CN112802018A - Integrity detection method, device and equipment for segmented circular workpiece and storage medium - Google Patents
Integrity detection method, device and equipment for segmented circular workpiece and storage medium Download PDFInfo
- Publication number
- CN112802018A CN112802018A CN202110348186.XA CN202110348186A CN112802018A CN 112802018 A CN112802018 A CN 112802018A CN 202110348186 A CN202110348186 A CN 202110348186A CN 112802018 A CN112802018 A CN 112802018A
- Authority
- CN
- China
- Prior art keywords
- circle center
- circle
- target
- fitting
- center
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- 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
- G01B11/14—Measuring arrangements characterised by the use of optical techniques for measuring distance or clearance between spaced objects or spaced apertures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Length Measuring Devices With Unspecified Measuring Means (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method, a device, equipment and a storage medium for detecting the integrity of a segmented circular workpiece, which are used for acquiring sampling point data of an original image of the workpiece to be detected, performing initial fitting on the sampling point data, and calculating the initial average circle center of each fitting circle obtained by the initial fitting; removing the circle centers of the fitting circles according to the initial average circle center to obtain initial circle center data; clustering the initial circle center data, and determining target circle center information of the category data according to the number of continuous sampling points of the category data obtained by clustering; calculating the target average circle center of each target circle center in the target circle center information, and calculating the distance information from the circle center of the target category in the category data to the target average circle center; and determining whether the workpiece to be detected is complete according to the distance information. The invention accurately carries out integrity detection on the batch of segmented circular workpieces to be detected one by one so as to eliminate unqualified workpieces and improve the overall quality of the batch workpieces.
Description
Technical Field
The invention relates to the technical field of detection, in particular to a method, a device, equipment and a storage medium for detecting the integrity of a segmented circular workpiece.
Background
Many circular workpieces in the industry require different circular arcs to be machined in sections and then assembled into a segmented circular workpiece. In the assembling process, the final segmented circular workpiece is not a perfect circle due to the factors of whether the circular arc parts are assembled in place and the like. When the radius of the segmented circular workpiece is within the allowable tolerance range, the segmented circular workpiece is regarded as a qualified product, otherwise, the segmented circular workpiece is regarded as a defective product. How to detect the integrity of the circle has been a difficult problem in the industry.
At present, the integrity of a segmented circular workpiece is detected in the industry mainly by adopting a sampling manual detection mode, the diameter or the radius of the manually detected product is measured by a caliper, and then whether the product is qualified or not is judged by further determining whether the circle is complete or not. The method can only carry out sampling detection but not complete detection, so that a small amount of unqualified defective products are sent to subsequent stations, and the overall quality of batch products is low.
Disclosure of Invention
The invention mainly aims to provide a method, a device, equipment and a storage medium for detecting the integrity of a segmented circular workpiece, and aims to solve the technical problem that the integral quality of batch products is low due to the fact that the batch products can only be sampled and manually detected at present and are easy to miss detection.
In order to achieve the above object, an embodiment of the present invention provides an integrity detection method for a segmented circular workpiece, including:
acquiring sampling point data of an original image of a workpiece to be detected, performing initial fitting on the sampling point data, and calculating an initial average circle center of each fitting circle obtained by the initial fitting;
removing the circle centers of the fitting circles according to the initial average circle center to obtain initial circle center data;
clustering the initial circle center data, and determining target circle center information of the category data according to the number of continuous sampling points of the category data obtained by clustering;
calculating the target average circle center of each target circle center in the target circle center information, and calculating the distance information from the circle center of the target category in the category data to the target average circle center;
and determining whether the workpiece to be detected is complete according to the distance information.
Preferably, the step of performing circle center elimination on each fitting circle according to the initial average circle center to obtain initial circle center data includes:
respectively calculating the center distance between the center of each fitting circle and the initial average center;
sorting the plurality of center distances based on a preset sorting mode;
and eliminating the circle centers corresponding to the circle center distances within the preset sorting range after sorting to obtain initial circle center data.
Preferably, the step of determining the target circle center information of the category data according to the number of consecutive sampling points of the category data obtained by clustering includes:
aiming at each category in the category data obtained by clustering, respectively executing the following steps:
detecting the number of continuous sampling points with the largest value in the current category, and comparing the number of the continuous sampling points with a preset threshold value;
if the number of the continuous sampling points is larger than or equal to the preset threshold, fitting a target circle center according to the sampling points corresponding to the number of the continuous sampling points of the current category so as to form target circle center information after fitting the target circle centers of all categories;
and if the number of the continuous sampling points is smaller than the preset threshold value, fitting the target circle center according to all the sampling points in the current category so as to form target circle center information after fitting the target circle centers of all the categories.
Preferably, the step of calculating the distance information from the center of the target class to the average center of the target in the class data includes:
comparing the number of continuous sampling points with the maximum numerical values respectively corresponding to a plurality of categories in the category data;
determining the category with the largest number of continuous sampling points as a target category;
and calculating the distance information from the center of the target category to the average center of the target.
Preferably, the step of initially fitting the sample point data comprises:
for each sampling point in the sampling point data, respectively executing the following steps:
acquiring a preset number of adjacent points of a current sampling point;
initially fitting the current sampling point with a preset number of adjacent points to obtain a fitting circle;
and determining the circle center information of the fitting circle.
Preferably, the step of calculating an initial average center of each fitting circle obtained by initial fitting includes:
and calculating the initial average circle center of each fitting circle according to a preset calculation formula and the circle center information of each fitting circle.
Preferably, the step of determining whether the workpiece to be detected is complete according to the distance information includes:
calculating parameter deviation information according to the distance information;
comparing the parameter deviation information with a preset deviation range;
and if the parameter deviation information is within the preset deviation range, judging that the workpiece to be detected is complete.
In order to achieve the above object, the present invention further provides an integrity inspection apparatus for a segmented circular workpiece, comprising:
the fitting module is used for acquiring sampling point data of an original image of a workpiece to be detected, performing initial fitting on the sampling point data, and calculating an initial average circle center of each fitting circle obtained by the initial fitting;
the elimination module is used for eliminating the circle center of each fitting circle according to the initial average circle center to obtain initial circle center data;
the clustering module is used for clustering the initial circle center data and determining target circle center information of the category data according to the number of continuous sampling points of the category data obtained by clustering;
the calculation module is used for calculating the target average circle center of each target circle center in the target circle center information and calculating the distance information from the circle center of the target category in the category data to the target average circle center;
and the determining module is used for determining whether the workpiece to be detected is complete according to the distance information.
Further, in order to achieve the above object, the present invention further provides an integrity check apparatus for a segmented circular workpiece, including a memory, a processor, and an integrity check program for a segmented circular workpiece stored in the memory and executable on the processor, wherein the integrity check program for a segmented circular workpiece, when executed by the processor, implements the steps of the integrity check method for a segmented circular workpiece.
Further, in order to achieve the above object, the present invention further provides a storage medium, wherein the storage medium stores an integrity check program for a segmented circular workpiece, and the integrity check program for the segmented circular workpiece is executed by a processor to implement the steps of the integrity check method for the segmented circular workpiece.
The embodiment of the invention provides a method, a device, equipment and a storage medium for detecting the integrity of a segmented circular workpiece, which are used for acquiring sampling point data of an original image of the workpiece to be detected, performing initial fitting on the sampling point data, and calculating the initial average circle center of each fitting circle obtained by the initial fitting; removing the circle centers of the fitting circles according to the initial average circle center to obtain initial circle center data; clustering the initial circle center data, and determining target circle center information of the category data according to the number of continuous sampling points of the category data obtained by clustering; calculating the target average circle center of each target circle center in the target circle center information, and calculating the distance information from the circle center of the target category in the category data to the target average circle center; and determining whether the workpiece to be detected is complete according to the distance information. The method comprises the steps of firstly carrying out initial fitting on sampling point data of an original image of a workpiece to be detected to obtain an initial average circle center of each fitting circle, then removing part of circle centers in each fitting circle to remove interference of the circle center with low reliability, then clustering the removed initial circle center data to determine target circle center information, carrying out precise fitting on the initial circle center data, and finally accurately determining whether the workpiece to be detected is complete or not according to the distance information between the circle center of the clustered target class and the target average circle center of each target circle center in the target circle center information, and accurately carrying out integrity detection on a batch of segmented circular workpieces to be detected one by one to remove unqualified workpieces and improve the overall quality of the batch of workpieces.
Drawings
FIG. 1 is a schematic structural diagram of a hardware operating environment according to an embodiment of the method for integrity detection of a segmented circular workpiece according to the present invention;
FIG. 2 is a schematic flow chart illustrating a first embodiment of the method for integrity testing of a segmented circular workpiece according to the present invention;
FIG. 3 is a schematic flow chart illustrating a second embodiment of the method for integrity testing of a segmented circular workpiece according to the present invention;
FIG. 4 is a diagram illustrating the determination of the target circle center information of the category data according to the third embodiment;
FIG. 5 is a functional block diagram of an integrity inspection apparatus for a segmented circular workpiece according to a preferred embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the invention provides a method, a device, equipment and a storage medium for detecting the integrity of a segmented circular workpiece, which are used for acquiring sampling point data of an original image of the workpiece to be detected, performing initial fitting on the sampling point data, and calculating the initial average circle center of each fitting circle obtained by the initial fitting; removing the circle centers of the fitting circles according to the initial average circle center to obtain initial circle center data; clustering the initial circle center data, and determining target circle center information of the category data according to the number of continuous sampling points of the category data obtained by clustering; calculating the target average circle center of each target circle center in the target circle center information, and calculating the distance information from the circle center of the target category in the category data to the target average circle center; and determining whether the workpiece to be detected is complete according to the distance information. The method comprises the steps of firstly carrying out initial fitting on sampling point data of an original image of a workpiece to be detected to obtain an initial average circle center of each fitting circle, then removing part of circle centers in each fitting circle to remove interference of the circle center with low reliability, then clustering the removed initial circle center data to determine target circle center information, carrying out precise fitting on the initial circle center data, and finally accurately determining whether the workpiece to be detected is complete or not according to the distance information between the circle center of the clustered target class and the target average circle center of each target circle center in the target circle center information, and accurately carrying out integrity detection on a batch of segmented circular workpieces to be detected one by one to remove unqualified workpieces and improve the overall quality of the batch of workpieces.
As shown in fig. 1, fig. 1 is a schematic structural diagram of an integrity detection apparatus for a segmented circular workpiece in a hardware operating environment according to an embodiment of the present invention.
In the following description, suffixes such as "module", "component", or "unit" used to denote elements are used only for facilitating the explanation of the present invention, and have no specific meaning in itself. Thus, "module", "component" or "unit" may be used mixedly.
The integrity detection device of the segmented circular workpiece in the embodiment of the invention can be a PC, and can also be a mobile terminal device such as a tablet personal computer and a portable computer.
As shown in fig. 1, the integrity inspection apparatus for a segmented circular workpiece may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
It will be understood by those skilled in the art that the segmented circular workpiece integrity check device configuration shown in fig. 1 does not constitute a limitation of the segmented circular workpiece integrity check device and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, the memory 1005, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and an integrity check program for a segmented circular workpiece.
In the device shown in fig. 1, the network interface 1004 is mainly used for connecting to a backend server and performing data communication with the backend server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be configured to invoke an integrity check program for the segmented circular workpiece stored in the memory 1005 and perform the following operations:
acquiring sampling point data of an original image of a workpiece to be detected, performing initial fitting on the sampling point data, and calculating an initial average circle center of each fitting circle obtained by the initial fitting;
removing the circle centers of the fitting circles according to the initial average circle center to obtain initial circle center data;
clustering the initial circle center data, and determining target circle center information of the category data according to the number of continuous sampling points of the category data obtained by clustering;
calculating the target average circle center of each target circle center in the target circle center information, and calculating the distance information from the circle center of the target category in the category data to the target average circle center;
and determining whether the workpiece to be detected is complete according to the distance information.
Further, the step of performing circle center elimination on each fitting circle according to the initial average circle center to obtain initial circle center data includes:
respectively calculating the center distance between the center of each fitting circle and the initial average center;
sorting the plurality of center distances based on a preset sorting mode;
and eliminating the circle centers corresponding to the circle center distances within the preset sorting range after sorting to obtain initial circle center data.
Further, the step of determining the target circle center information of the category data according to the number of continuous sampling points of the category data obtained by clustering comprises:
aiming at each category in the category data obtained by clustering, respectively executing the following steps:
detecting the number of continuous sampling points with the largest value in the current category, and comparing the number of the continuous sampling points with a preset threshold value;
if the number of the continuous sampling points is larger than or equal to the preset threshold, fitting a target circle center according to the sampling points corresponding to the number of the continuous sampling points of the current category so as to form target circle center information after fitting the target circle centers of all categories;
and if the number of the continuous sampling points is smaller than the preset threshold value, fitting the target circle center according to all the sampling points in the current category so as to form target circle center information after fitting the target circle centers of all the categories.
Further, the step of calculating the distance information from the center of the target class in the class data to the average center of the target class comprises:
comparing the number of continuous sampling points with the maximum numerical values respectively corresponding to a plurality of categories in the category data;
determining the category with the largest number of continuous sampling points as a target category;
and calculating the distance information from the center of the target category to the average center of the target.
Further, the step of initially fitting the sample point data comprises:
for each sampling point in the sampling point data, respectively executing the following steps:
acquiring a preset number of adjacent points of a current sampling point;
initially fitting the current sampling point with a preset number of adjacent points to obtain a fitting circle;
and determining the circle center information of the fitting circle.
Further, the step of calculating the initial average center of each fitting circle obtained by the initial fitting includes:
and calculating the initial average circle center of each fitting circle according to a preset calculation formula and the circle center information of each fitting circle.
Further, the step of determining whether the workpiece to be detected is complete according to the distance information includes:
calculating parameter deviation information according to the distance information;
comparing the parameter deviation information with a preset deviation range;
and if the parameter deviation information is within the preset deviation range, judging that the workpiece to be detected is complete.
For a better understanding of the above technical solutions, exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
Referring to fig. 2, a first embodiment of the invention provides a flow chart of a method for detecting the integrity of a segmented circular workpiece. In this embodiment, the integrity detection method for the segmented circular workpiece includes the following steps:
step S10, acquiring sampling point data of an original image of a workpiece to be detected, performing initial fitting on the sampling point data, and calculating an initial average circle center of each fitting circle obtained by the initial fitting;
the integrity detection method for the segmented circular workpiece in the embodiment is applied to an integrity detection system for the segmented circular workpiece, and for convenience of description, the integrity detection system for the segmented circular workpiece is hereinafter referred to as a system for short. The system comprises a camera and a shifting mechanism, wherein the camera is used for collecting images of a workpiece to be detected, the shifting mechanism is used for moving the workpiece to be detected so that the camera can collect the images of the workpiece to be detected, namely, the workpiece to be detected is moved to a shooting center of the camera, understandably, in order to enable the images collected by the camera to have enough definition, the system can be further provided with a polishing device which is used for providing a light source for the camera to collect the images, the workpiece to be detected in the embodiment is preferably a segmented circular workpiece, and the polishing device is preferably arranged below the workpiece to be detected.
When the requirement for integrity detection of the workpiece to be detected is met, a user can place the workpiece to be detected on the shifting mechanism, the workpiece to be detected is transported to a shooting center of the camera through the shifting mechanism by the system, the shifting mechanism places the workpiece to be detected between the shooting centers, the camera is triggered to collect an original image of the workpiece to be detected by sending a PLC signal to the camera, the place where the workpiece to be detected is located is imaged in black, and the place where the workpiece is not located (light transmission) is imaged in white. After an original image of a workpiece to be detected is acquired, the system scans from the boundary position of the original image to the middle of the image to find an effective edge, and sampling point data consisting of discrete sampling points is obtained on the edge in an equally-spaced sampling point mode. Further, the system fits a corresponding fitting circle to each sampling point in the sampling point data, specifically, fits the sampling points and the preset number of adjacent points of the sampling points, fits a fitting circle from the plurality of points together, and calculates the center of the fitting circle, where the preset number is preferably 3 in this embodiment, but may also be set according to the actual situation, for example, 4, 6, or 8, that is, the number of points used by the fitting circle may also be 5, 7, or 9; the system repeatedly executes the fitting steps until all the sampling points in the sampling point data are fitted with corresponding fitting circles and the circle centers of the fitting circles corresponding to all the sampling points are calculated; and after the circle centers of the fitting circles corresponding to all the sampling points are calculated, calculating the average value of the circle center information of the fitting circles corresponding to all the sampling points to obtain the initial average circle center of each fitting circle.
Further, the step of initially fitting the sample point data comprises:
step S11, for each sampling point in the sampling point data, respectively executing the following steps:
step S12, acquiring a preset number of adjacent points of the current sampling point;
step S13, obtaining a fitting circle according to the initial fitting of the current sampling point and a preset number of adjacent points;
and step S14, determining the center information of the fitting circle.
Further, the system performs an initial fit for each sample point in the sample point data, assuming a total of n sample points:
acquiring two preset adjacent points of the current sampling point and requiring the ith point
From the (i-1) th point
And the (i + 1) th point
Adjacent, where i =0, 1, …, n-1. The real subscripts require a modulo operation, i.e. taking into account the boundary position points
. For the ith point, combining two adjacent points, a circle can be solved, and the circle center of the circle where the point i is located is made to be the circle center
And by analogy, until each sampling point is fitted to obtain a fitting circle and determine the circle center of each fitting circle, n sampling points obtain n circle centers, which is not repeated in this embodiment. When the circle center information of the fitting circle is determined, two equations are formed by a calculation formula of the distances between the two points according to the distances between the three points and the circle center respectively, an equation set is formed, and the equation set is solved to obtain the circle center information (including the horizontal coordinate and the vertical coordinate of the circle center).
Further, the step of calculating the initial average center of each fitting circle obtained by the initial fitting includes:
and step S15, calculating the initial average circle center of each fitting circle according to a preset calculation formula and the circle center information of each fitting circle.
After calculating the center information of each fitting circle, the system averages the center information of each fitting circle, specifically, calculates the abscissa average information and the ordinate average information of a plurality of centers of circles respectively according to the following preset calculation formula, and the initial average center of each fitting circle is composed of the abscissa average information and the ordinate average information:
wherein the content of the first and second substances,
is the abscissa of the initial mean circle center,
is the ordinate of the initial average center of a circle,
is the abscissa of the ith circle center,
is the ordinate of the ith circle center.
Step S20, removing the circle center of each fitting circle according to the initial average circle center to obtain initial circle center data;
further, in order to reduce the influence of the partial fitting circles with lower reliability in each fitting circle on the integrity detection accuracy of the segmented circular workpiece, the system needs to eliminate the centers of the partial fitting circles in each fitting circle, specifically, after an initial average center calculated from the center information of each fitting circle is obtained, the center distances between the centers of each fitting circle and the initial average center are calculated respectively, then the calculated center distances are sorted, and finally, the centers corresponding to the center distances arranged in a preset sorting range in the sorted center distances are eliminated, wherein the preset sorting range can be determined according to the number of arc segments forming the workpiece to be detected, understandably, the number of the eliminated centers of the circles can also be set manually. After the centers of the fitting circles in the fitting circles are removed, the remaining centers of the circles form initial circle center data, so that the integrity of the workpiece to be detected can be detected based on the initial circle center data in the following process, and the integrity detection accuracy of the segmented circular workpiece can be improved.
Step S30, clustering the initial circle center data, and determining target circle center information of the category data according to the number of continuous sampling points of the category data obtained by clustering;
it can be understood that for a segmented circular workpiece possibly consisting of a plurality of circular arc components, the circle center positions fitted by the sampling points usually located on the same circular arc component have little difference, and the sampling points on different circular arc components have more or less difference due to the assembly reason, so that the initial circle center data is clustered by adopting a general k-means algorithm to form class data, wherein the k-means generally refers to a k-means clustering algorithm, and the k-means clustering algorithm (k-means clustering algorithm) is a clustering analysis algorithm for iterative solution; the category data is composed of a plurality of categories, for example, for a workpiece to be detected composed of P arc parts, the initial circle center data composed of the remaining n-2P circle centers is clustered by adopting a general k-means algorithm, P categories are classified by copolymerization, and the P categories form category data. Further, the system respectively detects the number of continuous sampling points with the largest value in each category in the category data, compares the number of the maximum continuous sampling points respectively corresponding to a plurality of the maximum continuous sampling points with a preset threshold value to determine target circle center information of the category data, specifically determines a target circle center fitting mode of each category according to a comparison result, and forms the target circle center information after the target circle center fitting of each type is completed, wherein the preset threshold value is a numerical value set according to the number of the sampling points and the cluster category data.
Step S40, calculating a target average circle center of each target circle center in the target circle center information, and calculating distance information from a circle center of a target category in the category data to the target average circle center;
after target circle center information consisting of the circle centers of the targets of each category in the category data is determined according to the number of continuous sampling points of the category data obtained by clustering, the system carries out average operation on the circle centers of the targets to obtain the target average circle center of the circle centers of the targets. Specifically, the abscissa and the ordinate of the target average circle center are calculated by the following formulas:
wherein the content of the first and second substances,
is the abscissa of the average center of the target,
is the ordinate of the average center of a circle of the target,
is the circle of the P-th arc partThe information on the abscissa of the heart is,
the longitudinal coordinate information of the center of the circle of the P-th arc part.
Further, the system determines the category with the largest number of continuous sampling points in the category data as the target category, and then calculates the distance information between the center of the target category and the average center of the target, so as to determine whether the workpiece to be detected is complete according to the distance information, facilitate the complete integrity detection of the batch products, eliminate unqualified products and improve the overall quality of the batch products.
Further, the step of calculating the distance information from the center of the target class in the class data to the average center of the target class comprises:
step S41, comparing the number of continuous sampling points with the maximum numerical value respectively corresponding to a plurality of categories in the category data;
step S42, determining the category with the largest number of continuous sampling points as a target category;
and step S43, calculating the distance information from the center of the target category to the average center of the target.
Further, the system compares the number of consecutive sampling points with the maximum numerical value respectively corresponding to a plurality of categories in the category data, specifically, the maximum number of consecutive sampling points in each category can be compared with the maximum number of consecutive sampling points corresponding to the remaining categories, firstly, the number of the continuous sampling points with the maximum value in the first category is compared with the maximum number of the continuous sampling points corresponding to the rest categories, then the number of the continuous sampling points with the maximum value in the second category is compared with the maximum number of the continuous sampling points corresponding to the rest categories, by analogy, until the maximum continuous sampling point number of all categories is compared with the maximum continuous sampling point number corresponding to the other categories respectively, and determining the number of continuous sampling points with the largest numerical value from the number of the continuous sampling points in the plurality of categories, and determining the category with the largest number of the continuous sampling points as the target category. Further, the system calls a distance calculation formula between two points to calculate distance information from the center of the target category to the average center of the target, for example, if the category with the largest number of consecutive sampling points is the pth arc component, the distance information from the center of the pth arc component to the average center of the target is calculated, and the calculation process is as follows:
wherein the content of the first and second substances,
is the coordinate information of the average center of a circle of the target,
is the abscissa information of the center of the circle of the pth circular arc component,
the longitudinal coordinate information of the center of the circle of the P-th arc part.
And step S50, determining whether the workpiece to be detected is complete according to the distance information.
Further, after calculating the distance information from the center of the target category with the largest number of continuous sampling points to the average center of the target in the category data, the system calculates a series of parameter deviation information according to the calculated distance information, wherein the parameter deviation information may include maximum deviation, average deviation, variance and the like, so as to determine whether the workpiece to be detected is complete according to the parameter deviation information.
Specifically, the step of determining whether the workpiece to be detected is complete according to the distance information includes:
step S51, calculating parameter deviation information according to the distance information;
step S52, comparing the parameter deviation information with a preset deviation range;
and step S53, if the parameter deviation information is within the preset deviation range, judging that the workpiece to be detected is complete.
After calculating the distance information from the center of the target category to the average center of the target, the system calculates the parameter deviation information such as the maximum deviation, the average deviation, the variance and the like according to the relationship between the distance information and the parameters such as the maximum deviation, the average deviation, the variance and the like by combining the distance information, for example, the target category is the P-th arc part, and the distance information from the center of the P-th arc part to the average center of the target is calculated as
Then the maximum deviation is:
the average deviation is:
the variance is:
wherein P represents the number of arc parts constituting the segmented circular workpiece, and max represents the selected maximum value. After calculating parameter deviation information such as maximum deviation, average deviation, variance and the like, the system acquires a preset deviation range manually set for the parameters such as the maximum deviation, the average deviation, the variance and the like, namely the preset deviation range can comprise the maximum deviation range, the average deviation range, the variance range and the like, and then compares the parameter deviation information such as the maximum deviation, the average deviation, the variance and the like with the preset deviation ranges such as the maximum deviation range, the average deviation range, the variance range and the like respectively; if the maximum deviation, the average deviation and the variance are within the corresponding maximum deviation range, average deviation range and variance range through comparison, and the parameter deviation information is within the deviation range allowed by the user, the workpiece to be detected is complete, namely the workpiece to be detected is qualified.
The embodiment of the invention provides a method, a device, equipment and a storage medium for detecting the integrity of a segmented circular workpiece, which are used for acquiring sampling point data of an original image of the workpiece to be detected, performing initial fitting on the sampling point data, and calculating the initial average circle center of each fitting circle obtained by the initial fitting; removing the circle centers of the fitting circles according to the initial average circle center to obtain initial circle center data; clustering the initial circle center data, and determining target circle center information of the category data according to the number of continuous sampling points of the category data obtained by clustering; calculating the target average circle center of each target circle center in the target circle center information, and calculating the distance information from the circle center of the target category in the category data to the target average circle center; and determining whether the workpiece to be detected is complete according to the distance information. The method comprises the steps of firstly carrying out initial fitting on sampling point data of an original image of a workpiece to be detected to obtain an initial average circle center of each fitting circle, then removing part of circle centers in each fitting circle to remove interference of the circle center with low reliability, then clustering the removed initial circle center data to determine target circle center information, carrying out precise fitting on the initial circle center data, and finally accurately determining whether the workpiece to be detected is complete or not according to the distance information between the circle center of the clustered target class and the target average circle center of each target circle center in the target circle center information, and accurately carrying out integrity detection on a batch of segmented circular workpieces to be detected one by one to remove unqualified workpieces and improve the overall quality of the batch of workpieces.
Further, referring to fig. 3, a second embodiment of the method for detecting integrity of a segmented circular workpiece according to the present invention is provided based on the first embodiment of the method for detecting integrity of a segmented circular workpiece according to the present invention, and in the second embodiment, the step of performing circle center elimination on each fitted circle according to the initial average circle center to obtain initial circle center data includes:
step S21, respectively calculating the center distance between the center of each fitting circle and the initial average center of the circle;
step S22, sorting the center distances based on a preset sorting mode;
and step S23, removing the circle centers corresponding to the circle center distances within the preset sorting range after sorting to obtain initial circle center data.
As can be understood, for a segmented circular workpiece assembled by a plurality of arc parts, the confidence of fitting circles of a plurality of continuous sampling points on the same arc part is high; in contrast, the circle fitted by the continuous sampling points at the junction of the two arc components has low reliability and needs to be eliminated. In practice, it is difficult to determine whether the continuous points are at the intersection points, so we can eliminate a certain proportion of the circle centers. Specifically, the system calculates the distance between the center of each fitting circle of the fitting circles and the initial average center of the fitting circle through a distance calculation formula between two points to obtain a plurality of center distances, wherein the distance calculation formula is as follows:
wherein the content of the first and second substances,
represents the distance between the ith circle center and the initial average circle center,
the abscissa representing the i-th circle center,
the ordinate representing the i-th circle center,
the abscissa representing the initial mean center of the circle,
denotes the ordinate of the initial mean circle center, i =0, 1, 2.
After calculating the distance between the center of each fitting circle and the initial average center of the circle to obtain a plurality of center distances, the system sorts the plurality of center distances according to a preset sorting mode, in this embodiment, a sorting mode from large to small is preferably adopted to sort the plurality of center distances, that is, the plurality of center distances are sorted from large to small. After finishing sorting, eliminating the circle centers corresponding to the circle center distances within a preset sorting range, wherein the preset sorting range is a value which is two times of the number of arc parts forming the segmented circular workpiece arranged in front, if the segmented circular workpiece consists of P equal arc parts (1 < P < 6), the arc parts have P joint points in total, and if 3 adjacent points are used for solving the circle centers, the 2P circle centers in total are possibly unstable. Therefore, if the workpiece to be detected is assembled by P arc workpieces, the circle centers corresponding to the circle center distances in the front 2P range after sequencing are removed, wherein the number of the removed circle centers can also be set manually; and simultaneously, eliminating the sampling points corresponding to the circle centers to obtain initial circle center data consisting of the residual circle centers.
It will be appreciated that if two circular arc components are assembled perfectly, fitting circles at the boundary points of adjacent circular arcs will be very good. At this point, the drain disturb may remove some valid sampling points. However, this has no effect on the final result, since the number of boundary points 2P is much smaller than the total number of sample points n. When the assembly is perfect, an effective fitting circle can be fitted even if a small number of effective sampling points are eliminated.
In the embodiment, the centers of partial fitting circles in each fitting circle are removed, and the centers of circles with lower reliability obtained by fitting the continuous sampling points at the joint position of the two arc parts are removed, so that the residual centers of circles in the initial circle center data are all the centers of circles of effective circles, the finally calculated target average center of circle is further more accurate, and the accuracy of the result of determining whether the workpiece to be detected is complete or not based on the target average center of circle is improved.
Further, based on the first embodiment of the method for detecting integrity of a segmented circular workpiece according to the present invention, a third embodiment of the method for detecting integrity of a segmented circular workpiece according to the present invention is provided, in which the step of determining the target circle center information of the category data according to the number of consecutive sampling points of the category data obtained by clustering includes:
step S31, for each category in the clustered category data, executing the following steps:
step S32, detecting the number of continuous sampling points with the largest value in the current category, and comparing the number of the continuous sampling points with a preset threshold value;
step S33, if the number of the continuous sampling points is larger than or equal to the preset threshold, fitting a target circle center according to the sampling points corresponding to the number of the continuous sampling points of the current category to form target circle center information after fitting the target circle centers of all categories;
step S34, if the number of the consecutive sampling points is smaller than the preset threshold, fitting the target circle center according to all the sampling points in the current category to form target circle center information after fitting the target circle centers of all the categories.
Usually, the circle center positions of the fitted sampling points on the same arc component have small difference, and the sampling points on different arc components have more or less difference due to the assembly reason, so that for P arc components, the general k-means algorithm is adopted to cluster the rest n-2P circle centers and copolymerize P types. As shown in fig. 4, fig. 4 is a schematic diagram illustrating the determination of the center information of the object in the category data, and the centers of the three different gray levels are three cluster centers. After clustering is completed, class data composed of a plurality of classes is obtained, and since the sampling points of different classes in the clustered class data are likely to be clustered into other classes, the sampling points in the classes are not all continuous, i.e. the sampling points can be divided into two or even more parts of continuous sampling points. Therefore, the system detects the number of continuous sampling points existing in the current category for each category in the category data obtained by clustering, compares the largest number of the continuous sampling points in the continuous sampling points with a preset threshold, and assumes that the largest number of the continuous sampling points in the multi-part continuous sampling points of the P-th category (P =0, 1.. P-1) is the largest number of the continuous sampling points
Then the number of consecutive sampling points will be
And a predetermined threshold value
Make a comparisonIf the comparison result is
That is, the number of the continuous sampling points is greater than or equal to the preset threshold value, which indicates that most fitting circles of the sampling points of the arc component are consistent, and then the center of the target circle is fitted according to the sampling point corresponding to the number of the continuous sampling points with the largest value in the current category
And forming target circle center information after fitting the target circle centers of all the categories. If the comparison result is
If the discrimination degree of the circle centers of the sampling point fitting circles of the plurality of arc parts is small and the arc workpieces are well assembled, the circle centers of the arc parts are re-fitted by directly using all the sampling points in the category
And forming target circle center information after fitting the target circle centers of all the categories. And the system repeatedly executes the steps, determines the center of a target circle for each category in the category data obtained by clustering until the center of the target circle is fitted in all categories, and forms target circle center information by a plurality of target circle centers.
In the embodiment, the residual initial circle center information after the circle center is removed is clustered, and the target circle center is formed by re-fitting the clustered category data, so that the target circle center information has higher validity, the distance information calculated according to the target circle center information in the follow-up process is more accurate, and the accuracy of the result of determining whether the workpiece to be detected is complete based on the distance information is improved.
Furthermore, the invention also provides an integrity detection device for the segmented circular workpiece.
Referring to fig. 5, fig. 5 is a functional block diagram of the integrity testing apparatus for segmented circular workpieces according to the first embodiment of the present invention.
The integrity detection device for the segmented circular workpiece comprises:
the fitting module 10 is configured to obtain sampling point data of an original image of a workpiece to be detected, perform initial fitting on the sampling point data, and calculate an initial average circle center of each fitting circle obtained by the initial fitting;
the eliminating module 20 is configured to perform circle center elimination on each fitting circle according to the initial average circle center to obtain initial circle center data;
the clustering module 30 is configured to cluster the initial circle center data, and determine target circle center information of the category data according to the number of continuous sampling points of the category data obtained by clustering;
a calculating module 40, configured to calculate a target average circle center of each target circle center in the target circle center information, and calculate distance information between a circle center of a target category in the category data and the target average circle center;
and the determining module 50 is used for determining whether the workpiece to be detected is complete according to the distance information.
Further, the fitting module 10 includes:
a first executing unit, configured to execute steps S12-S14 for each sample point in the sample point data;
the acquisition unit is used for acquiring the preset number of adjacent points of the current sampling point;
the first fitting unit is used for initially fitting the current sampling point with a preset number of adjacent points to obtain a fitting circle;
and the first determining unit is used for determining the center information of the fitting circle.
Further, the fitting module 10 further includes:
and the first calculating unit is used for calculating the initial average circle center of each fitting circle according to a preset calculation formula and the circle center information of each fitting circle.
Further, the culling module 20 includes:
the second calculation unit is used for calculating the center distance between the center of each fitting circle and the initial average center of the circle;
the sorting unit is used for sorting the plurality of center distances based on a preset sorting mode;
and the eliminating unit is used for eliminating the circle centers corresponding to the circle center distances within the preset sorting range after sorting to obtain initial circle center data.
Further, the clustering module 30 includes:
a second executing unit, configured to execute steps S32-S34 for each category in the clustered category data;
the device comprises a first comparison unit, a second comparison unit and a third comparison unit, wherein the first comparison unit is used for detecting the number of continuous sampling points with the largest value in the current category and comparing the number of the continuous sampling points with a preset threshold value;
the second fitting unit is used for fitting a target circle center according to the sampling points corresponding to the number of the continuous sampling points of the current category if the number of the continuous sampling points is greater than or equal to the preset threshold value, so as to form target circle center information after fitting the target circle centers of all categories;
and the third fitting unit is used for fitting the target circle center according to all the sampling points in the current category if the number of the continuous sampling points is smaller than the preset threshold value, so as to form target circle center information after the target circle centers of all the categories are fitted.
Further, the calculation module 40 includes:
the second comparison unit is used for comparing the number of the continuous sampling points with the maximum numerical values respectively corresponding to the multiple categories in the category data;
the second determining unit is used for determining the category with the largest number of continuous sampling points as a target category;
and the third calculating unit is used for calculating the distance information from the center of the target category to the average center of the target.
Further, the determining module 50 includes:
a fourth calculation unit for calculating parameter deviation information from the distance information;
the comparison unit is used for comparing the parameter deviation information with a preset deviation range;
and the judging unit is used for judging that the workpiece to be detected is complete if the parameter deviation information is within the preset deviation range.
Furthermore, the present invention also provides a storage medium, preferably a computer-readable storage medium, on which an integrity check program of a segmented circular workpiece is stored, which when executed by a processor implements the steps of the embodiments of the integrity check method of a segmented circular workpiece described above.
In the embodiments of the integrity inspection apparatus and the computer-readable medium for a segmented circular workpiece according to the present invention, all technical features of the embodiments of the integrity inspection method for a segmented circular workpiece are included, and the description and explanation contents are substantially the same as those of the embodiments of the integrity inspection method for a segmented circular workpiece, and are not repeated herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention or a part contributing to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk), and includes a plurality of instructions for enabling a terminal device (which may be a fixed terminal, such as an internet of things smart device including smart homes, such as a smart air conditioner, a smart lamp, a smart power supply, a smart router, etc., or a mobile terminal, including a smart phone, a wearable networked AR/VR device, a smart sound box, an autonomous driving automobile, etc.) to execute the method according to each embodiment of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. The integrity detection method of the segmented circular workpiece is characterized by comprising the following steps:
acquiring sampling point data of an original image of a workpiece to be detected, performing initial fitting on the sampling point data, and calculating an initial average circle center of each fitting circle obtained by the initial fitting;
removing the circle centers of the fitting circles according to the initial average circle center to obtain initial circle center data;
clustering the initial circle center data, and determining target circle center information of the category data according to the number of continuous sampling points of the category data obtained by clustering;
calculating the target average circle center of each target circle center in the target circle center information, and calculating the distance information from the circle center of the target category in the category data to the target average circle center;
and determining whether the workpiece to be detected is complete according to the distance information.
2. The method of claim 1, wherein the step of performing circle center culling on each of the fitted circles according to the initial mean circle center to obtain initial circle center data comprises:
respectively calculating the center distance between the center of each fitting circle and the initial average center;
sorting the plurality of center distances based on a preset sorting mode;
and eliminating the circle centers corresponding to the circle center distances within the preset sorting range after sorting to obtain initial circle center data.
3. The method for detecting the integrity of a segmented circular workpiece as claimed in claim 1, wherein the step of determining the target circle center information of the class data according to the number of consecutive sampling points of the class data obtained by clustering comprises:
aiming at each category in the category data obtained by clustering, respectively executing the following steps:
detecting the number of continuous sampling points with the largest value in the current category, and comparing the number of the continuous sampling points with a preset threshold value;
if the number of the continuous sampling points is larger than or equal to the preset threshold, fitting a target circle center according to the sampling points corresponding to the number of the continuous sampling points of the current category so as to form target circle center information after fitting the target circle centers of all categories;
and if the number of the continuous sampling points is smaller than the preset threshold value, fitting the target circle center according to all the sampling points in the current category so as to form target circle center information after fitting the target circle centers of all the categories.
4. The method of claim 1, wherein the step of calculating distance information from the center of the target category to the average center of the target category in the category data comprises:
comparing the number of continuous sampling points with the maximum numerical values respectively corresponding to a plurality of categories in the category data;
determining the category with the largest number of continuous sampling points as a target category;
and calculating the distance information from the center of the target category to the average center of the target.
5. The method of claim 1, wherein said step of initially fitting said sample point data comprises:
for each sampling point in the sampling point data, respectively executing the following steps:
acquiring a preset number of adjacent points of a current sampling point;
initially fitting the current sampling point with a preset number of adjacent points to obtain a fitting circle;
and determining the circle center information of the fitting circle.
6. The method of claim 5, wherein the step of calculating an initial mean center of each circle fit from the initial fit comprises:
and calculating the initial average circle center of each fitting circle according to a preset calculation formula and the circle center information of each fitting circle.
7. The method for inspecting the integrity of a segmented circular workpiece as defined in claim 1, wherein said step of determining whether said workpiece to be inspected is intact based on said distance information comprises:
calculating parameter deviation information according to the distance information;
comparing the parameter deviation information with a preset deviation range;
and if the parameter deviation information is within the preset deviation range, judging that the workpiece to be detected is complete.
8. An integrity inspection device for a segmented circular workpiece, the integrity inspection device comprising:
the fitting module is used for acquiring sampling point data of an original image of a workpiece to be detected, performing initial fitting on the sampling point data, and calculating an initial average circle center of each fitting circle obtained by the initial fitting;
the elimination module is used for eliminating the circle center of each fitting circle according to the initial average circle center to obtain initial circle center data;
the clustering module is used for clustering the initial circle center data and determining target circle center information of the category data according to the number of continuous sampling points of the category data obtained by clustering;
the calculation module is used for calculating the target average circle center of each target circle center in the target circle center information and calculating the distance information from the circle center of the target category in the category data to the target average circle center;
and the determining module is used for determining whether the workpiece to be detected is complete according to the distance information.
9. An integrity check apparatus for a segmented circular workpiece, comprising a memory, a processor, and an integrity check program for a segmented circular workpiece stored on the memory and executable on the processor, wherein the integrity check program for a segmented circular workpiece, when executed by the processor, implements the steps of the method of any one of claims 1-7.
10. A storage medium having stored thereon an integrity check program for a segmented circular workpiece, the integrity check program when executed by a processor implementing the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110348186.XA CN112802018B (en) | 2021-03-31 | 2021-03-31 | Integrity detection method, device and equipment for segmented circular workpiece and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110348186.XA CN112802018B (en) | 2021-03-31 | 2021-03-31 | Integrity detection method, device and equipment for segmented circular workpiece and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112802018A true CN112802018A (en) | 2021-05-14 |
| CN112802018B CN112802018B (en) | 2021-08-06 |
Family
ID=75816101
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110348186.XA Active CN112802018B (en) | 2021-03-31 | 2021-03-31 | Integrity detection method, device and equipment for segmented circular workpiece and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112802018B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115106666A (en) * | 2022-06-28 | 2022-09-27 | 广东利元亨智能装备股份有限公司 | Method, device, system, equipment and medium for positioning welding track of battery cell |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886597A (en) * | 2014-03-24 | 2014-06-25 | 武汉力成伟业科技有限公司 | Circle detection method based on edge detection and fitted curve clustering |
| CN105279756A (en) * | 2015-10-19 | 2016-01-27 | 天津理工大学 | Notch circular arc part dimension visual detection method based on self-adapting region division |
| CN105574516A (en) * | 2016-01-20 | 2016-05-11 | 浙江大学城市学院 | Ornamental pineapple chlorophyll detection method based on logistic regression in visible image |
| CN109357653A (en) * | 2018-11-14 | 2019-02-19 | 中国航发动力股份有限公司 | A kind of imperfect outer arc radius measuring device and measuring method of revolving body workpieces |
| CN110470242A (en) * | 2019-08-23 | 2019-11-19 | 贵阳新天光电科技有限公司 | A kind of heavy parts inner hole circularity on-position measure device and method |
| CN111243008A (en) * | 2020-01-19 | 2020-06-05 | 广西师范大学 | Arc data fitting method for high-precision workpiece |
| CN111429396A (en) * | 2019-01-09 | 2020-07-17 | 银河水滴科技（北京）有限公司 | Image detection method and device |
| WO2020197109A1 (en) * | 2019-03-28 | 2020-10-01 | 주식회사 디오 | Dental image registration device and method |
| US20200364899A1 (en) * | 2017-08-25 | 2020-11-19 | Chiris Hsinlai Liu | Stereo machine vision system and method for identifying locations of natural target elements |
-
2021
- 2021-03-31 CN CN202110348186.XA patent/CN112802018B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886597A (en) * | 2014-03-24 | 2014-06-25 | 武汉力成伟业科技有限公司 | Circle detection method based on edge detection and fitted curve clustering |
| CN105279756A (en) * | 2015-10-19 | 2016-01-27 | 天津理工大学 | Notch circular arc part dimension visual detection method based on self-adapting region division |
| CN105574516A (en) * | 2016-01-20 | 2016-05-11 | 浙江大学城市学院 | Ornamental pineapple chlorophyll detection method based on logistic regression in visible image |
| US20200364899A1 (en) * | 2017-08-25 | 2020-11-19 | Chiris Hsinlai Liu | Stereo machine vision system and method for identifying locations of natural target elements |
| CN109357653A (en) * | 2018-11-14 | 2019-02-19 | 中国航发动力股份有限公司 | A kind of imperfect outer arc radius measuring device and measuring method of revolving body workpieces |
| CN111429396A (en) * | 2019-01-09 | 2020-07-17 | 银河水滴科技（北京）有限公司 | Image detection method and device |
| WO2020197109A1 (en) * | 2019-03-28 | 2020-10-01 | 주식회사 디오 | Dental image registration device and method |
| CN110470242A (en) * | 2019-08-23 | 2019-11-19 | 贵阳新天光电科技有限公司 | A kind of heavy parts inner hole circularity on-position measure device and method |
| CN111243008A (en) * | 2020-01-19 | 2020-06-05 | 广西师范大学 | Arc data fitting method for high-precision workpiece |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115106666A (en) * | 2022-06-28 | 2022-09-27 | 广东利元亨智能装备股份有限公司 | Method, device, system, equipment and medium for positioning welding track of battery cell |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112802018B (en) | 2021-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110148130B (en) | Method and device for detecting part defects | |
| WO2021000524A1 (en) | Hole protection cap detection method and apparatus, computer device and storage medium | |
| CN111970506B (en) | Lens dirt detection method, device and equipment | |
| CN112115895B (en) | Pointer type instrument reading identification method, pointer type instrument reading identification device, computer equipment and storage medium | |
| KR102058427B1 (en) | Apparatus and method for inspection | |
| CN109726746B (en) | Template matching method and device | |
| CN115018850B (en) | Method for detecting burrs of punched hole of precise electronic part based on image processing | |
| CN111929314A (en) | Wheel hub weld visual detection method and detection system | |
| CN110378227B (en) | Method, device and equipment for correcting sample labeling data and storage medium | |
| CN109492688B (en) | Weld joint tracking method and device and computer readable storage medium | |
| CN112767366A (en) | Image recognition method, device and equipment based on deep learning and storage medium | |
| CN111242899B (en) | Image-based flaw detection method and computer-readable storage medium | |
| CN110766095A (en) | Defect detection method based on image gray level features | |
| CN115841488B (en) | PCB hole inspection method based on computer vision | |
| CN111325738A (en) | Intelligent detection method and system for peripheral cracks of transverse hole | |
| CN112802018B (en) | Integrity detection method, device and equipment for segmented circular workpiece and storage medium | |
| CN111223078A (en) | Method for determining defect grade and storage medium | |
| CN112070762A (en) | Mura defect detection method and device for liquid crystal panel, storage medium and terminal | |
| CN115018835A (en) | Automobile starter gear detection method | |
| CN113554645B (en) | Industrial anomaly detection method and device based on WGAN | |
| CN106682604B (en) | Blurred image detection method based on deep learning | |
| CN114226262A (en) | Flaw detection method, flaw classification method and flaw detection system | |
| US10241000B2 (en) | Method for checking the position of characteristic points in light distributions | |
| CN113516328B (en) | Data processing method, service providing method, device, equipment and storage medium | |
| CN112950598B (en) | Flaw detection method, device, equipment and storage medium for workpiece |
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 |