CN110634128A - Ball pin size detection method and device, computer equipment and storage medium - Google Patents
Ball pin size detection method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110634128A CN110634128A CN201910755038.2A CN201910755038A CN110634128A CN 110634128 A CN110634128 A CN 110634128A CN 201910755038 A CN201910755038 A CN 201910755038A CN 110634128 A CN110634128 A CN 110634128A
- Authority
- CN
- China
- Prior art keywords
- image
- ball stud
- edge
- detection
- straight line
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
Abstract
The invention is suitable for the field of computers, and provides a ball stud size detection method, a ball stud size detection device, computer equipment and a storage medium, wherein the ball stud size detection method comprises the following steps: acquiring a first image, and preprocessing the first image to obtain a second image, wherein the second image at least comprises a contour map of the ball stud; performing edge detection on the contour map, and determining an edge line of the ball stud; and performing line detection based on Hough transformation on the edge line, determining a straight line part in the edge line, determining two end points of the straight line part, measuring the distance between the two end points by adopting an Euclidean distance, and obtaining and outputting the linear size of the ball stud. According to the ball stud size detection method provided by the embodiment of the invention, the image of the ball stud is identified and measured through the computer program, the image noise is eliminated through image preprocessing, image edge detection and linear detection, the size is measured through the computer program, the speed is high, the efficiency is high, the product quality is ensured, and the production cost is reduced.
Description
Technical Field
The invention belongs to the field of computers, and particularly relates to a ball stud size detection method and device, computer equipment and a storage medium.
Background
The ball stud is widely adopted in an independent suspension system, is used for realizing connection between a control arm or a thrust rod and other parts, and is used as a relatively precise connecting piece, and the shape and the size of the ball stud are important detection parameters in the generation process.
The existing detection on the size and the shape of the ball pin is realized through manual jig detection, but the jig is abraded in the using process, so that the detection on the ball pin is error, the defects of low efficiency, poor precision and limited detection quantity exist in manual detection, the labor cost is also high, the worker is easy to fatigue, the missed detection or the false detection is caused, defective products or unqualified products flow into the market, and the loss on reputation and economy is caused to a merchant.
Therefore, the size of the conventional ball stud is detected basically by manpower, the cost is high, the precision is low, the efficiency is low, and the improvement is urgently needed.
Disclosure of Invention
The embodiment of the invention aims to provide a ball stud size detection method, a ball stud size detection device, computer equipment and a storage medium, and aims to solve the technical problems that the existing ball stud size detection basically depends on manual detection, and is high in cost, low in precision and low in efficiency.
The embodiment of the invention is realized in such a way that a method for detecting the size of a ball stud comprises the following steps:
acquiring a first image, wherein the first image at least comprises a complete ball stud image;
preprocessing the first image to obtain a second image, wherein the second image at least comprises a contour map of the ball stud;
carrying out edge detection on the contour map, and determining an edge line of the ball stud in the contour map;
carrying out straight line detection based on Hough transformation on the edge line, and determining a straight line part in the edge line;
and determining two end points of the straight line part by adopting a nearest neighbor searching algorithm, measuring the distance between the two end points by adopting an Euclidean distance in a coordinate system, and obtaining and outputting the straight line size of the ball stud.
Another object of an embodiment of the present invention is to provide a ball stud size detecting apparatus, including:
the device comprises an image acquisition device, a first image acquisition device and a second image acquisition device, wherein the first image acquisition device is used for acquiring a first image which at least comprises a complete ball stud image;
the image preprocessing device is used for preprocessing the first image to obtain a second image, and the second image at least comprises a contour map of the ball stud;
the edge detection device is used for carrying out edge detection on the contour map and determining an edge line of the ball stud in the contour map;
the straight line detection device is used for carrying out straight line detection based on Hough transformation on the edge line and determining a straight line part in the edge line; and
and the information output device is used for determining two end points of the straight line part by adopting a nearest neighbor search algorithm, measuring the distance between the two end points by adopting an Euclidean distance in a coordinate system, and obtaining and outputting the linear dimension of the ball stud.
Another object of an embodiment of the present invention is to provide a computer device, which includes a memory and a processor, where the memory stores a computer program, and the computer program, when executed by the processor, causes the processor to execute the steps of the ball stud size detection method according to the above embodiment.
Another object of an embodiment of the present invention is to provide a computer-readable storage medium, wherein the computer-readable storage medium stores thereon a computer program, and when the computer program is executed by a processor, the processor is enabled to execute the steps of the ball stud size detecting method according to the above embodiment.
The method for detecting the size of the ball pin comprises the steps of collecting an image with a detection ball pin, preprocessing the image, filtering and denoising the image to obtain a contour map of the ball pin, finding out an edge line of the ball pin through edge detection, performing line detection based on Hough transformation on the edge line to determine a straight line part in the edge line, measuring the length of the straight line part to determine the size of the ball pin, identifying and measuring the image of the ball pin through a computer program, eliminating image noise through image preprocessing, image edge detection and line detection, ensuring the accuracy of size detection, measuring the size through the computer program, and reducing the production cost while ensuring the product quality.
Drawings
FIG. 1 is a flow chart illustrating a method for detecting a size of a ball stud according to an embodiment of the present invention;
FIG. 2 illustrates a schematic view of a ball stud shape provided by the practice of the present invention;
FIG. 3 is a graph illustrating gradient strength of a pixel according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram illustrating a ball stud size detection apparatus according to an embodiment of the present invention;
fig. 5 is a diagram illustrating an internal structure of a computer device according to an embodiment of the present invention.
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.
Fig. 1 is a flowchart of a ball stud size detection method according to an embodiment of the present invention. As shown in fig. 1, a method for detecting a size of a ball stud may specifically include the following steps:
step S102, a first image is obtained, and the first image at least comprises a complete ball stud image.
In an embodiment of the present invention, fig. 2 shows a schematic shape of a ball stud provided by the practice of the present invention, as shown in fig. 2, which is widely used in independent suspension systems, a control arm or a thrust rod is often connected to other components through a ball stud at an end portion, and the main function of the ball stud is to realize up-and-down bouncing and steering movements of a wheel. The first image should at least include a complete ball stud image, and the ball stud image should show the portion of the ball stud to be measured.
In the embodiment of the present invention, the first image may be obtained through a wireless network, or may be obtained through a wired network, or directly read the first image stored in the removable storage medium, which is not limited in the present invention.
The embodiment of the invention acquires the ball stud image in various ways, facilitates subsequent size detection and can be applied to various scenes.
And step S104, preprocessing the first image to obtain a second image, wherein the second image at least comprises a contour map of the ball stud.
In the embodiment of the invention, the contour map refers to a shape contour map of the ball stud in the image, and the preprocessing refers to operations performed on the image before detecting the length in the image, including filtering, drying, sharpening, enhancing and the like.
As an embodiment of the present invention, the preprocessing of the first image may include actual advanced visualization processing and any preparation of image data for subsequent advanced visualization processing, including image enhancement processing of the original image, transforming the gray scale of the image to make its image sharp, contrast enhancement, edge feature highlighting, and image smoothing processing of the processed image to remove additive noise, multiplicative noise, and quantization noise. As an embodiment of the present invention, a gray scale conversion is performed on an original image, the gray scale conversion enhances the contrast of the image or stretches the contrast of the image to generate a gray scale enhanced image, and the gray scale enhanced image is converted into a histogram equalization image: setting the original gray scale of a pixel point in an original image as R, the gray scale of the pixel point after gray scale transformation as S, and the gray scale transformation function as T (R), then performing gray scale transformation according to the following formula:
wherein R is more than or equal to 0j≤l-1；py(Rj) Is the probability of the gray value of the j-th level, njIs the total number of pixels of the j-level gray in the image, l is the total number of gray levels in the image, n is the total number of pixels in the image, j identifies the level of gray that is consistent according to the gray level that can be identified in the computer.
The image preprocessing method provided by the embodiment of the invention solves the technical problem of carrying out sharpening processing on the image acquired by the camera, and the image preprocessing method adopts the processing methods of image enhancement, smooth filtering and image sharpening, so that the noise is effectively eliminated, the image quality is improved, the image is sharpened, and the effective information can be better extracted for subsequent analysis.
And S106, carrying out edge detection on the contour map, and determining an edge line of the ball stud in the contour map.
In embodiments of the present invention, edge detection is a fundamental problem in image processing and computer vision, the purpose of which is to identify points in a digital image where changes in brightness are significant, and where significant changes in image properties typically reflect significant events and changes in properties, including discontinuities in depth, surface orientation discontinuities, material property changes, and scene lighting changes.
As an embodiment of the present invention, a Canny edge detector and/or a Sobel edge detector may be used to perform edge detection on the contour map, so as to determine the edge line of the ball stud. As a self-service hairIn one embodiment, Canny edge detection operators are adopted to carry out edge detection on the image, the first step is to convolute the original data with Gaussian mask, and the obtained image is slightly blurred compared with the original image. Thus, the single-pixel noise becomes almost unaffected on the gaussian-smoothed image. Then, the intensity gradient in the image is searched, the gradient of each pixel point in the smoothed image can be obtained by a Sobel operator, and firstly, the gradients G along the horizontal (x) direction and the vertical (y) direction are respectively obtained by utilizing the following kernelsxAnd GySuch as:
＝[-101；-202；-121]；＝[-1-2-1；000；121]
then, the gradient amplitude of each pixel point can be obtained by using a formula:
sometimes G will be used for simplicity of calculationxAnd GyInstead of a two-norm. Replacing each point in the smoothed image with G, and obtaining a larger gradient metric G at the place (boundary) with severe change, wherein the corresponding color is white; however, these boundaries are often very thick, making it difficult to calibrate the true location of the boundary. To do this, it is also necessary to store the gradient direction, which is formulated as follows:
Θ＝arctan2(Gy，Gx)
after the intensity gradient of the image is found, the gradient direction of the image is approximate to one of the following values (0,45,90,135,180,225,270,315), the gradient strength of the pixel point in the positive and negative directions of the gradient direction of the image is compared, if the gradient strength of the pixel point is maximum, the gradient strength is kept, otherwise, the inhibition is carried out, as shown in FIG. 3, the number in the figure represents the gradient strength of the pixel point, and the arrow direction represents the gradient direction. Taking the third pixel point in the second row as an example, since the gradient direction is upward, the intensity (7) of the point is compared with the intensities (5 and 4) of the two pixel points above and below the point, and since the intensity of the point is the maximum, the point is retained. Because the gradient direction at the boundary always points to the direction perpendicular to the boundary, namely, a brightest thin line at the boundary is finally reserved, and then the edge line of the ball stud is detected by using the following boundary tracking.
According to the embodiment of the invention, the accurate edge line of the ball stud in the image is obtained through edge detection, so that the size of the ball stud can be identified conveniently.
And step S108, carrying out straight line detection based on Hough transformation on the edge line, and determining a straight line part in the edge line.
In the embodiment of the invention, the dual characteristic of point lines is utilized, namely the characteristics that collinear points in an image space correspond to intersected lines in a parameter space, and all straight lines intersected at the same point in the parameter space have the corresponding collinear points in the image space, so that the straight line detection problem in the image space is converted into the detection problem of the point in the parameter space, and the detection task is completed by carrying out simple accumulation statistics in the parameter space.
As an embodiment of the present invention, after the edge line of the ball stud in the image is extracted, the detection of the straight portion of the edge line of the ball stud is required to facilitate the detection of the size of the straight portion of the ball stud. In the embodiment of the invention, a straight line detection method based on Hough transformation is adopted to carry out straight line detection on an edge line, the straight line is detected by carrying out simple accumulation statistics in a parameter space and then searching for the peak value of an accumulator in the Hough parameter space, the essence of the Hough transformation is to cluster pixels with a certain relation in an image space and search for a parameter space accumulation corresponding point which can link the pixels in a certain analytic form, and the specific operation steps are explained in detail in the following part of the specification.
According to the embodiment of the invention, the edge line of the ball stud is subjected to linear detection through linear detection based on Hough transformation to obtain the linear part in the ball stud image, so that the subsequent detection of the size of the linear part of the ball stud is facilitated, the identification precision is high, and the detection result is accurate.
Step S110, determining two end points of the straight line part by adopting a nearest neighbor searching algorithm, measuring the distance between the two end points by adopting an Euclidean distance in a coordinate system, and obtaining and outputting the linear size of the ball stud.
In the embodiment of the present invention, the euclidean distance is an euclidean distance, and is a common distance between two points in an euclidean space, that is, a straight line distance.
As an embodiment of the present invention, in the straight-line portion obtained in step S108, through the confirmation of gray values, when the average gray value of a certain pixel area is significantly higher than the gray values of the area in three directions and slightly lower than the gray values of the area in another direction, the pixel area is used as an endpoint, a nearest neighbor search algorithm is used to find a second endpoint in the straight-line portion, so as to determine two endpoints of the straight-line portion, the two endpoints are projected into a rectangular coordinate system, and then the formula is used:
calculating Euclidean distance l of two end points, wherein x1、y1、x2、y2The coordinate values of the first end point and the second end point in the rectangular coordinate system are respectively. And after the distance between the two end points is obtained through calculation, directly outputting l, namely the size of the linear part of the ball stud.
The method for detecting the size of the ball pin comprises the steps of collecting an image with a detection ball pin, preprocessing the image, filtering and denoising the image to obtain a contour map of the ball pin, finding out an edge line of the ball pin through edge detection, performing line detection based on Hough transformation on the edge line to determine a straight line part in the edge line, measuring the length of the straight line part to determine the size of the ball pin, identifying and measuring the image of the ball pin through a computer program, eliminating image noise through image preprocessing, image edge detection and line detection, ensuring the accuracy of size detection, measuring the size through the computer program, and reducing the production cost while ensuring the product quality.
As an embodiment of the present invention, the preprocessing the first image to obtain a second image includes:
performing gradient sharpening on the first image; the gradient sharpening formula is:
wherein f (x, y) represents an image, G'M[f(x，y)]For the final gray-scale replacement value,
G′M[f(x，y)]max＝225，T′1representing a sharpening threshold value when the gradient value is greater than T'1While, the gradient edge is strengthened; t'2Representing a gray level threshold value when the gray level of the image is greater than T'2While, the gray value is decreased by T2。
And acquiring edge gray values of the ball stud image in the sharpened first image, and taking connected pixel points with gray value differences meeting edge judgment conditions as the outline of the ball stud to obtain a second image.
In the embodiment of the invention, the existing image sharpening uses bidirectional first differential operation, the gradient value is directly used for replacing the gray value of the point after the gradient is calculated, and the pixel value of the last row and column of the image is filled with the adjacent gradient value. Experiments show that the gradient value is directly used for replacing the gray value to cause the image to lose a large amount of original information, the invention sets a threshold for judging and improves the gradient sharpening according to the characteristics of the ball stud image, and the specific formula is as follows:
wherein f (x, y) represents an image, G'M[f(x，y)]Is a final gray-scale-level-substitute value, G'M[f(x，y)]max＝225，T′1Representing a sharpening threshold value when the gradient value is greater than T'1While, the gradient edge is strengthened; t'2Representing a gray level threshold value when the gray level of the image is greater than T'2While, the gray value is decreased by T2(ii) a The gradient sharpening method can retain the high gray value information of the original ball stud imageMeanwhile, the influence of the gradient edge on the gradient edge is eliminated, the gray value is unchanged under other conditions, and the processed image enhances the outline of the ball stud and increases the distinguishing degree of the edge information and other backgrounds. And after the edge is sharpened, acquiring a gray value of the image, analyzing the gray value, and when a boundary of the gray value of the image is obvious from appearance, the boundary is the edge line of the ball stud.
According to the embodiment of the invention, the edge gradient is enhanced by sharpening the ball stud image, the edge line of the ball stud is determined through the distribution of gray values, and the identification and measurement of the edge line and the subsequent linear part of the ball stud are carried out, so that the speed is high, and the measurement is accurate.
In an embodiment of the present invention, the performing edge detection on the contour map and determining an edge line of the ball stud in the contour map includes:
and performing edge detection on the contour diagram by using a Canny edge detection operator and/or a Sobel edge detection operator to determine the edge line of the ball stud.
As an embodiment of the present invention, a Canny edge detector and/or a Sobel edge detector may be used to perform edge detection on the contour map, so as to determine the edge line of the ball stud. As an embodiment of the invention, Canny edge detection operator is adopted to carry out edge detection on the image, the first step is to convolute the original data with Gaussian mask, and the obtained image is slightly blurred compared with the original image. Thus, the single-pixel noise becomes almost unaffected on the gaussian-smoothed image. Then, the intensity gradient in the image is searched, the gradient of each pixel point in the smoothed image can be obtained by a Sobel operator, and firstly, the gradients G along the horizontal (x) direction and the vertical (y) direction are respectively obtained by utilizing the following kernelsxAnd GySuch as:
＝[-101；-202；-121]；＝[-1-2-1；000；121]
then, the gradient amplitude of each pixel point can be obtained by using a formula:
sometimes G will be used for simplicity of calculationxAnd GyInstead of a two-norm. Replacing each point in the smoothed image with G, and obtaining a larger gradient metric G at the place (boundary) with severe change, wherein the corresponding color is white; however, these boundaries are often very thick, making it difficult to calibrate the true location of the boundary. To do this, it is also necessary to store the gradient direction, which is formulated as follows:
Θ＝arctan2(Gy，Gx)
after the intensity gradient of the image is found, the gradient direction of the image is approximate to one of the following values (0,45,90,135,180,225,270,315), the gradient strength of the pixel point in the positive and negative directions of the gradient direction of the image is compared, if the gradient strength of the pixel point is maximum, the gradient strength is kept, otherwise, the inhibition is carried out, as shown in FIG. 3, the number in the figure represents the gradient strength of the pixel point, and the arrow direction represents the gradient direction. Taking the third pixel point in the second row as an example, since the gradient direction is upward, the intensity (7) of the point is compared with the intensities (5 and 4) of the two pixel points above and below the point, and since the intensity of the point is the maximum, the point is retained. Because the gradient direction at the boundary always points to the direction perpendicular to the boundary, namely, a brightest thin line at the boundary is finally reserved, and then the edge line of the ball stud is detected by using the following boundary tracking.
According to the embodiment of the invention, the accurate edge line of the ball stud in the image is obtained through edge detection, so that the size of the ball stud can be identified conveniently.
As an embodiment of the present invention, the performing Hough transform-based line detection on the edge line to determine a straight line portion in the edge line includes:
projecting the edge line into a plane rectangular coordinate system, and acquiring the coordinates of sampling points on the edge line;
converting the sampling points to a polar coordinate system through polar coordinate operation; wherein the transformation equation is as follows:
wherein x and y represent the horizontal and vertical coordinates of the sample point in the rectangular plane coordinate system,
p represents the polar diameter of the sample point, and theta is the polar angle of the sample point;
and detecting the number of collinear points in the sampling points under the polar coordinates, and judging that a straight line is detected when the number of the collinear points is greater than a preset value.
In an embodiment of the invention, a point in the original image space corresponds to a sinusoid in the new parameter space, i.e. a point-sinusoid pair. The specific process of detecting the straight line is to make theta take possible values, then calculate the rho value, and accumulate the array according to the values of theta and rho to obtain the number of collinear points. When the straight line rotates anticlockwise from the position overlapped with the x axis, the value of theta starts to increase from 0 DEG to 180 DEG, namely the value range of theta is 0-180 deg. From the linear polar equation:
so if and only if x and y both reach a maximum and θ + Φ is ± 90 °, there is:
that is, the value range of ρ is:
the size of the Hough transformation accumulator can be determined according to the value ranges of theta and rho and the resolution ratios of theta and rho, and points of which the accumulated value is smaller than the threshold value in the Hough transformation accumulator are cleared according to the size of the threshold value, namely the points are not considered to correspond to a straight line in the image domain until the straight line is detected.
In the embodiment of the invention, the linear part of the contour line of the ball pin is detected by a line detection algorithm based on Hough transformation, so that the accuracy of linear detection is ensured, and the accuracy of size measurement of the linear part of the ball pin is ensured.
As an embodiment of the present invention, before determining two end points of the straight line portion by using a nearest neighbor searching algorithm, and measuring a distance between the two end points by using an euclidean distance in a coordinate system, and obtaining and outputting a straight line size of the ball stud, the method further includes:
determination of the magnification of an optical system by static calibration of a workpiece of known dimension L
K is the pixel size of the camera, and N is the number of pixels occupied by the workpiece on the image;
by the formula
Calculating the adjusted magnification beta of the optical system1Wherein δ is vibration displacement, and μ is object distance of the optical system during static calibration;
using formulas
Calculating the size of the ball stud; wherein l is the size of the ball stud after error compensation, N1The number of pixel points occupied by the ball pin on the second image is
In the embodiment of the invention, in the high-speed online detection process, the conveying mechanism drives the workpiece to operate, the workpiece and the surface of the conveying mechanism generate vibration, and the vibration can be decomposed into two directions: i.e. vertical vibrations perpendicular to the direction of movement of the transport mechanism, back and forth vibrations along the direction of movement of the transport mechanism. Vertical vibration will cause changes in object distance in the optical imaging system, changing the magnification of the imaging system, and introducing dimensional measurement errors. The front-back vibration refers to that the conveying mechanism runs at a certain speed in the online detection process, so that relative motion is generated between the workpiece and the conveying mechanism. The image blurring phenomenon caused by motion blurring in the online detection process can make the detail resolution of the surface of an object unclear, the definition of an image is directly influenced, the resolution of the surface characteristics of a workpiece image is difficult, and the edge of the image is enlarged due to the motion blurring, so that the size measurement precision is influenced.
As an embodiment of the present invention, the compensation of the vibration error is divided into vertical error compensation and horizontal vibration error compensation, wherein in the vertical error compensation, the on-line dimension detection of the workpiece is performed, and the corresponding relationship between the image pixel and the actual dimension is established. And (4) performing static calibration by using the workpiece with the known size L, and determining the imaging magnification. The optical system magnification is beta and the camera pixel size is K. And processing the workpiece image to obtain the number N of the pixels of the workpiece on the image. The magnification is then:
the method comprises the steps of carrying out online size detection on a workpiece without changing parameters of an online image acquisition device, not considering vertical vibration compensation, setting the number of pixels occupied by the workpiece on an image and setting a target workpiece size detection value as N1From the above formula, N is:
the vertical vibration error compensation is carried out on the workpiece size in the process of detecting the linear size, and the magnification beta is calculated by an optical Gaussian formula under the condition of not changing the focal length1Comprises the following steps:
wherein delta is vibration displacement, beta is magnification ratio in static calibration, and the object distance mu of the optical imaging system in the static calibration is calculated by beta and focal length.
Considering the influence of vertical vibration factor on the dimensional measurement accuracy, according to the above formulaCompensating for the error in the measured dimension due to vibration, so that the compensated dimension measurement value L2Comprises the following steps:
wherein N is1The number of pixels of the workpiece on the image is the number of the pixels occupied by the workpiece in online detection. The method corrects the magnification of the optical system in real time through online measurement of the vertical vibration displacement of the workpiece, and compensates the size detection error caused by the vertical vibration.
For the horizontal vibration error, when the speed v of the transmission mechanism is fixed, and the exposure time of the camera is set as t, the motion blur value of the measured object relative to the imaging system is as follows:
x＝vtβ
in the case of v, β determination, x is affected by t. In practical application, as long as on-line detection is adopted, the motion blur cannot be eliminated due to the existence of the speed, so that the motion blur can be only controlled and reduced to a size measurement accuracy. The common method is to control the motion blur value by reducing the exposure time, which is beneficial to reducing the influence of speed factors and front and back vibration on the dimension measurement value in the online detection. However, the reduction of the motion blur needs to be at the cost of reducing the exposure time, which may cause insufficient image brightness and difficulty in recognition, and at this time, the shortage of the light source needs to be compensated by the high-brightness light source and the large light-transmitting aperture, which may increase the detection cost, and the high-brightness light source has a large heat value, which is not favorable for long-term operation. A large clear aperture results in a reduction of the depth of field of the lens. Therefore, the motion blur control needs to be realized by comprehensively considering the reduction of the exposure time, the size control of the clear aperture and the light source brightness adjustment.
According to the embodiment of the invention, the vertical vibration error compensation and the horizontal vibration error compensation are carried out on the image, so that the influence of the error on the measurement result is reduced as much as possible, the accuracy of the dimension measurement result is improved, and the precision and the yield of the product are ensured.
The method for detecting the size of the ball pin comprises the steps of collecting an image with a detection ball pin, preprocessing the image, filtering and denoising the image to obtain a contour map of the ball pin, finding out an edge line of the ball pin through edge detection, performing line detection based on Hough transformation on the edge line to determine a straight line part in the edge line, measuring the length of the straight line part to determine the size of the ball pin, identifying and measuring the image of the ball pin through a computer program, eliminating image noise through image preprocessing, image edge detection and line detection, ensuring the accuracy of size detection, measuring the size through the computer program, and reducing the production cost while ensuring the product quality.
Fig. 4 is a schematic structural diagram of a ball stud size detection apparatus according to an embodiment of the present invention, and as shown in fig. 4, the ball stud size detection apparatus according to the embodiment of the present invention includes:
the image acquiring device 410 is configured to acquire a first image, where the first image at least includes a complete ball stud image.
In an embodiment of the present invention, fig. 2 shows a schematic shape of a ball stud provided by the practice of the present invention, as shown in fig. 2, which is widely used in independent suspension systems, a control arm or a thrust rod is often connected to other components through a ball stud at an end portion, and the main function of the ball stud is to realize up-and-down bouncing and steering movements of a wheel. The first image should at least include a complete ball stud image, and the ball stud image should show the portion of the ball stud to be measured.
In the embodiment of the present invention, the first image may be obtained through a wireless network, or may be obtained through a wired network, or may be obtained through a local area network, or directly read the first image stored in the removable storage medium, which is not limited in the present invention.
The embodiment of the invention acquires the ball stud image in various ways, facilitates subsequent size detection and can be applied to various scenes.
And the image preprocessing device 420 is configured to preprocess the first image to obtain a second image, where the second image at least includes the contour map of the ball stud.
In the embodiment of the invention, the contour map refers to a shape contour map of the ball stud in the image, and the preprocessing refers to operations performed on the image before detecting the length in the image, including filtering, drying, sharpening, enhancing and the like.
As an embodiment of the present invention, the preprocessing of the first image may include actual advanced visualization processing and any preparation of image data for subsequent advanced visualization processing, including image enhancement processing of the original image, transforming the gray scale of the image to make its image sharp, contrast enhancement, edge feature highlighting, and image smoothing processing of the processed image to remove additive noise, multiplicative noise, and quantization noise. As an embodiment of the present invention, a gray scale conversion is performed on an original image, the gray scale conversion enhances the contrast of the image or stretches the contrast of the image to generate a gray scale enhanced image, and the gray scale enhanced image is converted into a histogram equalization image: setting the original gray scale of a pixel point in an original image as R, the gray scale of the pixel point after gray scale transformation as S, and the gray scale transformation function as T (R), then performing gray scale transformation according to the following formula:
wherein R is more than or equal to 0j≤l-1；py(Rj) Is the probability of the gray value of the j-th level, njIs the total number of pixels of the j-level gray in the image, l is the total number of gray levels in the image, n is the total number of pixels in the image, j identifies the level of gray that is consistent according to the gray level that can be identified in the computer.
The image preprocessing method provided by the embodiment of the invention solves the technical problem of carrying out sharpening processing on the image acquired by the camera, and the image preprocessing method adopts the processing methods of image enhancement, smooth filtering and image sharpening, so that the noise is effectively eliminated, the image quality is improved, the image is sharpened, and the effective information can be better extracted for subsequent analysis.
And the edge detection device 430 is used for performing edge detection on the contour map and determining an edge line of the ball stud in the contour map.
In embodiments of the present invention, edge detection is a fundamental problem in image processing and computer vision, the purpose of which is to identify points in a digital image where changes in brightness are significant, and where significant changes in image properties typically reflect significant events and changes in properties, including discontinuities in depth, surface orientation discontinuities, material property changes, and scene lighting changes.
As an embodiment of the present invention, a Canny edge detector and/or a Sobel edge detector may be used to perform edge detection on the contour map, so as to determine the edge line of the ball stud. As an embodiment of the invention, Canny edge detection operator is adopted to carry out edge detection on the image, the first step is to convolute the original data with Gaussian mask, and the obtained image is slightly blurred compared with the original image. Thus, the single-pixel noise becomes almost unaffected on the gaussian-smoothed image. Then, the intensity gradient in the image is searched, the gradient of each pixel point in the smoothed image can be obtained by a Sobel operator, and firstly, the gradients G along the horizontal (x) direction and the vertical (y) direction are respectively obtained by the following sumxAnd GySuch as:
＝[-101；-202；-121]；＝[-1-2-1；000；121]
then, the gradient amplitude of each pixel point can be obtained by using a formula:
sometimes G will be used for simplicity of calculationxAnd GyInstead of a two-norm. Replacing each point in the smoothed image with G, and obtaining a larger gradient metric G at the place (boundary) with severe change, wherein the corresponding color is white; however, these boundaries are often very thick, making it difficult to calibrate the true location of the boundary. To do soThe point, the gradient direction must also be stored, which is formulated as follows:
Θ＝arctan2(Gy，Gx)
after the intensity gradient of the image is found, the gradient direction of the image is approximate to one of the following values (0,45,90,135,180,225,270,315), the gradient strength of the pixel point in the positive and negative directions of the gradient direction of the image is compared, if the gradient strength of the pixel point is maximum, the gradient strength is kept, otherwise, the inhibition is carried out, as shown in FIG. 2, the number in the figure represents the gradient strength of the pixel point, and the arrow direction represents the gradient direction. Taking the third pixel point in the second row as an example, since the gradient direction is upward, the intensity (7) of the point is compared with the intensities (5 and 4) of the two pixel points above and below the point, and since the intensity of the point is the maximum, the point is retained. Because the gradient direction at the boundary always points to the direction perpendicular to the boundary, namely, a brightest thin line at the boundary is finally reserved, and then the edge line of the ball stud is detected by using the following boundary tracking.
According to the embodiment of the invention, the accurate edge line of the ball stud in the image is obtained through edge detection, so that the size of the ball stud can be identified conveniently.
And the straight line detection device 440 is used for performing straight line detection based on Hough transformation on the edge line and determining a straight line part in the edge line.
In the embodiment of the invention, the dual characteristic of point lines is utilized, namely the characteristics that collinear points in an image space correspond to intersected lines in a parameter space, and all straight lines intersected at the same point in the parameter space have the corresponding collinear points in the image space, so that the straight line detection problem in the image space is converted into the detection problem of the point in the parameter space, and the detection task is completed by carrying out simple accumulation statistics in the parameter space.
As an embodiment of the present invention, after the edge line of the ball stud in the image is extracted, the detection of the straight portion of the edge line of the ball stud is required to facilitate the detection of the size of the straight portion of the ball stud. In the embodiment of the invention, a straight line detection method based on Hough transformation is adopted to carry out straight line detection on an edge line, the straight line is detected by carrying out simple accumulation statistics in a parameter space and then searching for the peak value of an accumulator in the Hough parameter space, the essence of the Hough transformation is to cluster pixels with a certain relation in an image space and search for a parameter space accumulation corresponding point which can link the pixels in a certain analytic form, and the specific operation steps are explained in detail in the following part of the specification.
According to the embodiment of the invention, the edge line of the ball stud is subjected to linear detection through linear detection based on Hough transformation to obtain the linear part in the ball stud image, so that the subsequent detection of the size of the linear part of the ball stud is facilitated, the identification precision is high, and the detection result is accurate.
And the information output device 450 is configured to determine two end points of the straight line portion by using a nearest neighbor search algorithm, measure a distance between the two end points by using a euclidean distance in a coordinate system, and obtain and output a straight line size of the ball stud.
In the embodiment of the present invention, the euclidean distance is an euclidean distance, and is a common distance between two points in an euclidean space, that is, a straight line distance.
As an embodiment of the present invention, in the straight-line portion obtained in step S108, through the confirmation of gray values, when the average gray value of a certain pixel area is significantly higher than the gray values of the area in three directions and slightly lower than the gray values of the area in another direction, the pixel area is used as an endpoint, a nearest neighbor search algorithm is used to find a second endpoint in the straight-line portion, so as to determine two endpoints of the straight-line portion, the two endpoints are projected into a rectangular coordinate system, and then the formula is used:
calculating Euclidean distance l of two end points, wherein x1、y1、y2、y2The coordinate values of the first end point and the second end point in the rectangular coordinate system are respectively. And after the distance between the two end points is obtained through calculation, directly outputting l, namely the size of the linear part of the ball stud.
According to the ball pin size detection device provided by the embodiment of the invention, the image of the ball pin is detected through the acquisition belt, the image is preprocessed, the filtering and denoising of the image are realized, the contour map of the ball pin is obtained, then the edge line of the ball pin is found out through the edge detection, the straight line detection based on Hough transformation is carried out on the edge line, the straight line part in the edge line is determined, the length of the straight line part is measured, the size of the ball pin is determined, the image of the ball pin is identified and measured through a computer program, the image noise is eliminated through the image preprocessing, the edge detection of the image and the straight line detection, the size detection accuracy is ensured, meanwhile, the size is measured through the computer program, the speed is high, the efficiency is high, the product quality is ensured, and the production cost is reduced.
FIG. 5 is a diagram illustrating an internal structure of a computer device in one embodiment. 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 also store a computer program that, when executed by the processor, causes the processor to implement the ball stud size detection method. The internal memory may also store a computer program, and the computer program, when executed by the processor, may cause the processor to perform the ball stud size detection method. 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 architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
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:
acquiring a first image, wherein the first image at least comprises a complete ball stud image;
preprocessing the first image to obtain a second image, wherein the second image at least comprises a contour map of the ball stud;
carrying out edge detection on the contour map, and determining an edge line of the ball stud in the contour map;
carrying out straight line detection based on Hough transformation on the edge line, and determining a straight line part in the edge line;
and determining two end points of the straight line part by adopting a nearest neighbor searching algorithm, measuring the distance between the two end points by adopting an Euclidean distance in a coordinate system, and obtaining and outputting the straight line size of the ball stud.
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:
acquiring a first image, wherein the first image at least comprises a complete ball stud image;
preprocessing the first image to obtain a second image, wherein the second image at least comprises a contour map of the ball stud;
carrying out edge detection on the contour map, and determining an edge line of the ball stud in the contour map;
carrying out straight line detection based on Hough transformation on the edge line, and determining a straight line part in the edge line;
and determining two end points of the straight line part by adopting a nearest neighbor searching algorithm, measuring the distance between the two end points by adopting an Euclidean distance in a coordinate system, and obtaining and outputting the straight line size of the ball stud.
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 the 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 in turn or alternately with other steps or at least a portion of the 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, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. 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.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A ball stud size detection method, characterized in that the method comprises:
acquiring a first image, wherein the first image at least comprises a complete ball stud image;
preprocessing the first image to obtain a second image, wherein the second image at least comprises a contour map of the ball stud;
carrying out edge detection on the contour map, and determining an edge line of the ball stud in the contour map;
carrying out straight line detection based on Hough transformation on the edge line, and determining a straight line part in the edge line;
and determining two end points of the straight line part by adopting a nearest neighbor searching algorithm, measuring the distance between the two end points by adopting an Euclidean distance in a coordinate system, and obtaining and outputting the straight line size of the ball stud.
2. The method of claim 1, wherein pre-processing the first image to obtain a second image comprises:
performing gradient sharpening on the first image; the gradient sharpening formula is:
wherein f (x, y) represents an image, G'M[f(x，y)]Is a final gray-scale-level-substitute value, G'M[f(x，y)]max＝225，T′1Representing a sharpening threshold value when the gradient value is greater than T'1While, the gradient edge is strengthened; t'2Representing a gray level threshold value when the gray level of the image is greater than T'2While, the gray value is decreased by T2；
And acquiring edge gray values of the ball stud image in the sharpened first image, and taking connected pixel points with gray value differences meeting edge judgment conditions as the outline of the ball stud to obtain a second image.
3. The method of claim 1, wherein the edge detecting the contour map and determining the edge line of the ball stud in the contour map comprises:
and performing edge detection on the contour diagram by using a Canny edge detection operator and/or a Sobel edge detection operator to determine the edge line of the ball stud.
4. The method according to claim 1, wherein the performing line detection based on Hough transform on the edge line to determine a straight line part in the edge line comprises:
projecting the edge line into a plane rectangular coordinate system, and acquiring the coordinates of sampling points on the edge line;
converting the sampling points to a polar coordinate system through polar coordinate operation; wherein the transformation equation is as follows:
wherein x and y represent horizontal and vertical coordinates of the sample point in the plane rectangular coordinate system, ρ represents the polar diameter of the sample point, and θ is the polar angle of the sample point;
and detecting the number of collinear points in the sampling points under the polar coordinates, and judging that a straight line is detected when the number of the collinear points is greater than a preset value.
5. The method of claim 4, wherein the detecting the number of collinear points in the sampling points under the polar coordinates, and when the number of collinear points is greater than a preset value, determining that a straight line is detected comprises:
according to a preset step length, the value of the adjustment theta is increased from 0 to 180, and the calculation is carried outDetermining the value range of rho, wherein
Determining the value of a Hough transformation accumulator corresponding to each group (rho, theta) according to the value of each group (rho, theta), taking the sample point corresponding to the (rho, theta) of the Hough transformation accumulator larger than a preset threshold value as the collinear point, and judging that a straight line is detected when the number of the collinear points is larger than a preset value.
6. The method of claim 1, wherein before determining two end points of the straight line portion by using a nearest neighbor searching algorithm and measuring a distance between the two end points by using a Euclidean distance in a coordinate system, and obtaining and outputting a straight line size of the ball stud, the method further comprises:
determination of the magnification of an optical system by static calibration of a workpiece of known dimension LWherein K is the pixel size of the camera, and N is the number of pixels occupied by the workpiece on the image；
By the formula
Calculating the adjusted magnification beta of the optical system1Wherein δ is vibration displacement, and μ is object distance of the optical system during static calibration;
using formulas
Calculating the size of the ball stud; wherein l is the size of the ball stud after error compensation, N1And the number of pixel points occupied by the ball pin on the second image is counted.
7. The method of claim 1, wherein preprocessing the first image to obtain a second image further comprises:
processing the first picture through a morphological processing method to remove noise in the first image; wherein the morphological processing method at least comprises image expansion and erosion.
8. A ball stud size detection device, characterized in that it comprises:
the device comprises an image acquisition device, a first image acquisition device and a second image acquisition device, wherein the first image acquisition device is used for acquiring a first image which at least comprises a complete ball stud image;
the image preprocessing device is used for preprocessing the first image to obtain a second image, and the second image at least comprises a contour map of the ball stud;
the edge detection device is used for carrying out edge detection on the contour map and determining an edge line of the ball stud in the contour map;
the straight line detection device is used for carrying out straight line detection based on Hough transformation on the edge line and determining a straight line part in the edge line; and
and the information output device is used for determining two end points of the straight line part by adopting a nearest neighbor search algorithm, measuring the distance between the two end points by adopting an Euclidean distance in a coordinate system, and obtaining and outputting the linear dimension of the ball stud.
9. A computer device comprising a memory and a processor, the memory having stored therein a computer program that, when executed by the processor, causes the processor to perform the steps of the ball stud size detection method of any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that a computer program is stored thereon, which, when being executed by a processor, causes the processor to carry out the steps of the ball stud dimension detecting method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910755038.2A CN110634128A (en) | 2019-08-15 | 2019-08-15 | Ball pin size detection method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910755038.2A CN110634128A (en) | 2019-08-15 | 2019-08-15 | Ball pin size detection method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110634128A true CN110634128A (en) | 2019-12-31 |
Family
ID=68970054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910755038.2A Pending CN110634128A (en) | 2019-08-15 | 2019-08-15 | Ball pin size detection method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110634128A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111951324A (en) * | 2020-07-30 | 2020-11-17 | 佛山科学技术学院 | Aluminum profile packaging length detection method and system |
| CN112897431A (en) * | 2020-10-24 | 2021-06-04 | 泰州无印广告传媒有限公司 | Compatible type self-adaptation filling system |
| CN113052837A (en) * | 2021-04-22 | 2021-06-29 | 杭州电力设备制造有限公司 | Handcart contact state identification method and device |
| CN114427965A (en) * | 2022-03-28 | 2022-05-03 | 迈赫机器人自动化股份有限公司 | Ball pin assembly design verification and durability test platform and use method thereof |
| CN115138527A (en) * | 2022-06-22 | 2022-10-04 | 深圳市双翌光电科技有限公司 | Rapid machining path generation method through visual guidance |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103292701A (en) * | 2013-06-24 | 2013-09-11 | 哈尔滨工业大学 | Machine-vision-based online dimensional measurement method of precise instrument |
| CN105258647A (en) * | 2015-07-26 | 2016-01-20 | 湖北工业大学 | Visual detection method of automobile lock catch rivet point |
| CN106643549A (en) * | 2017-02-07 | 2017-05-10 | 泉州装备制造研究所 | Machine vision-based tile size detection method |
| CN108662977A (en) * | 2018-03-14 | 2018-10-16 | 浙江大学山东工业技术研究院 | A kind of refractory brick geometric dimension measurement method |
-
2019
- 2019-08-15 CN CN201910755038.2A patent/CN110634128A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103292701A (en) * | 2013-06-24 | 2013-09-11 | 哈尔滨工业大学 | Machine-vision-based online dimensional measurement method of precise instrument |
| CN105258647A (en) * | 2015-07-26 | 2016-01-20 | 湖北工业大学 | Visual detection method of automobile lock catch rivet point |
| CN106643549A (en) * | 2017-02-07 | 2017-05-10 | 泉州装备制造研究所 | Machine vision-based tile size detection method |
| CN108662977A (en) * | 2018-03-14 | 2018-10-16 | 浙江大学山东工业技术研究院 | A kind of refractory brick geometric dimension measurement method |
Non-Patent Citations (1)
| Title |
|---|
| 诸晓锋: "基于机器视觉的工件表面质量高速在线检测技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111951324A (en) * | 2020-07-30 | 2020-11-17 | 佛山科学技术学院 | Aluminum profile packaging length detection method and system |
| CN111951324B (en) * | 2020-07-30 | 2024-03-29 | 佛山科学技术学院 | Method and system for detecting packaging length of aluminum profile |
| CN112897431A (en) * | 2020-10-24 | 2021-06-04 | 泰州无印广告传媒有限公司 | Compatible type self-adaptation filling system |
| CN113052837A (en) * | 2021-04-22 | 2021-06-29 | 杭州电力设备制造有限公司 | Handcart contact state identification method and device |
| CN114427965A (en) * | 2022-03-28 | 2022-05-03 | 迈赫机器人自动化股份有限公司 | Ball pin assembly design verification and durability test platform and use method thereof |
| CN115138527A (en) * | 2022-06-22 | 2022-10-04 | 深圳市双翌光电科技有限公司 | Rapid machining path generation method through visual guidance |
| CN115138527B (en) * | 2022-06-22 | 2023-12-26 | 深圳市双翌光电科技有限公司 | Rapid processing path generation method through visual guidance |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110634128A (en) | Ball pin size detection method and device, computer equipment and storage medium | |
| CN108921176B (en) | Pointer instrument positioning and identifying method based on machine vision | |
| US20230342925A1 (en) | System and method for calculating focus variation for a digital microscope | |
| US10823681B2 (en) | System and method for imaging a surface defect on an object | |
| CN108629775B (en) | Thermal state high-speed wire rod surface image processing method | |
| CN111179243A (en) | Small-size chip crack detection method and system based on computer vision | |
| CN110298840B (en) | Yarn defect detection method based on image | |
| CN115096206B (en) | High-precision part size measurement method based on machine vision | |
| CN114240845B (en) | Light cutting method surface roughness measurement method applied to cutting workpiece | |
| CN111415349B (en) | Polyester filament yarn detection method based on image processing technology | |
| US8315457B2 (en) | System and method for performing multi-image training for pattern recognition and registration | |
| CN113177924A (en) | Industrial production line product flaw detection method | |
| CN113034474A (en) | Test method for wafer map of OLED display | |
| CN114331995A (en) | Multi-template matching real-time positioning method based on improved 2D-ICP | |
| CN115272256A (en) | Sub-pixel level sensing optical fiber path Gaussian extraction method and system | |
| CN109387524A (en) | Thread defect detection method and device based on linearly polarized photon | |
| CN111354047B (en) | Computer vision-based camera module positioning method and system | |
| CN113705564B (en) | Pointer type instrument identification reading method | |
| CN114170165A (en) | Chip surface defect detection method and device | |
| CN114581805A (en) | Coating roller surface defect detection method adopting 3D line laser profile technology | |
| CN111539951B (en) | Visual detection method for outline size of ceramic grinding wheel head | |
| US11493453B2 (en) | Belt inspection system, belt inspection method, and recording medium for belt inspection program | |
| CN113538399A (en) | Method for obtaining accurate contour of workpiece, machine tool and storage medium | |
| CN116563298A (en) | Cross line center sub-pixel detection method based on Gaussian fitting | |
| CN116824294A (en) | Solder defect detection method and system based on small target identification |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191231 |