CN116660271A - Method for detecting surface flatness and smoothness of indium ingot after demolding - Google Patents

Method for detecting surface flatness and smoothness of indium ingot after demolding Download PDF

Info

Publication number
CN116660271A
CN116660271A CN202310745564.7A CN202310745564A CN116660271A CN 116660271 A CN116660271 A CN 116660271A CN 202310745564 A CN202310745564 A CN 202310745564A CN 116660271 A CN116660271 A CN 116660271A
Authority
CN
China
Prior art keywords
indium ingot
smoothness
gray
image
indium
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
Application number
CN202310745564.7A
Other languages
Chinese (zh)
Inventor
肖清泰
许威
杨凯
姚钦文
王�华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Kunming University of Science and Technology
Original Assignee
Kunming University of Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Kunming University of Science and Technology filed Critical Kunming University of Science and Technology
Priority to CN202310745564.7A priority Critical patent/CN116660271A/en
Publication of CN116660271A publication Critical patent/CN116660271A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • 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
    • G01B11/30—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces
    • G01B11/303—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces using photoelectric detection means
    • 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
    • G01B11/30—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces
    • G01B11/306—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces for measuring evenness
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P10/00—Technologies related to metal processing
    • Y02P10/20—Recycling

Abstract

The application discloses a method for detecting the flatness and the smoothness of the surface of an indium ingot after demolding, which comprises the following steps: irradiating the surface of the indium ingot to be detected through a light source to form a light beam; absorbing the light beam by the image pickup device and converting the light beam into an electric signal; the method comprises the steps that an electric signal output by a camera device is received based on a data acquisition card, the electric signal is transmitted to an image processing device, the electric signal is processed, and the processed electric signal is put in through a display device to obtain a gray level image; machine learning analysis is carried out on the gray level image based on the image processing device, a damaged area of the surface of the indium ingot is identified, and whether the indium ingot is qualified or not is judged; the gradation image is evaluated for flatness and smoothness by the image processing device, and the gradation image, the damaged area judgment result, and the fraction of flatness and smoothness are displayed based on the display device. The application can effectively reflect the characteristics of the surface of the indium ingot, and is simple and easy to implement.

Description

Method for detecting surface flatness and smoothness of indium ingot after demolding
Technical Field
The application relates to the technical field of photoelectric detection, in particular to a method for detecting the surface flatness and smoothness of an indium ingot after demolding.
Background
Indium is a metal element widely used in the field of optoelectronics, such as for manufacturing liquid crystal displays, solar cells, laser diodes, etc. Indium ingots are one of the basic forms of indium obtained by melting indium and casting the melted indium into ingots. The quality of the indium ingot surface directly affects the performance and the service life of the photoelectric device, so that the indium ingot surface needs to be detected to judge whether the indium ingot surface meets the requirements.
At present, the detection method for the flatness and the smoothness of the surface of the indium ingot mainly comprises the following steps: one is to observe the microstructure of the surface of an indium ingot by means of an optical microscope and then evaluate it according to international or national standards. The method has the advantages that the details of the surface of the indium ingot can be intuitively seen, but has the disadvantages of complex operation, long time consumption, high cost, great influence of human factors on accuracy and the like. The other is to use a laser interferometer or other optical instruments to measure the surface of the indium ingot with high precision. The method has high precision and high efficiency, but has the advantages of high cost, complex operation and need of professional operators. Still another is to observe the macroscopic appearance of the surface of the indium ingot with the human eye and then judge it empirically or with reference to a sample. The method has the advantages of simplicity, easiness, low cost, wide application range and the like, but has the defects of strong subjectivity, low precision, difficult fatigue and the like. Therefore, at present, no detection method capable of simultaneously meeting the requirements of high efficiency, accuracy, economy and the like of detecting the surface flatness and the smoothness of the indium ingot and being not limited by occasions and conditions exists.
Disclosure of Invention
In order to solve the technical problems, the application provides a method for detecting the surface flatness and the smoothness of the demolded indium ingot, which can effectively reflect the characteristics of the surface of the indium ingot, and has the advantages of simplicity, easiness, low cost, high precision and wide application range.
To achieve the above object, the present application provides a method for detecting surface flatness and smoothness after demolding of an indium ingot, comprising:
irradiating the surface of the indium ingot to be detected through a light source to form a light beam;
absorbing the light beam by an image pickup device and converting the light beam into an electric signal;
the method comprises the steps of receiving an electric signal output by the camera device based on a data acquisition card, transmitting the electric signal to an image processing device, processing the electric signal, and throwing the processed electric signal through a display device to obtain a gray level image;
and carrying out model learning analysis on the gray level image based on the image processing device, identifying a damaged area on the surface of the indium ingot, judging whether the indium ingot is qualified or not, evaluating the gray level image, giving out corresponding scores, and displaying the gray level image, the damaged area judging result and the evaluation scores based on the display device.
Preferably, the light source is a blue light source or a white light source.
Preferably, the blue light source is a monochromatic light source or a narrowband filter with a wavelength of 450nm, the reflectance of the blue light source being greater than 200 lumens.
Preferably, the indium ingot to be detected is arranged on a fixed support, the fixed support is a fixed support with a horizontal desktop, a leveling knob is arranged at the bottom of the fixed support and used for adjusting the height and levelness of the fixed support, a level gauge is arranged on the side face of the fixed support and used for measuring the inclination angle of the fixed support.
Preferably, the image pickup device is a color image pickup device or a black-and-white image pickup device, and the image pickup device has a COMS sensor of not less than 1200 ten thousand pixels and a sensitivity of not less than 200 IOS.
Preferably, processing the electrical signal includes:
and carrying out gray processing on the electric signals through the image processing device, and throwing the electric signals subjected to gray processing through the display device to form gray images.
Preferably, the method for gray scale processing of the electric signal comprises the following steps:
Gray＝0.114B
where Gray represents the Gray value and B represents the blue channel value.
Preferably, the display device is a display apparatus that can display a gray-scale image.
Preferably, performing model learning analysis on the gray scale image includes:
classifying and regressing the gray level image by using a method of a deep convolutional neural network DCNN or a support vector machine, and outputting a damaged area, a qualification judgment, flatness and a finish score, wherein the method of the deep convolutional neural network DCNN or the support vector machine is a model obtained by learning and training by using a marked data sample.
Preferably, the marking data sample is a data set obtained by manually detecting the surface of the indium ingot by a professional and giving qualification judgment, flatness and finish score and damaged area marking.
Compared with the prior art, the application has the following advantages and technical effects:
(1) The method is used for assisting workers in site after indium ingot casting to judge whether the indium ingot is qualified or not, and compared with human eyes, the method is more convenient and faster and is not easy to fatigue. The method can effectively reflect the characteristics of the surface of the indium ingot, is simple and feasible, has low cost and high precision, and has wide application range;
(2) The application avoids the influence of temperature change and noise interference on the detection result; the camera is used as a detection instrument, blue light reflected by the indium surface can be captured in real time and converted into a digital signal, so that subsequent image processing and analysis are facilitated; the gray processing is used as an image processing method, so that the calculation process can be simplified, the difference of the reflected light intensity of the indium surface is highlighted, and the detection precision and efficiency are improved; the data acquisition card is used as signal transmission equipment, so that the stability and the integrity of signals are ensured, and the data loss and the interference are reduced; the quality characteristics of the indium surface can be quantitatively reflected by taking the flatness and the smoothness as evaluation indexes, so that the evaluation objectivity and comparability are improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:
FIG. 1 is a schematic diagram of an apparatus for detecting in an embodiment of the present application;
FIG. 2 is a flow chart of a method for detecting surface flatness and finish of an indium ingot after demolding in accordance with an embodiment of the present application;
the device comprises a bracket, a blue light source, a camera, a display, a level gauge, a leveling knob, an indium ingot and a display, wherein the bracket is arranged at the bottom of the bracket, the blue light source is arranged at the bottom of the bracket, and the blue light source is arranged at the bottom of the bracket.
Detailed Description
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
Embodiment 1,
The application provides a method for detecting the flatness and the smoothness of the surface of an indium ingot after demolding, which is shown in fig. 1-2 and comprises the following steps:
(a) The indium ingot 7 is placed on a fixed support 1 and the table top is leveled so that its surface is perpendicular to the horizontal plane. The bottom of the bracket 1 is provided with four leveling knobs 6, and the height and the levelness of the bracket 1 can be adjusted by rotating. The side of the bracket 1 is provided with a level 5 for displaying the inclination angle of the bracket 1 so as to be convenient for leveling.
(b) The surface of the indium ingot 7 is irradiated from above with a blue light source 2, such as a blue LED lamp, to form a parallel beam of blue light. The blue light source 2 is a monochromatic light source or a narrow-band filter having a wavelength of about 450nm, and can emit blue light with high brightness, and has a reflectance of 200 lumens or more.
(c) The blue light reflected by the surface of the indium ingot 7 is received just above the indium ingot 7 by a camera 3 and converted into an electric signal. The camera 3 is a color or black-and-white camera, has a CMOS sensor of at least 1200 ten thousand pixels and a sensitivity of at least 200IOS, and can clearly record reflected light from the surface of the indium ingot 7 and convert it into a grayscale image. The Gray image conversion formula is gray=0.114B, and the gradation processing is performed according to a preset threshold or standard.
(d) The electric signal output from the camera 3 is received by a data acquisition card and transmitted to an image processor, such as a computer. The image processor subjects the electrical signal to a grey scale process and puts it on a display 4 to form a grey scale image. The display 4 is a liquid crystal display or other display device capable of displaying gray-scale images and has a sufficient size and definition.
(e) And carrying out machine learning analysis on the gray level image by using an image processor, identifying the damaged area on the surface of the indium ingot 7, and judging whether the indium ingot is qualified or not. The machine learning analysis method classifies and regresses gray images using a Deep Convolutional Neural Network (DCNN), and outputs a damaged area, a pass or fail judgment, flatness, and a finish score.
The method specifically comprises the following steps:
and inputting the gray level image into a DCNN model, wherein the DCNN model consists of a plurality of convolution layers, a pooling layer, an activation layer and a full connection layer and is used for extracting the characteristics of the image and outputting classification and regression results. The DCNN model is trained using the marker data samples to optimize parameters and loss functions of the model. The gray image is divided according to the output of the DCNN model, the broken area and the normal area are separated, and the area and the position of each area are given. And classifying the gray level images according to the output of the DCNN model, judging whether the surface of the indium ingot 7 is qualified or not, and giving the probability or score of whether the indium ingot is qualified or not. And (3) carrying out regression on the gray level image according to the output of the DCNN model, predicting the flatness and the smoothness of the surface of the indium ingot 7, and giving corresponding values or grades.
The Deep Convolutional Neural Network (DCNN) is a model obtained by learning and training by using a marked data sample, wherein the marked data sample is a data set obtained by manually detecting the surface of an indium ingot by a professional and giving qualification judgment, flatness and finish scores and damaged area labeling.
(f) The display 4 displays a gray image, a broken area, a pass or fail judgment, flatness, and a finish score.
Embodiment II,
As shown in fig. 2, a specific flowchart for detecting the flatness and smoothness of the surface of the indium ingot 7 in this embodiment is shown.
This embodiment is substantially the same as the first embodiment except that: in step (b), the surface of the indium ingot 7 is irradiated with a white light source instead of a blue light source, and in step (c), the color image is converted into a gray image using a red-green-blue three-channel (RGB) conversion formula.
The RGB conversion formula is gray=0.299r+0.587g+0.114 b.
Third embodiment,
This embodiment is substantially the same as the first embodiment except that: in step (e), a Support Vector Machine (SVM) is used instead of a Deep Convolutional Neural Network (DCNN) to perform machine learning analysis on the gray scale image and to output a breakage region, a pass or fail judgment, flatness, and finish score. A Support Vector Machine (SVM) is a model trained using labeled data samples, where the labeled data samples are the same as in embodiment one.
The model training specifically comprises:
data preparation: a set of marked gray scale image samples is collected, including images of normal indium ingots and images of broken indium ingots. Ensure that the sample contains various breakage conditions and normal conditions. Feature extraction: the gray scale image is input into a feature extractor SIFT (scale invariant feature transform), keypoints in the image are detected, and local feature descriptors associated with each keypoint are calculated. By extracting the keypoints and feature descriptors, a fixed length feature vector for each image can be obtained.
Training a classifier: the feature vector is input into an SVM (support vector machine) classifier. The feature space is mapped to a high-dimensional space using nonlinear kernel functions and an optimal hyperplane is found to partition the different classes of data. Training the SVM classifier by using marked data samples, and improving the accuracy of the classifier by optimizing parameters and loss functions of the classifier.
Dividing the damaged area and the normal area: and dividing the gray level image according to the output of the SVM classifier, and separating the damaged area from the normal area. By treating the output of the classifier as a label of pixels and applying an image segmentation algorithm threshold segmentation. After the division, the area and position information of each region are calculated.
Judging whether the surface of the indium ingot is qualified or not: and classifying the gray level images according to the output of the SVM classifier, and judging whether the surface of the indium ingot is qualified or not. A threshold is set according to the decision value (probability value or confidence degree output by the classifier) of the classifier to determine whether the classifier is qualified or not. If the decision value is higher than the threshold value, judging that the test result is qualified; otherwise, the test is judged to be unqualified.
Predicted surface flatness and finish: and carrying out regression on the gray level image according to the output of the SVM classifier, and predicting the flatness and the smoothness of the indium ingot surface. Regression models (e.g., linear regression, support vector regression, etc.) may be used to establish the relationship between the feature vector and the target value (flatness and smoothness) and predict the value or grade.
Model verification and evaluation: and verifying and evaluating the optimized model. Unlabeled test data sets are used to evaluate the performance and generalization ability of the model to determine the effectiveness and reliability of the model.
By executing the steps, a gray image analysis system is established, and the damaged area, the surface qualification, the flatness, the smoothness and the like of the indium ingot are evaluated and predicted by using a SIFT feature extractor, an SVM classifier and a prediction and segmentation method.
According to the application, blue light is used for irradiating the surface of the indium ingot, and the reflected light is recorded and subjected to gray processing by using the camera, so that a gray image of the surface of the indium ingot is obtained. And classifying and regressing the gray level images by using a Deep Convolutional Neural Network (DCNN) according to the change condition of gray level values in the gray level images, and outputting damaged areas, qualification judgment, flatness and smoothness scores. The method has the advantages of simplicity in operation, low cost, high precision, wide application range and the like.
In the application, the blue light source is a monochromatic light source or a narrow-band filter with the wavelength of about 450nm, and the characteristics of the surface of the indium ingot can be better reflected because the indium has higher reflectivity and low transmissivity to blue light. The camera is a color or black-and-white camera and has sufficient resolution and sensitivity to clearly record the reflected light from the surface of the indium ingot and convert it into a gray scale image. The gray level image is converted into 8-bit or 16-bit gray level values, and grading treatment is carried out according to a preset threshold value or standard, so that the brightness difference of the surface of the indium ingot can be distinguished better, and the subsequent judgment is facilitated.
In the step of judging the flatness and the smoothness of the surface of the indium ingot, a Deep Convolutional Neural Network (DCNN) is used for classifying and regressing gray level images, and a damaged area, a qualification judgment, flatness and smoothness score are output. The Deep Convolutional Neural Network (DCNN) is a model obtained by learning and training by using a marked data sample, wherein the marked data sample is a data set obtained by manually detecting the surface of an indium ingot by a professional and giving qualification judgment, flatness and finish scores and damaged area labeling.
The application has the following advantages: (1) The blue light is used as a detection light source, so that the absorption and emission of the indium surface to light with other wavelengths can be effectively inhibited, and the influence of temperature change and noise interference on a detection result is avoided; (2) The camera is used as a detection instrument, blue light reflected by the indium surface can be captured in real time and converted into a digital signal, so that subsequent image processing and analysis are facilitated; (3) The gray processing is used as an image processing method, so that the calculation process can be simplified, the difference of the reflected light intensity of the indium surface is highlighted, and the detection precision and efficiency are improved; (4) The data acquisition card is used as signal transmission equipment, so that the stability and the integrity of signals can be ensured, and the data loss and the interference are reduced; (5) By using machine learning as an image analysis method, the damaged area of the indium surface can be automatically identified, and whether the indium surface is qualified or not is judged, so that personal errors and subjective judgment are reduced; (6) The flatness and the smoothness are used as evaluation indexes, so that the quality characteristics of the indium surface can be quantitatively reflected, and the evaluation objectivity and comparability are improved; (7) The display is used as output equipment of the detection result, the gray level image, the damaged area, the judgment of whether the indium surface is qualified or not, the flatness and the score of the smoothness can be intuitively displayed, and the observation and the judgment of workers are facilitated. The method is suitable for on-site auxiliary workers to judge whether the indium ingot is qualified or not after the indium ingot is cast, and compared with human eyes, the method is more convenient, quick and less prone to fatigue. The method can effectively reflect the characteristics of the surface of the indium ingot, and is simple and feasible, low in cost, high in precision and wide in application range.
The present application is not limited to the above-mentioned embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present application are intended to be included in the scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims (10)

1. A method for detecting surface flatness and finish of an indium ingot after demolding, comprising:
irradiating the surface of the indium ingot to be detected through a light source to form a light beam;
absorbing the light beam by an image pickup device and converting the light beam into an electric signal;
the method comprises the steps of receiving an electric signal output by the camera device based on a data acquisition card, transmitting the electric signal to an image processing device, processing the electric signal, and throwing the processed electric signal through a display device to obtain a gray level image;
and carrying out model learning analysis on the gray level image based on the image processing device, identifying a damaged area on the surface of the indium ingot, judging whether the indium ingot is qualified or not, evaluating the gray level image, giving out corresponding scores, and displaying the gray level image, the damaged area judging result and the evaluation scores based on the display device.
2. The method for detecting surface flatness and smoothness after demolding of an indium ingot according to claim 1, wherein the light source is a blue light source or a white light source.
3. The method for detecting surface flatness and smoothness after indium ingot stripping according to claim 2, wherein the blue light source is a monochromatic light source or a narrowband filter with wavelength of 450nm, and the reflectance of the blue light source is more than 200 lumens.
4. The method for detecting the surface flatness and smoothness of an indium ingot after demolding according to claim 1, wherein the indium ingot to be detected is placed on a fixed support, the fixed support is a fixed support with a horizontal table top, a leveling knob is arranged at the bottom of the fixed support, the leveling knob is used for adjusting the height and levelness of the fixed support, a level gauge is arranged on the side face of the fixed support, and the level gauge is used for measuring the inclination angle of the fixed support.
5. The method for detecting the flatness and smoothness of the surface of an indium ingot after demolding according to claim 1, wherein the image pickup device is a color image pickup device or a black-and-white image pickup device, and the image pickup device has a COMS sensor of not less than 1200 ten thousand pixels and a sensitivity of not less than 200 IOS.
6. The method for detecting surface flatness and finish after stripping an indium ingot according to claim 1, wherein processing the electrical signal comprises:
and carrying out gray processing on the electric signals through the image processing device, and throwing the electric signals subjected to gray processing through the display device to form gray images.
7. The method for detecting surface flatness and smoothness after demolding of an indium ingot according to claim 6, wherein the method for gray-scale processing the electric signal is:
Gray＝0.114B
where Gray represents the Gray value and B represents the blue channel value.
8. The method for detecting surface flatness and smoothness after demolding of an indium ingot according to claim 1, wherein the display means is a display device capable of displaying a gray-scale image.
9. The method for detecting surface flatness and smoothness after indium ingot stripping according to claim 1, wherein performing model learning analysis on the gray scale image comprises:
classifying and regressing the gray level image by using a method of a deep convolutional neural network DCNN or a support vector machine, and outputting a damaged area, a qualification judgment, flatness and a finish score, wherein the method of the deep convolutional neural network DCNN or the support vector machine is a model obtained by learning and training by using a marked data sample.
10. The method for detecting surface flatness and smoothness after indium ingot stripping according to claim 9, wherein the marked data samples are data sets obtained by manual inspection of the indium ingot surface by a professional and giving a pass or fail judgment, flatness and smoothness scores, and damage region labeling.
CN202310745564.7A 2023-06-21 2023-06-21 Method for detecting surface flatness and smoothness of indium ingot after demolding Pending CN116660271A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310745564.7A CN116660271A (en) 2023-06-21 2023-06-21 Method for detecting surface flatness and smoothness of indium ingot after demolding

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310745564.7A CN116660271A (en) 2023-06-21 2023-06-21 Method for detecting surface flatness and smoothness of indium ingot after demolding

Publications (1)

Publication Number Publication Date
CN116660271A true CN116660271A (en) 2023-08-29

Family

ID=87722402

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310745564.7A Pending CN116660271A (en) 2023-06-21 2023-06-21 Method for detecting surface flatness and smoothness of indium ingot after demolding

Country Status (1)

Country Link
CN (1) CN116660271A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117541589A (en) * 2024-01-10 2024-02-09 深圳市京鼎工业技术股份有限公司 Automatic detection method, system and medium for surface finish of injection mold

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117541589A (en) * 2024-01-10 2024-02-09 深圳市京鼎工业技术股份有限公司 Automatic detection method, system and medium for surface finish of injection mold
CN117541589B (en) * 2024-01-10 2024-03-19 深圳市京鼎工业技术股份有限公司 Automatic detection method, system and medium for surface finish of injection mold

Similar Documents

Publication Publication Date Title
CN103018180B (en) Method and device for detecting cotton diseases based on multisource light information technology
CN109477848B (en) Systems, methods, and apparatus for identifying sample container lids
JP6879366B2 (en) Methods, devices and quality check modules for detecting hemolysis, jaundice, lipemia, or normality of a sample
CN103792699A (en) TFT-LCD Mura defect machine vision detecting method based on B spline surface fitting
Gunasekaran et al. Image processing for stress cracks in corn kernels
JP2019504996A (en) Method and apparatus for classifying artifacts in a sample
JP2011180120A (en) Method and device for diagnosis of waterproof sheet
JP2022522348A (en) Equipment and methods for inspecting membranes on substrates
CN116660271A (en) Method for detecting surface flatness and smoothness of indium ingot after demolding
KR20190122160A (en) System and Method for Inspecting Optical Power and Thickness of Ophthalmic Lenses immersed in a Solution
JP2013134666A (en) Binary image generation device, classification device, binary image generation method, and classification method
JPWO2019168142A1 (en) Image classification methods, devices and programs
CN113822852A (en) Image processing method, program, and recording medium
CN104777172A (en) Quick and intelligent defective optical lens detection device and method
JP2015161575A (en) Tire deterioration evaluation device, system thereof, method thereof, and program thereof
Yan et al. Non-destructive testing of composite fiber materials with hyperspectral imaging—Evaluative studies in the EU H2020 FibreEUse project
CN113421230A (en) Vehicle-mounted liquid crystal display light guide plate defect visual detection method based on target detection network
CN112070762A (en) Mura defect detection method and device for liquid crystal panel, storage medium and terminal
CN114881987A (en) Improved YOLOv 5-based hot-pressing light guide plate defect visual detection method
CN109685046A (en) A kind of skin light transparency analysis method and its device based on image grayscale
CN111226110A (en) Detection method and system
US11137355B2 (en) Process and system for diamond clarity measurement
CN105954205B (en) Green plum pol based on light spectrum image-forming and acidity Rapid non-destructive testing device
CN114152621A (en) Processing method, processing device and processing system
KR20030083359A (en) Method and Analysis Apparatus for Automatic Crack Recognition of Structure using Image Processing 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