the product, and improves the accuracy of visual detection and analysis. The invention is applied to automatic production, can realize on-line continuous detection, and has good accuracy and high efficiency.
FIG. 5 is a diagram illustrating an internal structure of a computer device in one embodiment. The image detection module shown in fig. 4 may be run in the computer device. As shown in fig. 5, the computer apparatus includes a processor, a memory, a network interface, an input device, and a display screen connected through a system bus. Wherein the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system, and may further store a computer program, and when the computer program is executed by a processor, the computer program may enable the processor to implement the multi-camera based solder terminal detection method provided by the embodiment of the present invention. The internal memory may also store a computer program, and when the computer program is executed by the processor, the processor may execute the method for detecting the solder terminal based on the multiple cameras according to the embodiment of the present invention. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the configuration shown in fig. 5 is a block diagram of only a portion of the configuration associated with aspects of the present invention and is not intended to limit the computing devices to which aspects of the present invention may be applied, and that a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, the multi-camera based welding terminal detection apparatus provided by the embodiment of the present invention can be implemented in the form of a computer program, and the computer program can be run on a computer device as shown in fig. 5. The memory of the computer device may store various program modules constituting the multi-camera based welding terminal detection apparatus, such as an image acquisition module, a preprocessing module, a flatness determination module, a center distance determination module, and a verticality determination module shown in fig. 3. The computer program constituted by the respective program modules causes the processor to execute the steps in the multi-camera based solder terminal detection method of the respective embodiments of the present invention described in this specification.
For example, the computer device shown in fig. 5 may perform step S100 by an image acquisition module in the multi-camera based solder terminal detection apparatus shown in fig. 3; the computer device may perform step S200 through the preprocessing module; the computer device may perform step S300 through the flatness determination module; the computer device may perform step S400 through the center distance determination module; the computer device may perform step S500 through the perpendicularity determining module.
In one embodiment, a computer device is proposed, the computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
supplementing light from the upper side to obtain a top view of the welding terminal; supplementing light from the lower side to obtain a bottom view of the welding terminal; closing the light supplement and acquiring a side view of the welding terminal;
performing decoloring treatment on the acquired top view, bottom view and side view to obtain a gray-scale image;
judging whether the flatness of the upper surface of the welding terminal is qualified or not according to the top view and the side view, if so, executing the next step, otherwise, discarding;
judging whether the center distance of the rivet is qualified or not according to the top view and the bottom view, if so, executing the next step, otherwise, discarding;
and judging whether the verticality of the rivet is qualified or not according to the top view, the side view and the bottom view, if so, judging that the product is qualified, and if not, judging that the verticality of the rivet is unqualified and discarding.
In one embodiment, a computer readable storage medium is provided, having a computer program stored thereon, which, when executed by a processor, causes the processor to perform the steps of:
supplementing light from the upper side to obtain a top view of the welding terminal; supplementing light from the lower side to obtain a bottom view of the welding terminal; closing the supplementary lighting to obtain a side view of the welding terminal;
performing decoloring treatment on the acquired top view, bottom view and side view to obtain a gray-scale image;
judging whether the flatness of the upper surface of the welding terminal is qualified or not according to the top view and the side view, if so, executing the next step, otherwise, discarding;
judging whether the center distance of the rivet is qualified or not according to the top view and the bottom view, if so, executing the next step, otherwise, discarding;
and judging whether the verticality of the rivet is qualified or not according to the top view, the side view and the bottom view, if so, judging that the product is qualified, and otherwise, judging that the product is unqualified and discarding.
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of steps in various embodiments may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least a portion of sub-steps or stages of other steps.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, databases, or other media used in embodiments provided herein may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A multi-camera based welding terminal detection method is characterized by comprising the following steps:
supplementing light from the upper side to obtain a top view of the welding terminal; supplementing light from the lower side to obtain a bottom view of the welding terminal; closing the supplementary lighting to obtain a side view of the welding terminal;
performing decoloring treatment on the acquired top view, bottom view and side view to obtain a gray-scale image;
judging whether the flatness of the upper surface of the welding terminal is qualified or not according to the top view and the side view, if so, executing the next step, otherwise, discarding;
judging whether the center distance of the rivet is qualified or not according to the top view and the bottom view, if so, executing the next step, otherwise, discarding;
and judging whether the verticality of the rivet is qualified or not according to the top view, the side view and the bottom view, if so, judging that the product is qualified, and otherwise, judging that the product is unqualified and discarding.
2. The multi-camera based solder terminal detection method of claim 1, wherein the decolorizing the acquired top, bottom and side views to obtain a gray scale comprises:
reading the numerical value of each pixel point in the Lab space in each view;
representing the contrast and the gray scale difference of any two pixels in each image;
constructing an objective function;
and solving a gray value representation method for minimizing the objective function value to obtain parameters for converting the RGB mode into gray scale, and converting each view into a gray scale image according to the obtained parameters.
3. The multi-camera based solder terminal detection method of claim 2, wherein in the RGB mode grayscale conversion parameters, when the fill-in color is a single color, the fill-in color has a maximum parameter; when the fill-in color is mixed, the fill-in color has a set of maximum parameters.
4. The multi-camera based solder terminal inspection method according to claim 1, wherein said determining from a top view and a side view whether the flatness of the upper surface of the solder terminal is acceptable comprises:
acquiring the gray value of each pixel point of the top view;
constructing a position-gray map according to the positions of the pixel points and the corresponding gray values;
determining a peak and a trough according to the position-gray scale image;
in a side view, a boundary start pixel is determined from top to bottom;
expanding the boundary starting pixel to the left side and the right side to obtain a boundary pixel chain;
determining a boundary line of an upper surface of the soldering terminal by the boundary pixel chain;
determining the corresponding relation between the wave crest and the wave trough and the corresponding relation between the wave crest and the corresponding relation between the wave trough and the corresponding relation between the corresponding relation and the corresponding relation between the corresponding relation and the corresponding relation between the corresponding relation and the corresponding relation of the corresponding relation between the corresponding relation and the corresponding relation between the corresponding relation of the corresponding relation between the corresponding relation of the corresponding relation between the corresponding relation of the corresponding peak and the corresponding relation of the corresponding relation;
for the bulges, if the maximum value of the bulges is smaller than a set first set threshold value and the quantity of the bulges is smaller than a second set threshold value, the bulges are qualified;
for the depressions, if the number of the depressions is less than a third set threshold value, the depressions are qualified;
and if the bulges and the depressions are qualified, judging that the flatness of the upper surface of the welding terminal is qualified, otherwise, judging that the flatness of the upper surface of the welding terminal is unqualified.
5. The multi-camera based solder terminal detection method of claim 1, wherein the determining whether the center distance of the rivet is acceptable from the top view and the bottom view comprises:
acquiring gray values of all pixel points of the top view and the bottom view;
constructing a position-gray map according to the positions of the pixel points and the corresponding gray values;
for the top view, positioning the excircle and the circle center of the rivet in a top view state according to a position-gray scale diagram, determining the coordinate of the circle center on the upper surface, and recording as a first coordinate;
for the bottom view, positioning the excircle and the circle center of the rivet in an upward view state according to the position-gray scale diagram, and determining the coordinate of the circle center on the lower surface and recording as a second coordinate;
and calculating the distance between the first coordinate and the second coordinate, and judging whether the calculated distance is smaller than a fourth set threshold value, if so, judging whether the center distance of the rivet is qualified, otherwise, judging that the rivet is unqualified.
6. The multi-camera based solder terminal inspection method according to claim 5, wherein positioning the outer circle of the rivet and the center of the circle thereof according to the position-gray scale diagram for the top view or the bottom view comprises:
making a plurality of radiation line segments which are arranged at equal angles and have equal length from the center of the image;
calculating the product of the difference value of the gray values of two adjacent pixel points through which the radiation line segment passes and the length proportion of the corresponding position of the radiation line from the center to the outside;
making a circle center, and obtaining the circle center of the rivet by minimizing the sum of the distances from the circle center to the point with the maximum product on each radiation line;
and determining the excircle radius of the rivet, and obtaining the excircle of the rivet through the pair with the largest product of the excircle number of the rivet.
7. The multi-camera based solder terminal detection method of claim 5, wherein the determining whether the verticality of the rivet is qualified from the top view, the side view and the bottom view comprises:
judging whether the center distance of the rivet meets a set verticality threshold value, if so, executing the next step, otherwise, judging that the verticality is unqualified;
identifying, in a side view, a lower sideline and an upper sideline of the rivet;
determining the middle points of the identified lower edge line and the upper edge line;
and determining the deviation of the center of the lower line and the center of the upper line in the horizontal direction, and judging whether the deviation meets a set verticality threshold value, wherein if the deviation meets the set verticality threshold value, the verticality of the rivet is qualified, and if the deviation does not meet the set verticality threshold value, the rivet is unqualified.
8. The multi-camera based solder terminal detection method of claim 7, wherein said determining the midpoint of the identified lower edge line and the midpoint of the identified upper edge line comprises:
generating a horizontal line at the bottom of the side view;
translating the horizontal line upwards by a set step distance, and calculating the gray value average value of pixel points through which the horizontal line passes;
selecting three positions with the maximum gray value mean value;
from bottom to top, the first position is the position of the lower sideline, and the second position is the position of the upper sideline;
determining pixels with continuous gray values from the center of the image to two sides at the determined position of the lower edge line to obtain a lower edge line;
and determining pixels with continuous gray values from the center of the image to two sides at the determined position of the upper edge line to obtain the upper edge line.
9. The utility model provides a welding terminal detection device based on many cameras which characterized in that, welding terminal detection device based on many cameras includes:
the image acquisition module is used for supplementing light from the upper side and acquiring a top view of the welding terminal; supplementing light from the lower side to obtain a bottom view of the welding terminal; closing the supplementary lighting to obtain a side view of the welding terminal;
the preprocessing module is used for performing decoloring processing on the acquired top view, bottom view and side view to obtain a gray-scale image;
the flatness judging module is used for judging whether the flatness of the upper surface of the welding terminal is qualified or not according to the top view and the side view, if so, executing the next step, and otherwise, discarding;
the center distance judging module is used for judging whether the center distance of the rivet is qualified or not according to the top view and the bottom view, if so, executing the next step, and if not, discarding;
and the verticality judging module is used for judging whether the verticality of the rivet is qualified or not according to the top view, the side view and the bottom view, if so, the product is qualified, and if not, the product is unqualified and is discarded.
10. A multi-camera based weld terminal detection system, comprising:
the image acquisition device is used for acquiring an image of a product;
an image detection module, configured to perform, according to the product image acquired by the image acquisition device, the steps of processing the image and determining whether the product is qualified according to any one of claims 1 to 8 in the multi-camera based welding terminal detection method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210797147.2A CN114882028B (en) | 2022-07-08 | 2022-07-08 | Multi-camera-based welding terminal detection method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210797147.2A CN114882028B (en) | 2022-07-08 | 2022-07-08 | Multi-camera-based welding terminal detection method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114882028A true CN114882028A (en) | 2022-08-09 |
| CN114882028B CN114882028B (en) | 2022-10-21 |
Family
ID=82682872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210797147.2A Active CN114882028B (en) | 2022-07-08 | 2022-07-08 | Multi-camera-based welding terminal detection method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114882028B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119251230A (en) * | 2024-12-05 | 2025-01-03 | 浙江金桥铜业科技有限公司 | Welding quality visual inspection method and system applied to welding machine |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5710631A (en) * | 1995-04-11 | 1998-01-20 | International Business Machines Corporation | Apparatus and method for storing interferometric images of scanned defects and for subsequent static analysis of such defects |
| CN101523287A (en) * | 2006-09-29 | 2009-09-02 | 朗姆研究公司 | Offset correction methods and arrangement for positioning and inspecting substrates |
| CN104165894A (en) * | 2014-06-23 | 2014-11-26 | 中国计量学院 | A detection device used for curved-surface workpiece surface defects |
| CN105243662A (en) * | 2015-09-21 | 2016-01-13 | 广州视源电子科技股份有限公司 | Terminal position determining method and terminal equipment |
| CN106705850A (en) * | 2017-02-09 | 2017-05-24 | 厦门大学 | Image-based terminal quality detection method |
| CN106934803A (en) * | 2017-03-13 | 2017-07-07 | 珠海格力智能装备有限公司 | Method and device for detecting surface defects of electronic device |
| CN106940178A (en) * | 2017-03-22 | 2017-07-11 | 上海日进机床有限公司 | Silicon crystal workpiece flatness detecting device and silicon crystal workpiece measurement method of planeness |
| CN107941811A (en) * | 2017-12-01 | 2018-04-20 | 西南交通大学 | A kind of full-automatic accurate rivet detects screening plant |
| CN108176608A (en) * | 2017-12-25 | 2018-06-19 | 中国科学院自动化研究所 | Nut defect inspection method and device based on machine vision |
| US20180211373A1 (en) * | 2017-01-20 | 2018-07-26 | Aquifi, Inc. | Systems and methods for defect detection |
| EP3636063A1 (en) * | 2018-09-10 | 2020-04-15 | PÖTTINGER Landtechnik GmbH | Method and device for detecting wear of a component for agricultural equipment |
| CN111047547A (en) * | 2019-12-17 | 2020-04-21 | 中国科学院声学研究所 | Combined defect quantification method based on multi-view TFM |
| CN111127394A (en) * | 2019-11-18 | 2020-05-08 | 中科君胜(深圳)智能数据科技发展有限公司 | Overlook shooting visual detection method for bolt installation verticality |
| CN111356914A (en) * | 2018-10-27 | 2020-06-30 | 合刃科技（深圳）有限公司 | Detection method and detection device |
| US20200271758A1 (en) * | 2019-02-26 | 2020-08-27 | Topcon Corporation | Target Instrument And Surveying System |
| CN212389669U (en) * | 2020-12-07 | 2021-01-22 | 陕西紫兆装备制造有限公司 | Shaft coupling with detect axle head axiality function |
| CN113344931A (en) * | 2021-08-09 | 2021-09-03 | 深圳智检慧通科技有限公司 | Plug-in visual detection and identification method, readable storage medium and device |
| CN113450356A (en) * | 2021-09-01 | 2021-09-28 | 蘑菇物联技术（深圳）有限公司 | Method, apparatus, and storage medium for recognizing mounting state of target component |
| CN113706525A (en) * | 2021-10-20 | 2021-11-26 | 武汉飞恩微电子有限公司 | Intelligent printed circuit board patch defect identification method based on image processing |
| CN216348416U (en) * | 2021-11-02 | 2022-04-19 | 四川和心亿科技有限公司 | Rivet quality inspection equipment and image and contour acquisition equipment thereof |
-
2022
- 2022-07-08 CN CN202210797147.2A patent/CN114882028B/en active Active
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5710631A (en) * | 1995-04-11 | 1998-01-20 | International Business Machines Corporation | Apparatus and method for storing interferometric images of scanned defects and for subsequent static analysis of such defects |
| CN101523287A (en) * | 2006-09-29 | 2009-09-02 | 朗姆研究公司 | Offset correction methods and arrangement for positioning and inspecting substrates |
| CN104165894A (en) * | 2014-06-23 | 2014-11-26 | 中国计量学院 | A detection device used for curved-surface workpiece surface defects |
| CN105243662A (en) * | 2015-09-21 | 2016-01-13 | 广州视源电子科技股份有限公司 | Terminal position determining method and terminal equipment |
| US20180211373A1 (en) * | 2017-01-20 | 2018-07-26 | Aquifi, Inc. | Systems and methods for defect detection |
| CN106705850A (en) * | 2017-02-09 | 2017-05-24 | 厦门大学 | Image-based terminal quality detection method |
| CN106934803A (en) * | 2017-03-13 | 2017-07-07 | 珠海格力智能装备有限公司 | Method and device for detecting surface defects of electronic device |
| CN106940178A (en) * | 2017-03-22 | 2017-07-11 | 上海日进机床有限公司 | Silicon crystal workpiece flatness detecting device and silicon crystal workpiece measurement method of planeness |
| CN107941811A (en) * | 2017-12-01 | 2018-04-20 | 西南交通大学 | A kind of full-automatic accurate rivet detects screening plant |
| CN108176608A (en) * | 2017-12-25 | 2018-06-19 | 中国科学院自动化研究所 | Nut defect inspection method and device based on machine vision |
| EP3636063A1 (en) * | 2018-09-10 | 2020-04-15 | PÖTTINGER Landtechnik GmbH | Method and device for detecting wear of a component for agricultural equipment |
| CN111356914A (en) * | 2018-10-27 | 2020-06-30 | 合刃科技（深圳）有限公司 | Detection method and detection device |
| US20200271758A1 (en) * | 2019-02-26 | 2020-08-27 | Topcon Corporation | Target Instrument And Surveying System |
| CN111127394A (en) * | 2019-11-18 | 2020-05-08 | 中科君胜(深圳)智能数据科技发展有限公司 | Overlook shooting visual detection method for bolt installation verticality |
| CN111047547A (en) * | 2019-12-17 | 2020-04-21 | 中国科学院声学研究所 | Combined defect quantification method based on multi-view TFM |
| CN212389669U (en) * | 2020-12-07 | 2021-01-22 | 陕西紫兆装备制造有限公司 | Shaft coupling with detect axle head axiality function |
| CN113344931A (en) * | 2021-08-09 | 2021-09-03 | 深圳智检慧通科技有限公司 | Plug-in visual detection and identification method, readable storage medium and device |
| CN113450356A (en) * | 2021-09-01 | 2021-09-28 | 蘑菇物联技术（深圳）有限公司 | Method, apparatus, and storage medium for recognizing mounting state of target component |
| CN113706525A (en) * | 2021-10-20 | 2021-11-26 | 武汉飞恩微电子有限公司 | Intelligent printed circuit board patch defect identification method based on image processing |
| CN216348416U (en) * | 2021-11-02 | 2022-04-19 | 四川和心亿科技有限公司 | Rivet quality inspection equipment and image and contour acquisition equipment thereof |
Non-Patent Citations (4)
| Title |
|---|
| AKIRA KUSANO 等: "Defect detection of terminal lead by single stereo vision", 《THE 19TH KOREA-JAPAN JOINT WORKSHOP ON FRONTIERS OF COMPUTER VISION》 * |
| 刘作鹏 等: "输电电缆引线端子过热故障分析", 《东北电力技术》 * |
| 徐超: "基于视觉测量的沉头孔垂直度检测新技术研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 邓智超 等: "基于改进残差网络的多视图焊点缺陷检测", 《焊接学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119251230A (en) * | 2024-12-05 | 2025-01-03 | 浙江金桥铜业科技有限公司 | Welding quality visual inspection method and system applied to welding machine |
| CN119251230B (en) * | 2024-12-05 | 2025-03-07 | 浙江金桥铜业科技有限公司 | Welding quality visual inspection method and system applied to welding machine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114882028B (en) | 2022-10-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7978903B2 (en) | Defect detecting method and defect detecting device | |
| US6289117B1 (en) | Analysis of an image of a pattern of discrete objects | |
| US11567207B2 (en) | Apparatus and method for efficient point cloud feature extraction and segmentation framework | |
| CN106485275A (en) | A kind of cover-plate glass of realizing positions, with liquid crystal display screen, the method fitted | |
| CN108154502A (en) | A kind of though-hole solder joint recognition methods based on convolutional neural networks | |
| CN114240845B (en) | Light cutting method surface roughness measurement method applied to cutting workpiece | |
| CN114882028B (en) | Multi-camera-based welding terminal detection method, device and system | |
| US20230118709A1 (en) | Method for detecting undesired connection on printed circuit board | |
| US9996766B2 (en) | Imaging-based methods for detecting and measuring defects in extruded cellular ceramic articles | |
| CN114199148A (en) | Heat exchanger fin pitch measurement method and device based on machine vision and medium | |
| CN117058411B (en) | Method, device, medium and equipment for identifying edge appearance flaws of battery | |
| CN114972575A (en) | A Line Fitting Algorithm Based on Contour Edge | |
| CN117611528A (en) | PCB image detection method and device | |
| CN115880209A (en) | Surface defect detection system, method, device and medium suitable for steel plate | |
| CN114638793B (en) | Screen aging degree detection method and device | |
| Johan et al. | Weld seam feature point extraction using laser and vision sensor | |
| WO2013191132A1 (en) | Analyzing system and method for repeatedly patterned image and three-dimensionally repeated structural data | |
| Hocenski et al. | A simple and efficient method for ceramic tile surface defects detection | |
| CN115272134B (en) | PCB image reflection removing method based on PCB interference reflection recognition | |
| CN115631199B (en) | Pin needle defect detection method, device, equipment and storage medium | |
| JP2005003473A (en) | Visual inspection method for welding mark | |
| JPH04346011A (en) | Visual inspection apparatus for soldered state | |
| JP2007033126A (en) | Substrate inspection device, parameter adjusting method thereof and parameter adjusting device | |
| JP4821647B2 (en) | Electronic component terminal position detection method | |
| Guclu et al. | Enhanced defect detection on steel surfaces using integrated residual refinement module with synthetic data augmentation |
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 |