An automatic measurement system for ingot size based on machine vision

Abstract

The present application is applicable to the field of metallurgical intelligent technology, and provides a system for automatically measuring the size of a billet based on machine vision, the system comprising: an automatic acquisition module, which acquires a billet image when it is detected that the billet reaches a preset measurement area; an intelligent measurement module, which processes the billet image according to a preset deep learning algorithm, obtains the pixel coordinates of the edge of the billet surface, obtains the pixel coordinates of the corner points of the billet surface by fitting the pixel coordinates of the edge of the billet surface to the billet edge line, and obtains the billet surface size according to the distance value of the pixel coordinates of the corner points of the billet surface. The embodiment of the present application can automatically and intelligently measure the billet size, and the measurement result has high reliability.

Description

Technical Field

[0001] The present application belongs to the field of intelligent metallurgical technology, and specifically relates to an automatic ingot size measurement system based on machine vision. Background Art

[0002] In steel enterprises, the ingots produced by the steelmaking plant are transported to the rolling line via rollers. The rolling process requires that the length, width and thickness of the ingots meet the specified dimensional deviation range. Therefore, accurate measurement is required before the ingots are sent to the rolling line.

[0003] At present, there are two main ways to measure the size of the ingot, namely: the first is manual measurement. Obviously, this method has low detection efficiency, high labor costs, poor working environment, and great safety hazards; the second is automatic measurement using a laser rangefinder. Although this method can avoid the disadvantages of manual measurement to a certain extent, it still has defects such as poor measurement accuracy, inconvenient installation, and poor adaptability to the posture of the ingot on the roller. Summary of the invention

[0004] The embodiment of the present application provides a system for automatically measuring the size of a casting ingot based on machine vision to solve the above-mentioned technical problems in the prior art.

[0005] An automatic billet size measurement system based on machine vision according to an embodiment of the present application includes: An automatic acquisition module acquires an image of the billet when it is detected that the billet reaches a preset measurement area; The intelligent measurement module processes the ingot image according to a preset deep learning algorithm to obtain the pixel coordinates of the edge of the ingot surface, and obtains the pixel coordinates of the corner points of the ingot surface by fitting the pixel coordinates of the edge of the ingot surface into the edge of the ingot. The surface size of the ingot is obtained according to the distance value of the pixel coordinates of the corner points of the ingot surface.

[0006] Furthermore, the automatic acquisition module includes a position detection sensor, a controller, an auxiliary light source and an industrial camera; When the position detection sensor detects that the casting billet conveyed by the roller reaches the preset measurement area, a first signal is sent to the controller; The controller controls the motor of the roller to stop running according to the first signal, and generates a second signal and a third signal according to the first signal, and there is a preset time interval between the second signal and the third signal, wherein the second signal is used to start the auxiliary light source, and the third signal is used to start the industrial camera; The industrial camera is used to capture images of the ingot and transmit the images of the ingot to the intelligent measurement module.

[0007] Furthermore, the intelligent measurement module includes a billet edge recognition module and a billet size calculation module; The ingot edge recognition module is trained according to a preset deep learning algorithm to obtain a deep learning model, extracts the ingot surface edge feature pixels in the ingot image based on the deep learning model, and obtains the ingot surface edge pixel coordinates according to the ingot surface edge feature pixels; The ingot size calculation module uses a linear regression algorithm to fit the pixel coordinates of the edge of the ingot surface to obtain the ingot surface edge line, obtains the pixel coordinates of the corner points on the ingot surface based on the ingot surface edge line, converts the pixel coordinates of the corner points on the ingot surface into world coordinates, calculates the distance between the coordinates through the world coordinates of the corner points, and obtains the ingot surface size.

[0008] Furthermore, the intelligent measurement module also includes a casting billet number recognition module and an association module; The billet number recognition module uses an image reconstruction algorithm to recognize the billet image to obtain the billet number; The association module is used to associate and store information of the billet number and the billet surface size.

[0009] Furthermore, the ingot number recognition module includes a positioning detection module, a data reconstruction module and a recognition module; The positioning detection module extracts the feature information of the ingot number through a convolutional neural network, and generates a position boundary box of the ingot number according to the feature information of the ingot number; The data reconstruction module is used to increase the channel dimension of the image within the position boundary box of the casting billet number through sub-pixel convolution calculation, and use the additional channels as pixel data to increase the resolution of the image to obtain a high-resolution feature map, and up-sample the high-resolution feature map to obtain a reconstructed casting billet number image; The recognition module is used to recognize the reconstructed ingot number image through a preset deep learning model to obtain the ingot number.

[0010] Furthermore, it also includes an interaction module; The interactive module is used to display the relevant data sent by the intelligent measurement module.

[0011] Furthermore, the interaction module also receives and displays manual measurement data according to instructions of the manual operation module.

[0012] Further, the interaction module includes a display module, wherein the display module includes an image display module; The image display module includes a captured image display module and a measurement diagram display module, wherein the captured image display module is used to display the current ingot image; The measurement image display module is used to display the measurement image, wherein the measurement image is a measurement line superimposed on the current ingot image, wherein the line is fitted by the pixel coordinates of the ingot surface edge obtained by the ingot edge recognition module, and the line color is different from the color of the current ingot image.

[0013] Further, the interaction module includes a display module, wherein the display module includes a data display module; The data display module is used to display relevant data of the intelligent measurement module and the manual operation module.

[0014] Furthermore, it also includes a storage module; The storage module is used to store relevant data sent to the intelligent measurement module and / or the manual operation module.

[0015] As can be seen from the above, the embodiment of the present application adopts the method of machine vision and deep learning intelligent analysis. By automatically taking pictures of the ingot online, the ingot image of the measured ingot is obtained, and the ingot image is processed by a preset deep learning algorithm. It can realize real-time and high-precision automatic measurement of the ingot size, which can effectively improve the measurement accuracy and efficiency, and at the same time reduce the number of inspection personnel, reduce inspection costs, and improve the safety of inspection operations, which plays an important role in improving the product quality, process continuity and operation safety of the rolling production line. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 It is a schematic diagram of the structure of an automatic measurement system for ingot size based on machine vision provided in an embodiment of the present application; Figure 2 yes Figure 1 A schematic diagram of one of the interfaces of the display module in . DETAILED DESCRIPTION

[0018] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0019] It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0020] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0021] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0022] In order to illustrate the technical solution described in this application, a specific embodiment is provided below for illustration.

[0023] See also Figure 1 , Figure 1 is a schematic diagram of the structure of a system for automatically measuring the size of a casting blank based on machine vision provided in an embodiment of the present application, such as Figure 1 As shown, a system for automatically measuring the size of a casting billet based on machine vision, the system comprises: The automatic acquisition module acquires the image of the casting billet when it is detected that the casting billet 1 reaches the preset measurement area; The intelligent measurement module processes the ingot image according to a preset deep learning algorithm to obtain the pixel coordinates of the edge of the ingot surface, and obtains the pixel coordinates of the corner points of the ingot surface by fitting the pixel coordinates of the edge of the ingot surface into the edge of the ingot. The surface size of the ingot is obtained according to the distance value of the pixel coordinates of the corner points of the ingot surface.

[0024] As can be seen from the above, the embodiment of the present application adopts the method of machine vision and deep learning intelligent analysis. By automatically taking pictures of the ingot online, the ingot image of the measured ingot is obtained, and the ingot image is processed by a preset deep learning algorithm. It can realize real-time and high-precision automatic measurement of the ingot size, which can effectively improve the measurement accuracy and efficiency, and at the same time reduce the number of inspection personnel, reduce inspection costs, and improve the safety of inspection operations, which plays an important role in improving the product quality, process continuity and operation safety of the rolling production line.

[0025] In some embodiments, the automatic acquisition module includes a position detection sensor, a controller 2, an auxiliary light source 3 and an industrial camera 4, wherein the position detection sensor can be a laser position sensor 5, but is not limited thereto, and can be specifically configured as required; When the position detection sensor detects that the cast billet transported by the roller table 6 reaches the measuring area, a first signal is sent to the controller 2; The controller 2 controls the motor of the roller table 6 to stop running according to the first signal so that the casting billet stays in the measuring area, and generates a second signal and a third signal according to the first signal. There is a preset time interval between the second signal and the third signal, wherein the second signal is used to start the auxiliary light source 3, and the third signal is used to start the industrial camera 4; The industrial camera 4 is used to capture images of the ingot and transmit the images to the intelligent measurement module through the gateway 7; When the industrial camera 4 captures the image of the ingot, a fourth signal is sent to the controller 2. The controller 2 turns off the auxiliary light source 3 and / or the industrial camera 4 according to the fourth signal to reduce loss.

[0026] To facilitate a clear understanding of the above solution, a more detailed embodiment is provided below for explanation: The controller 2 , the industrial camera 4 , the computer 8 and the like construct an industrial Ethernet system through a network cable and a gateway 7 .

[0027] The controller 2 is connected to the laser position sensor 5, the conveyor roller 6 motor, and the control switch of the auxiliary light source 3 through the power signal cable. After the ingot is transported to the measurement area by the conveyor roller 6, the laser position sensor 5 is triggered and generates a high level to be sent to the controller 2. The controller 2 detects the signal sent by the laser position sensor 5 and immediately controls the conveyor roller 6 motor to stop, the roller stops rotating, and the ingot stops at the predetermined position; the controller 2 further sends a signal to control the auxiliary light source 3 switch to turn on, and the auxiliary light source 3 lights up; after the auxiliary light source 3 is turned on, it delays a certain time interval, and the controller 2 sends a rectangular pulse signal to the industrial camera 4. When the industrial camera 4 captures the rising edge of the signal, it automatically starts taking pictures, and the auxiliary light source 3 is turned off after taking pictures.

[0028] As can be seen from the above, the embodiment of the present application uses the ingot position detection as the initial trigger signal, and then through a series of logical controls such as the roller 6 control, the industrial camera 4 and the auxiliary light source 3, it can realize automatic ingot image capture, that is, realize unmanned operation.

[0029] In some embodiments, the intelligent measurement module includes a slab edge recognition module and a slab size calculation module; The ingot edge recognition module is trained according to a preset deep learning algorithm to obtain a deep learning model, extracts the edge feature pixels of the ingot surface in the ingot image based on the deep learning model, and obtains the pixel coordinates of the edge of the ingot surface according to the edge feature pixels of the ingot surface; Among them, the deep learning model can be obtained by using a large number of ingot photos taken by industrial cameras 4, manually marking the ingot surface area, and training with a deep learning algorithm; The ingot size calculation module uses a linear regression algorithm to fit the pixel coordinates of the edge of the ingot surface to obtain the edge line of the ingot surface. According to the edge line of the ingot surface, the pixel coordinates of the corner points on the ingot surface are obtained, and the pixel coordinates of the corner points on the ingot surface are converted into world coordinates. The distance between the coordinates is calculated through the world coordinates of the corner points and the average value is obtained to obtain the ingot surface size.

[0030] For ease of understanding, the length and width of the billet are used as an example: The linear regression algorithm is used to fit the four edge lines of the billet surface to the pixel coordinates of the edge of the billet, and the pixel coordinates of the four corner points are obtained. The pixel coordinates are converted into world coordinates, and the distance between the coordinates is calculated through the world coordinates of the corner points and the average value is obtained, which is the length and width of the billet.

[0031] It should be noted that the thickness of the ingot can be set to different thickness dimensions according to preset standards or specifications for selection. For example, in the embodiment of the present application, the preset ingot thickness is 400mm, 245mm, and 350mm, but it is not limited to this and can be set according to specific needs.

[0032] In some embodiments, the intelligent measurement module further includes a casting billet number identification module and an association module; The billet number recognition module uses an image reconstruction algorithm to recognize the billet image and obtain the billet number; The association module is used to associate and store information of the billet number and the billet surface size.

[0033] Among them, the ingot number is an identification code corresponding one to one to the current ingot. The identification code can be a character code, DM code and / or QR code, etc., which is not limited here and can be set as needed. The identification code can be marked on the side of the ingot or other surface that is convenient for information collection through identification equipment (for example, a laser machine, an inkjet printer, etc.), which is not limited here.

[0034] Obviously, recognizing the ingot image through the image reconstruction algorithm can avoid the influence of low-quality ingot images such as blurry, incomplete, and serious geometric distortion on the ingot number recognition, thereby improving the reliability of ingot number recognition.

[0035] At the same time, by setting an identification code for each ingot and storing the identification code in association with the surface size of the ingot, it can be ensured that the size of each ingot is traceable and meets the rolling requirements.

[0036] Specifically, the billet number recognition module includes a positioning detection module, a data reconstruction module and a recognition module; A positioning detection module extracts the feature information of the billet number through a convolutional neural network, generates a position bounding box of the billet number according to the feature information of the billet number, and realizes the positioning detection of the billet number, wherein the convolutional neural network may include a column convolution layer, a fully connected layer, and an activation function, etc.; A data reconstruction module is used to increase the channel dimension of the image within the position boundary box of the ingot number through sub-pixel convolution calculation, and use the additional channels as pixel data to increase the resolution of the image to obtain a high-resolution feature map, and upsample the high-resolution feature map to obtain a reconstructed ingot number image; The recognition module is used to recognize the reconstructed ingot number image through a preset deep learning model to obtain the ingot number.

[0037] The data reconstruction module is specifically used to: generate a high-resolution feature map by sub-pixel convolution calculation of the image within the position boundary box of the ingot number, wherein in the sub-pixel convolution calculation, the channel dimension is increased by the convolution operation, and the additional channels are used as pixel data to increase the resolution of the image; increase the width and height of the high-resolution feature map by γ times, wherein γ is the scale factor, and obtain γ 2 channel feature map; the high-resolution feature map after upsampling is obtained by the periodic screening method to realize the reconstruction of the billet number data; Obviously, by sequentially positioning and detecting the ingot numbers and reconstructing the low-quality ingot number data, the efficiency and accuracy of ingot number recognition can be effectively improved.

[0038] In some embodiments, the automatic measurement system for ingot size based on machine vision may further include an interaction module; The interactive module is used to display the relevant data sent by the intelligent measurement module, wherein the relevant data includes the billet number, billet size and billet image, etc., which are not limited here; Specifically, the interaction module can also receive and display manual measurement data according to the instructions of the manual operation module.

[0039] Due to special circumstances such as irregular billet shape, there is a practical need to manually measure the billet. Therefore, a manual operation mode can be set. Under the manual operation mode instruction, manual measurement data is received and displayed to provide convenience for the operator.

[0040] Specifically, Figure 2 As shown, the interaction module includes a display module, wherein the display module includes an image display module and a data display module; The image display module includes a captured image display module and a measurement diagram display module, wherein the captured image display module is used to display the current ingot image; The measurement image display module is used to display the measurement image, wherein the measurement image is a measurement line superimposed on the current ingot image, wherein the line is fitted by the pixel coordinates of the ingot surface edge obtained by the ingot edge recognition module, and the line color is different from the color of the current ingot image; The data display module is used to display relevant data of the intelligent measurement module and the manual operation module, for example, data information such as the billet number, billet length, billet width and billet thickness.

[0041] Obviously, through the above settings, the operator can not only monitor whether the photos taken by the industrial camera 4 place the ingot within the field of view, but also observe the process and effect of the intelligent measurement.

[0042] In some embodiments, the automatic measurement system for ingot size based on machine vision may further include a storage module; The storage module is used to store relevant data sent by the intelligent measurement module and / or the manual operation module.

[0043] In addition, it should be noted that the intelligent measurement module, the interactive module, the storage module, etc. can be installed as applications on a terminal, and the terminal includes but is not limited to other portable devices such as mobile phones, laptop computers or tablet computers with touch-sensitive surfaces (e.g., touch screen displays and / or touch pads).

[0044] For ease of understanding, the working process of the automatic measurement system for ingot size based on machine vision provided in the embodiment of the present application is briefly described by taking the terminal device as a computer as an example, specifically: After the industrial camera 4 takes a photo, the photo data is automatically transmitted to the computer 8 through the network. When the photo display frame in the display module of the computer 8 detects that the "shot image" is updated, the trained deep learning model is used to perform image segmentation and calculation, and the automatically identified billet number, calculated billet length and width and other data are displayed at the corresponding position of the display module, and saved to the specified file through the storage module; For special ingot situations, such as irregular external shape of the ingot, the operator can choose the manual operation mode. In this working mode, the operator determines whether the photo meets the requirements of integrity and usability. If the photo meets the requirements, select "Ingot Thickness", enter the ingot number of the measured ingot, the manually measured ingot length and width data, and click "Confirm Submit". The software will display the measured data in "Measurement Results". Click "Save Data" to save the measurement result data to the specified file.

[0045] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0046] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0047] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0048] In the embodiments provided in the present application, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0049] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0050] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0051] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc.

[0052] The present application implements all or part of the processes in the above-mentioned embodiment method, and may also be implemented through a computer program product. When the computer program product runs on a terminal, the terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0053] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A system for automatically measuring the size of a casting ingot based on machine vision, characterized in that: include: An automatic acquisition module acquires an image of the casting when it is detected that the casting reaches a preset measurement area; The intelligent measurement module processes the ingot image according to a preset deep learning algorithm to obtain pixel coordinates of the edge of the ingot surface, obtains pixel coordinates of the corner points of the ingot surface by fitting the pixel coordinates of the edge of the ingot surface into the edge of the ingot, and obtains the surface size of the ingot according to the distance value of the pixel coordinates of the corner points of the ingot surface; The intelligent measurement module includes a billet edge recognition module and a billet size calculation module; The ingot edge recognition module is trained according to a preset deep learning algorithm to obtain a deep learning model, extracts the ingot surface edge feature pixels in the ingot image based on the deep learning model, and obtains the ingot surface edge pixel coordinates according to the ingot surface edge feature pixels; The ingot size calculation module uses a linear regression algorithm to fit the pixel coordinates of the edge of the ingot surface to obtain the ingot surface edge line, obtains the pixel coordinates of the corner points on the ingot surface based on the ingot surface edge line, converts the pixel coordinates of the corner points on the ingot surface into world coordinates, calculates the distance between the coordinates through the world coordinates of the corner points, and obtains the ingot surface size.

2. The automatic measurement system for ingot size based on machine vision according to claim 1 is characterized in that: The automatic acquisition module includes a position detection sensor, a controller, an auxiliary light source and an industrial camera; When the position detection sensor detects that the casting billet conveyed by the roller reaches the preset measurement area, a first signal is sent to the controller; The controller controls the motor of the roller to stop running according to the first signal, and generates a second signal and a third signal according to the first signal, and there is a preset time interval between the second signal and the third signal, wherein the second signal is used to start the auxiliary light source, and the third signal is used to start the industrial camera; The industrial camera is used to capture images of the ingot and transmit the images of the ingot to the intelligent measurement module.

3. The automatic measurement system for ingot size based on machine vision according to claim 1 is characterized in that: The intelligent measurement module also includes a casting billet number recognition module and an association module; The billet number recognition module uses an image reconstruction algorithm to recognize the billet image to obtain the billet number; The association module is used to associate and store information of the billet number and the billet surface size.

4. The automatic measurement system for ingot size based on machine vision according to claim 3 is characterized in that: The ingot number recognition module includes a positioning detection module, a data reconstruction module and an recognition module; The positioning detection module extracts the feature information of the billet number through a convolutional neural network, and generates a position boundary box of the billet number according to the feature information of the billet number; The data reconstruction module is used to increase the channel dimension of the image within the position boundary box of the casting billet number through sub-pixel convolution calculation, and use the additional channels as pixel data to increase the resolution of the image to obtain a high-resolution feature map, and up-sample the high-resolution feature map to obtain a reconstructed casting billet number image; The recognition module is used to recognize the reconstructed billet number image through a preset deep learning model to obtain the billet number.

5. The automatic measurement system for ingot size based on machine vision according to claim 1 is characterized in that: It also includes interactive modules; The interactive module is used to display the relevant data sent by the intelligent measurement module.

6. The automatic measurement system for ingot size based on machine vision according to claim 5 is characterized in that: The interactive module also receives and displays manual measurement data according to instructions from the manual operation module.

7. The automatic measurement system for ingot size based on machine vision according to claim 5 is characterized in that: The interaction module includes a display module, wherein the display module includes an image display module; The image display module includes a captured image display module and a measurement diagram display module, wherein the captured image display module is used to display the current ingot image; The measurement image display module is used to display the measurement image, wherein the measurement image is a measurement line superimposed on the current ingot image, wherein the line is fitted by the pixel coordinates of the ingot surface edge obtained by the ingot edge recognition module, and the line color is different from the color of the current ingot image.

8. The automatic measurement system for ingot size based on machine vision according to claim 5 is characterized in that: The interaction module includes a display module, wherein the display module includes a data display module; The data display module is used to display relevant data of the intelligent measurement module and the manual operation module.

9. The automatic measurement system for ingot size based on machine vision according to claim 1, characterized in that: Also included is a storage module; The storage module is used to store relevant data sent by the intelligent measurement module and / or the manual operation module.

Images