CN115791838A - Defect detection device and method for cylindrical tubular structure object - Google Patents
Defect detection device and method for cylindrical tubular structure object Download PDFInfo
- Publication number
- CN115791838A CN115791838A CN202211492169.4A CN202211492169A CN115791838A CN 115791838 A CN115791838 A CN 115791838A CN 202211492169 A CN202211492169 A CN 202211492169A CN 115791838 A CN115791838 A CN 115791838A
- Authority
- CN
- China
- Prior art keywords
- light source
- image
- module
- optical system
- detecting
- 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
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention aims to provide a defect detection device and a defect detection method for an object with a cylindrical tubular structure, which can be suitable for detecting objects with smaller diameters, collect high-precision pictures and have strong adjustment and anti-interference capabilities. Including image acquisition module, light source module and main control module, image acquisition module and light source module respectively with main control module electric connection, image acquisition module includes optical system and opens and stops the mechanism, detects the object and can trigger to open and stop the mechanism control optical system and shoot detecting the object through the in-process of test channel, and light source module can calculate the light intensity of carrying out the light filling to detecting the object, makes and detects the object and forms luminance difference with the look background, and main control module is used for cutting apart, proofreading and joint and calculating the size information of defect on the image to the region that detects the object on the image.
Description
Technical Field
The invention relates to the technical field of defect detection, in particular to a defect detection device and a defect detection method for a cylindrical tubular structure object.
Background
Defect detection is an item which is often required to be detected in the production process of a plurality of cylindrical tubular structure objects, such as optical fibers, wires, steel pipes and other objects, and is used for detecting whether fine defects such as burrs, pits and the like exist on the surface of the cylindrical tubular object, for example, a patent with the publication number of CN111402248A discloses a transmission line wire defect detection method based on machine vision, and the method comprises the following steps: acquiring images on the power transmission line through an unmanned aerial vehicle, and transmitting the images to a remote server end through a network; constructing a MASK-RCNN network to train the grids to obtain a prediction model; obtaining a binary skeleton map and an average width of the lead by adopting a skeleton algorithm; using a homomorphic filtering algorithm to eliminate the influence of uneven illumination and extracting a wire area image; constructing and training a shallow classification network to obtain a classification prediction model; and inputting the lead region picture into a classification prediction model to obtain the lead segment state. A patent with publication number CN111340787A discloses a method, a device and computer equipment for detecting and identifying the defects of a wire of a power transmission line, wherein the method comprises the following steps: processing the conductor defect image in the power transmission line inspection historical defect database by adopting methods such as image enhancement, rendering and the like to obtain an image sample library; training a defect image sample library by using a RetinaNet deep neural network to obtain a defect identification neural network model; acquiring an image to be detected on a power transmission line, inputting the image to be detected into the defect recognition neural network model for detection, and recognizing the conductor defect in the image to be detected.
The detection equipment mainly aims at large targets, is difficult to image when used for detecting wires with small diameters, cannot shoot defects such as burrs and pits on the surface of a detected object, and is low in accuracy.
Disclosure of Invention
Therefore, the invention aims to provide a defect detection device and a defect detection method for an object with a cylindrical tubular structure, which can be suitable for detecting objects with small diameters, collect high-precision pictures and have strong adjustment and anti-interference capabilities.
In order to achieve the purpose, the invention provides the following technical scheme:
the utility model provides a defect detection device of cylinder tubular structure object, includes image acquisition module, light source module and main control module, image acquisition module and light source module respectively with main control module electric connection, image acquisition module includes optical system and opens and stops the mechanism, detects the object and can trigger to open and stop mechanism control optical system and shoot detecting the object at the in-process through the test channel, and light source module can calculate the light intensity that carries out the light filling to detecting the object, makes and detects the object and forms luminance difference with the look background, and main control module is used for cutting apart, proofreading and correct, the concatenation calculates the size information of defect on the image to the region of detecting the object on the image.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, the high-precision photo of the detected object is acquired through the cooperation of the image acquisition module, the light source module and the main control module, so that the high-accuracy defect detection is carried out on the detected object, and the method specifically comprises the following steps: carry out the light filling through light source module to detecting the object, make burr or pit that detect the object surface more outstanding to effectively overcome ambient light and disturb the stability of guaranteeing the image, also make simultaneously detect the object and form luminance difference with the look background, make it can more clear formation of image.
As an improvement, the optical system is an industrial camera.
As an improvement, the number of the industrial cameras is three, and the industrial cameras are arranged at intervals along the circumferential direction of the detection channel respectively, so that all surfaces of the object can be completely detected by shooting the object to be detected for one circle from three angles respectively.
As an improvement, the image acquisition module further comprises a longitudinal mechanism capable of driving the optical system to slide along the radial direction of the detection channel and a surrounding mechanism capable of driving the optical system to move around along the detection channel.
As the improvement, vertical mechanism includes slide rail and slider, is provided with the first bayonet socket that a plurality of can fix the slider position on the slide rail, encircles the mechanism and includes solid fixed ring, gu fixed ring goes up the installation seat that the slip was provided with optical system, and be provided with the second bayonet socket that a plurality of can fix the installation seat position on solid fixed ring, when in-service use: set up 100 according to precision 0.001mm altogether between the first bayonet socket, the shooting distance of the position accurate control light source system through control slider and slide rail can not be because of removal, collision etc. produce the error like this, can realize shooting the conversion of distance when different diameter objects simultaneously, and gu set up 360 second bayonet sockets altogether according to 1 on the fixed ring, can guarantee like this not to shoot the dead angle to shooting the object.
As the improvement, start the stop mechanism and include the runner and install the encoder on the runner, detect the object and can drive the runner rotation when passing through the detection passageway to trigger the encoder and send signal to main control module, main control module sends the signal of shooing to optical system after receiving the encoder signal, and like this, the encoder sends a signal, and optical system shoots a line of image, splices out the image of complete a set for the height with this.
As an improvement, the light source module comprises a photosensitive sensor and a plurality of light source control cards which are distributed on the outer side of the optical system in an annular mode, light source control chips are arranged inside the light source control cards and can adjust light steplessly, therefore, ambient light information of a detected object is obtained through the photosensitive sensor and transmitted to the main control module, the light intensity most suitable for light supplement of the detected object is calculated by the main control module, light supplement is carried out on the light source control chips, an LED light source is arranged in the light source control chips, and the light intensity most suitable for light supplement of the detected object can be preset.
As an improvement, the light source module further comprises a light source gray level sensor connected with the light source control chip, so that the light source gray level sensor can sense the gray level of a shooting area and accurately control the 256 gray levels of the multi-path light source control chip, the proportion of different light wavelength can be realized, light spots with smaller sizes are formed, and sensor pixels with different sizes can be better utilized.
The image display module and the alarm module are respectively connected with the main control module, an image of a detection object on the optical system and an image of the detection object spliced by the main control module can be displayed on the image display module, and when the size of the defect on the image calculated by the main control module is larger than a set size, the alarm module prompts through the alarm module and prompts an operator.
In order to achieve the purpose, the invention provides the following technical scheme:
the detection method of the defect detection device for the cylindrical tubular structure object comprises
The method comprises the following steps: conveying the detection object into the detection channel;
step two: the light source module acquires ambient light information and supplements light to a detected object;
step three: an optical system collects a detection object image;
step four: the main control module detects the detected object image;
step five: the main control module calculates the size of the defect on the detected object image;
step six: and if the size of the detected image is larger than the set value, displaying an alarm.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, the light source module can acquire the ambient light information, and the light supplement light intensity which is most suitable for the detected object is calculated according to the ambient light information, so that the detected object and the same-color background form a brightness difference, further burrs on the detected object are more prominent, the shooting effect is more obvious, and the accuracy of defect detection is improved.
Drawings
Fig. 1 is a flowchart of a method for inspecting a defect inspection apparatus for an object having a cylindrical tubular structure according to the present invention.
Fig. 2 is a structural view of a light source module in the defect detecting apparatus for the cylindrical tubular structure object according to the present invention.
Fig. 3 is an imaging structure in the present invention.
FIG. 4 is a schematic diagram of an industrial camera and a light source according to the present invention.
Detailed Description
The invention is explained in further detail below:
with specific reference to fig. 1-4:
the utility model provides a defect detection device of cylinder tubular structure object, includes image acquisition module, light source module and main control module, image acquisition module and light source module respectively with main control module electric connection, image acquisition module includes optical system and opens and stops the mechanism, detects the object and can trigger to open and stop mechanism control optical system and shoot detecting the object at the in-process through detecting channel, and light source module can calculate the light intensity that carries out the light filling to detecting the object, makes detecting the object and form the luminance difference with the look background, and main control module is used for cutting apart, correcting, the concatenation and calculates the size information of defect on the image to detecting the region of object on the image. According to the invention, the high-precision photo of the detected object is acquired through the cooperation of the image acquisition module, the light source module and the main control module, so that the high-accuracy defect detection is carried out on the detected object, and the method specifically comprises the following steps: carry out the light filling through light source module to detecting the object, make burr or pit that detect the object surface more outstanding to effectively overcome ambient light and disturb the stability of guaranteeing the image, also make simultaneously detect the object and form luminance difference with the look background, make it can more clear formation of image.
In this embodiment, the segmentation of the detection object on the image: the method comprises the steps that an industrial camera shoots a detected object image under the cooperation of an auxiliary light source, the area of the detected object image has obvious brightness difference with a background, the detected object image is binarized by utilizing an opencv image processing library, the coordinate of the central point of the brightness area is calculated, and finally the area where the detected object image is located is segmented.
In this embodiment, the correction of the detection object on the image: the main control module reads the tooth number and tooth pitch information of the gear of the longitudinal mechanism, the aperture information of the camera and the wavelength information on the light source control chip while acquiring an image of a detected object, calculates the distance between the camera lens and the detected object at the moment, corrects a picture by establishing an image pixel coordinate system, a camera coordinate system and an actual coordinate system, and calculates the size information of each defect on the shot image of the detected object, wherein the imaging structure of the application is shown in fig. 3. Due to the structural characteristics of the light source module and the image acquisition module, the industrial camera can be influenced by the three light sources when shooting a single detection object image, as shown in fig. 4, when single image correction is carried out, the light paths of the three light source control chips are combined into one path by using the optical filter to be used as the optical axis in fig. 3 for calculation.
In fig. 3, the center of projection is the optical center point of the camera lens, and the intersection point of the optical axis and the image plane is called principal point O0. Establishing an image pixel coordinate system: and (3) expressing the shot guide wire image by M x N pixels, establishing an O0-uv image pixel coordinate system, and expressing point coordinates by adopting pixel units. As shown in fig. 3, O0-xy is the image physical coordinate system, and the image point coordinate is expressed in physical units (usually mm), O0 is the intersection point of the optical axis of the camera and the image plane, and the x-axis and the y-axis are parallel to the u-axis and the v-axis, respectively. Theoretically, O0 should be located at the center of the image, but in practical situations, there is a certain deviation due to the lens distortion of the camera and the mounting error of the imaging chip. Assuming that the pixel coordinate of O0 is (u 0, v 0), the image physical coordinate of the image point q is (x, y), and assuming that the pixel of the camera chip after digital discretization is a rectangle, and the length and width thereof respectively represent dx and dy, the relationship between the pixel coordinate of the image point q and the image coordinate is:
establishing a camera coordinate system: and the Oc-XcYcZc in the projection center relation graph is a camera coordinate system, wherein Oc is the optical center of the camera, namely the projection center, the Xc axis and the Yc axis are respectively parallel to the x axis and the y axis of the image physical coordinate system, and the Zc axis is coincident with the optical axis of the camera and is vertical to the image plane. The OcO0 is the distance from the optical center Oc to the image plane, i.e., the focal length f0. Assuming that the camera coordinate system of the Q point on the space is (Xc, yc, zc), the relation expression projected from the center is:
establishing an actual coordinate system: the actual coordinate system is mainly used for describing a coordinate system of the position relation between the camera and a certain object in a three-dimensional scene, and can be selected randomly according to the scene, and in the application, ow-XwYwZw in fig. 3 is set as the actual coordinate system. Given the world coordinate system of the Q point on the space as (Xw, yw, zw), there are
Where R is a 3 × 3 rotation matrix and T is a translation vector, which are used to represent the positional transformation relationship between the world coordinate system and the camera coordinate system. The above expression is taken together to obtain the conversion relationship between the world coordinate system of the spatial point Q to the pixel coordinate system of its image point Q:
therefore, the size information of the defect on the image can be calculated by correcting a single picture according to the tooth number and the tooth pitch information of the gear teeth on the longitudinal mechanism and the camera aperture.
After a single correction image is obtained, the images of the same group need to be spliced, so that a complete guide wire image is obtained. The method for splicing the images of the detected object by using the image characteristic points comprises the following steps: firstly, SIFT feature points are extracted from a single picture processed in the same group and stored, the extracted SIFT feature points are purified to obtain feature interior points among three pictures, and the matching relation among the pictures is calculated; constructing a feature vector according to the feature interior points; calculating a transformation matrix among the three images according to the matching relation and the purified characteristic interior points, and further obtaining an iterative optimization initial value of a rotation parameter and a translation parameter of each image; and (3) calculating a final transformation matrix according to the feature vector and feature point matching relation iterative optimization rotation parameters and translation parameters, obtaining the relative positions of the three images through the transformation matrix, and carrying out image fusion by using opencv to obtain a final guide wire image.
The defect detection algorithm used in the present application is a fast R-CNN network to which an Adaptive Class Suppression Loss (ACSL) module is added. Firstly, a defect detection network based on fast R-CNN is constructed according to the characteristics that the environment of the surface of a guide wire is complex and defects such as burrs, bright spots and the like are difficult to detect, then an ACSL module is introduced into a basic network according to the characteristic that the number of various defect samples of an object image is unbalanced in the actual production environment, and the influence of the imbalance of the samples on the detection precision is solved by adjusting the weight coefficient of the classification loss of different classification positions and maintaining the relative balance of the positive activation loss and the negative activation loss of the different classification positions. The improved model provided by the application continuously balances the attention of the head category (category with high occurrence frequency, such as surface pits, and the like), the middle category (category with medium occurrence frequency, such as silking, and the like) and the tail category (category with low occurrence frequency, such as surface yellowing, and the like) in the training process, and improves the accuracy of the algorithm.
In this embodiment, the optical system is an industrial camera.
In this embodiment, the quantity of industry camera is three, and sets up along the circumference interval of detecting channel respectively, like this, can follow respectively that three angle shoots and detect object a week, the complete all surfaces that detect the object.
In this embodiment, the image capturing module further includes a longitudinal mechanism capable of driving the optical system to slide along the radial direction of the detection channel and a surrounding mechanism capable of driving the optical system to move along the detection channel in a surrounding manner.
In this embodiment, vertical mechanism includes slide rail and slider, is provided with the first bayonet socket that a plurality of can fix the slider position on the slide rail, encircles the mechanism and includes solid fixed ring, gu fixed ring goes up to slide and is provided with optical system's mount pad, and be provided with the second bayonet socket that a plurality of can fix the mount pad position on solid fixed ring, when in-service use: set up 100 according to the precision 0.001mm altogether between the first bayonet socket, the shooting distance through the position accurate control light source system of control slider and slide rail can not be because of producing the error such as removal, collision like this, can realize shooting the conversion of distance when different diameter objects simultaneously, and gu set up 360 second bayonet sockets according to 1 altogether on the fixed ring, can guarantee like this not to shoot the dead angle to shooting the object.
In this embodiment, start and stop the mechanism and include the runner and install the encoder on the runner, detect the object and can drive the runner rotation when passing through the detection passageway to trigger the encoder and send signal to main control module, main control module sends the signal of shooing to optical system after receiving the encoder signal, and like this, the encoder sends a signal, and optical system shoots a line of image, splices out the image of complete a set for the height with this.
In this embodiment, the light source module includes photosensitive sensor and a plurality of annular distribution sets up the light source control card in the optical system outside, the inside light source control chip that all is provided with of light source control card, light source control chip can stepless adjusting luminance, thus, acquire the ambient light information of detection object and transmit for main control module through photosensitive sensor, calculate the light intensity that is most suitable for the detection object light filling by main control module, carry out the light filling at control light source control chip, be equipped with the LED light source in the light source control chip, the light intensity that is most suitable for the detection object light filling also can be realized predetermineeing.
In this embodiment, the light source module still includes the light source grey level inductor of being connected with light source control chip, and like this, light source grey level inductor can respond to the grey level of shooting region and through the accurate control of 256 grades of grey levels of multichannel light source control chip, can realize the ratio of different light wavelength, forms the less facula of size, the sensor pixel of utilizing not equidimension that can be better.
In the embodiment, the system further comprises upper computer software which comprises a real-time image display module and an alarm module, in this way, the image display module and the alarm module are respectively connected with the main control module, images of the detection object on the optical system and the detection object image spliced and processed by the main control module can be displayed on the image display module, and when the size of the defect on the image calculated by the main control module is larger than the set size, the alarm module prompts the user through the alarm module and prompts the operator.
In order to achieve the purpose, the invention provides the following technical scheme:
the detection method of the defect detection device for the cylindrical tubular structure object comprises
The method comprises the following steps: conveying the detection object into the detection channel;
step two: the light source module acquires ambient light information and supplements light to a detected object;
step three: an optical system collects a detection object image;
step four: the main control module detects the detected object image;
step five: the main control module calculates the size of the defect on the detected object image;
step six: and if the size of the detected image is larger than the set value, displaying an alarm. In the invention, the light source module can acquire the ambient light information and calculate the light supplementing light intensity which is most suitable for the detected object aiming at the ambient light information, so that the detected object and the same-color background form a brightness difference, further burrs on the detected object are more prominent, the shooting effect is more obvious, and the accuracy of defect detection is improved,
before the fourth step, because of the cylindrical tubular structure, the brightness of the detection object needs to be homogenized, and the brightness homogenizing method used in the present application comprises the following steps: firstly, obtaining a shot single detected object image, determining a first area and a second area according to the image, and determining the sum of the first area and the second area as a third area; respectively calculating first gray value uniformity, second gray value uniformity and third gray value uniformity of the first region, the second region and the third region; and judging the uniformity of the light source according to the first gray value uniformity, the second gray value uniformity and the third gray value uniformity.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. The utility model provides a defect detection device of cylinder tubular structure object, a serial communication port, including image acquisition module, light source module and main control module, image acquisition module and light source module respectively with main control module electric connection, image acquisition module includes optical system and opens and stops the mechanism, detects the object and can trigger to open and stop mechanism control optical system and shoot detecting the object at the in-process through detecting channel, and light source module can calculate the light intensity that carries out the light filling to detecting the object, makes and detects the object and forms luminance difference with the look background, and main control module is used for cutting apart, proofreaies and correct and splices and calculate the size information of defect on the image to detecting the region of object on the image.
2. The apparatus for inspecting defects of cylindrical tubular structured objects as claimed in claim 1, wherein said optical system is an industrial camera.
3. The apparatus for detecting defects of an object having a cylindrical tubular structure according to claim 2, wherein the number of the industrial cameras is three, and the industrial cameras are respectively arranged at intervals along the circumferential direction of the detection passage.
4. The apparatus according to claim 1, wherein the image capturing module further comprises a longitudinal mechanism for driving the optical system to slide along the radial direction of the detecting channel and a surrounding mechanism for driving the optical system to move around along the detecting channel.
5. The apparatus according to claim 4, wherein the longitudinal mechanism comprises a slide rail and a slide block, the slide rail is provided with a plurality of first bayonets capable of fixing the position of the slide block, the circumferential mechanism comprises a fixing ring, the fixing ring is slidably provided with a mounting seat of the optical system, and the fixing ring is provided with a plurality of second bayonets capable of fixing the position of the mounting seat.
6. The apparatus of claim 1, wherein the start/stop mechanism comprises a rotating wheel and an encoder mounted on the rotating wheel, the detection object can drive the rotating wheel to rotate when passing through the detection channel, and trigger the encoder to send a signal to the main control module, and the main control module sends a photographing signal to the optical system after receiving the encoder signal.
7. The device for detecting the defects of the cylindrical tubular structure object according to claim 1, wherein the light source module comprises a photosensitive sensor and a plurality of light source control cards which are annularly distributed on the outer side of the optical system, light source control chips are arranged inside the light source control cards, and the light source control chips can adjust light steplessly.
8. The apparatus for detecting the defects of the cylindrical tubular structure object according to claim 7, wherein the light source module further comprises a light source gray scale sensor connected to the light source control chip.
9. The apparatus for detecting defects of an object having a cylindrical tubular structure according to claim 1, further comprising a real-time image display module and an alarm module.
10. A detection method of a defect detection device of a cylindrical tubular structure object is characterized by comprising the following steps: conveying the detection object into the detection channel;
step two: the light source module acquires ambient light information and supplements light for a detected object;
step three: an optical system collects a detection object image;
step four: the main control module detects the detected object image;
step five: the main control module calculates the size of the defect on the detected object image;
step six: and if the size of the detected image is larger than the set value, displaying an alarm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211492169.4A CN115791838A (en) | 2022-11-25 | 2022-11-25 | Defect detection device and method for cylindrical tubular structure object |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211492169.4A CN115791838A (en) | 2022-11-25 | 2022-11-25 | Defect detection device and method for cylindrical tubular structure object |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115791838A true CN115791838A (en) | 2023-03-14 |
Family
ID=85441633
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211492169.4A Pending CN115791838A (en) | 2022-11-25 | 2022-11-25 | Defect detection device and method for cylindrical tubular structure object |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115791838A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117761080A (en) * | 2023-12-27 | 2024-03-26 | 常熟中佳新材料有限公司 | Copper pipe surface defect detection system during copper pipe processing |
-
2022
- 2022-11-25 CN CN202211492169.4A patent/CN115791838A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117761080A (en) * | 2023-12-27 | 2024-03-26 | 常熟中佳新材料有限公司 | Copper pipe surface defect detection system during copper pipe processing |
| CN117761080B (en) * | 2023-12-27 | 2024-07-05 | 常熟中佳新材料有限公司 | Copper pipe surface defect detection system during copper pipe processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108765416B (en) | PCB surface defect detection method and device based on rapid geometric alignment | |
| CN109544679B (en) | Three-dimensional reconstruction method for inner wall of pipeline | |
| CN105511123B (en) | A kind of High Precision Automatic Systems for optical inspection and method based on mechanical arm | |
| CN109859272B (en) | Automatic focusing binocular camera calibration method and device | |
| CN108918542B (en) | Optical cable surface defect detection device and method | |
| CN107869954B (en) | Binocular vision volume weight measurement system and implementation method thereof | |
| CN114280075B (en) | Online visual detection system and detection method for surface defects of pipe parts | |
| CN113884497B (en) | FPCA (focal plane array) fly shooting detection method based on composite light source | |
| CN107014291B (en) | A kind of vision positioning method of material precision transfer platform | |
| CN108596173B (en) | Single-camera full-view line number real-time recognition device and detection method thereof | |
| CN116433780B (en) | Automatic calibration method for laser structured light based on machine vision | |
| CN114383505A (en) | Automatic detection device for dimension of short shaft type part | |
| CN115791838A (en) | Defect detection device and method for cylindrical tubular structure object | |
| CN115546170B (en) | Fan blade defect positioning method and system based on laser ranging | |
| CN109596058A (en) | The size detection recognition methods of plastic workpiece | |
| CN114820439A (en) | PCB bare board defect detection system and method based on AOI | |
| CN116625258A (en) | Chain spacing measuring system and chain spacing measuring method | |
| CN115014248A (en) | Laser projection line identification and flatness judgment method | |
| CN114820475A (en) | Edge identification method and system, wafer processing device and method for determining concentric state of wafer and processing table | |
| CN114113116A (en) | Accurate detection process method for micro-defects on surface of large-diameter element | |
| US6798515B1 (en) | Method for calculating a scale relationship for an imaging system | |
| CN112785647A (en) | Three-eye stereo image detection method and system | |
| CN113256576A (en) | Automatic optical element detection system and method based on polarization imaging and machine learning | |
| CN113516709B (en) | Flange positioning method based on binocular vision | |
| CN209803848U (en) | Integrated road tunnel variable-focus visual detection system |
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 |