WO2023276101A1 - 異常検出装置および異常検出方法 - Google Patents
異常検出装置および異常検出方法 Download PDFInfo
- Publication number
- WO2023276101A1 WO2023276101A1 PCT/JP2021/024917 JP2021024917W WO2023276101A1 WO 2023276101 A1 WO2023276101 A1 WO 2023276101A1 JP 2021024917 W JP2021024917 W JP 2021024917W WO 2023276101 A1 WO2023276101 A1 WO 2023276101A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- value
- luminance
- abnormality
- image
- rolling
- Prior art date
Links
- 230000005856 abnormality Effects 0.000 title claims abstract description 139
- 238000001514 detection method Methods 0.000 title claims abstract description 110
- 238000005096 rolling process Methods 0.000 claims abstract description 91
- 238000012545 processing Methods 0.000 claims abstract description 76
- 239000000284 extract Substances 0.000 claims abstract description 9
- 230000002159 abnormal effect Effects 0.000 claims description 51
- 239000002184 metal Substances 0.000 claims description 33
- 238000005286 illumination Methods 0.000 claims description 21
- 238000009826 distribution Methods 0.000 claims description 15
- 238000005259 measurement Methods 0.000 claims description 5
- 238000003384 imaging method Methods 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 abstract description 75
- 238000000034 method Methods 0.000 abstract description 50
- 238000010586 diagram Methods 0.000 description 19
- 230000008569 process Effects 0.000 description 19
- 230000009467 reduction Effects 0.000 description 9
- 238000012937 correction Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 5
- 230000006872 improvement Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000000052 comparative effect Effects 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 2
- 238000005452 bending Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 238000005315 distribution function Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000005098 hot rolling Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000007769 metal material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002250 progressing effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21B—ROLLING OF METAL
- B21B38/00—Methods or devices for measuring, detecting or monitoring specially adapted for metal-rolling mills, e.g. position detection, inspection of the product
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/8914—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the material examined
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21B—ROLLING OF METAL
- B21B1/00—Metal-rolling methods or mills for making semi-finished products of solid or profiled cross-section; Sequence of operations in milling trains; Layout of rolling-mill plant, e.g. grouping of stands; Succession of passes or of sectional pass alternations
- B21B1/22—Metal-rolling methods or mills for making semi-finished products of solid or profiled cross-section; Sequence of operations in milling trains; Layout of rolling-mill plant, e.g. grouping of stands; Succession of passes or of sectional pass alternations for rolling plates, strips, bands or sheets of indefinite length
- B21B1/30—Metal-rolling methods or mills for making semi-finished products of solid or profiled cross-section; Sequence of operations in milling trains; Layout of rolling-mill plant, e.g. grouping of stands; Succession of passes or of sectional pass alternations for rolling plates, strips, bands or sheets of indefinite length in a non-continuous process
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N2021/8909—Scan signal processing specially adapted for inspection of running sheets
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/8914—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the material examined
- G01N2021/8918—Metal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30136—Metal
Definitions
- the present invention relates to an anomaly detection device and an anomaly detection method.
- Patent Document 1 discloses a method for detecting flaws on the surface of a running metal steel strip.
- a threshold calculation unit includes a density histogram calculation unit that obtains a density histogram for each unit area from an image signal, and a density histogram calculation unit that obtains a peak position of the density histogram, and a normal value when the peak position is used as an average value.
- the determination threshold value is obtained by minimizing the inclusion of flaw signal components other than texture signal components in the standard deviation value.
- strip reduction phenomenon (this is called rolling abnormality) occurs due to the rapid meandering of strips when passing through the tail end of the strip after the rear tension is released.
- the occurrence of scratches on the roll surface increases, and the number of roll replacements increases, which may lead to a decrease in product yield.
- rolling strip reduction rolling abnormality
- early intervention can be implemented, and the probability of preventing subsequent rolling abnormalities and equipment failures can be increased. possible to raise.
- Rolling plate reduction phenomenon is a phenomenon in which a metal strip is rolled in a folded state when it passes through a rolling mill.
- the image of the strip surface is monitored with a camera, and the brightness of the strip surface exceeds a certain threshold and the area increases. Sometimes plate anomalies can be detected.
- This threshold can vary depending on the type and material of the plate. It is disclosed that determination thresholds can be accurately and efficiently set for the entire surface and all types of metal steel strips by obtaining the deviation value as the formation signal level.
- the determination threshold used is constant.
- the present inventors have found that even if the type, material, etc. are the same, the luminance detected by the camera differs depending on the brightness of the illumination, the amount of water vapor in the surroundings, and the like. It has been clarified that there is room for improvement because the above-mentioned Patent Document 1 does not consider this point.
- An object of the present invention is to provide an anomaly detection device and an anomaly detection method capable of improving the detection accuracy of plate rolling anomalies compared to conventional methods.
- the present invention includes a plurality of means for solving the above problems, and one example thereof is an abnormality detection device for detecting a rolling abnormality on the surface of a metal strip rolled by a rolling mill, comprising: A camera for capturing an image of the metal strip during rolling of the metal strip, which is a target for detecting an abnormality, and extracting the metal strip from at least one image captured by the camera, and extracting the metal strip.
- a luminance reference value setting unit for obtaining a luminance reference value for determining that there is no abnormality in the board from the luminance data of the pixels within the range; an image processing unit that extracts the metal strip from the comparison image of the metal strip and detects the rolling abnormality based on the brightness difference between the brightness data of pixels within the range of the metal strip and the brightness reference value.
- FIG. 1 is a schematic diagram showing the configuration of an abnormality detection device according to an embodiment of the present invention
- FIG. 4 is a diagram showing how the range of a material to be rolled is extracted from an image in the abnormality detection device of the embodiment
- FIG. 4 is a diagram showing an example of a luminance (RGB) histogram of pixels within a plate range for one image in the abnormality detection device of the embodiment
- FIG. 5 is a diagram showing an example of a method of calculating a luminance reference value in the abnormality detection device of the embodiment
- FIG. 5 is a diagram showing an example of a method of calculating a luminance reference value in the abnormality detection device of the embodiment;
- FIG. 5 is a diagram showing another example of a method of calculating a luminance reference value in the abnormality detection device of the embodiment;
- FIG. 5 is a diagram showing an example of abnormal region extraction determination processing in the abnormality detection device of the embodiment;
- FIG. 5 is a diagram showing an example of abnormal region extraction determination processing in the abnormality detection device of the embodiment.
- FIG. 10 is a diagram showing another example of the abnormal region extraction determination process in the abnormality detection device of the embodiment;
- FIG. 10 is a diagram showing another example of the abnormal region extraction determination process in the abnormality detection device of the embodiment;
- FIG. 10 is a diagram showing another example of the abnormal region extraction determination process in the abnormality detection device of the embodiment;
- FIG. 5 is a diagram for explaining the flow of a method for calculating an abnormal area based on a reflected light area in the abnormality detection device of the embodiment;
- FIG. 5 is a diagram for explaining the flow of a method for calculating an abnormal area based on a reflected light area in the abnormality detection device of the embodiment;
- FIG. 5 is a diagram for explaining the flow of a method for calculating an abnormal area based on a reflected light area in the abnormality detection device of the embodiment;
- 4 is a flowchart of abnormality determination processing in the abnormality detection device of the embodiment.
- FIG. 1 An embodiment of the abnormality detection device and the abnormality detection method of the present invention will be described with reference to FIGS. 1 to 15.
- FIG. 1 the same or corresponding components are denoted by the same or similar reference numerals, and repeated descriptions of these components may be omitted.
- the metal strip that is the material to be rolled in the present invention is generally a strip of a metal material that can be rolled, and its type is not particularly limited. be able to.
- FIG. 1 is a schematic diagram showing the configuration of an abnormality detection device of this embodiment and a rolling mill equipped with the same
- FIG. 2 is a schematic diagram illustrating the configuration of the abnormality detection device.
- a rolling facility 100 shown in FIG. 1 is a finish rolling facility for rolling a material 1 to be rolled, and includes an F1 stand 10, an F2 stand 20, an F3 stand 30, an F4 stand 40, an F5 stand 50, an F6 stand 60, and an F7 stand. It has a stand 70, cameras 81 and 82, a tension control looper 65, an image processing computer 90, a display device 95, and the like.
- the cameras 81 and 82, the illumination device 67, and the image processing computer 90 constitute an abnormality detection device 101 for detecting an abnormality on the surface of the material 1 to be rolled.
- the rolling facility 100 is not limited to the configuration in which seven rolling stands are provided as shown in FIG. 1, and may have at least one stand.
- Each of the F1 stand 10, the F2 stand 20, the F3 stand 30, the F4 stand 40, the F5 stand 50, the F6 stand 60, and the F7 stand 70 has an upper work roll and a lower work roll, and the upper work roll and the lower work roll, respectively.
- the roll configuration of the rolling mill is not limited to the form described above, and it is sufficient that there are at least upper and lower work rolls.
- the looper 65 is a roll for line tension control. This roll is installed with its rotating shaft extending in the width direction of the material 1 to be rolled, and the line tension can be changed by raising or lowering the material 1 to be rolled vertically. between F1 stand 10 and F2 stand 20, between F2 stand 20 and F3 stand 30, between F3 stand 30 and F4 stand 40, between F4 stand 40 and F5 stand 50, between F5 stand 50 and They are provided between the F6 stand 60 and between the F6 stand 60 and the F7 stand 70, respectively.
- the looper 65 may also have the function of a plate shape meter for detecting the tension distribution in the plate width direction.
- the camera 81 is provided at a position capable of capturing an image including the material 1 to be rolled on the delivery side of the F4 stand 40 and the entry side of the F5 stand 50. For example, directly above the material 1 to be rolled, Alternatively, an image including the material to be rolled 1 is taken from obliquely above at an interval shorter than 0.1 seconds, preferably in a moving image format. Data of the image captured by the camera 81 is transmitted to the image processing computer 90 via the communication line 85 .
- the camera 82 is provided on the delivery side of the F7 stand 70 at a position capable of capturing an image including the material 1 to be rolled. An image including the material to be rolled 1 is taken at an interval shorter than 0.1 seconds, for example. Data of images captured by the camera 82 are also transmitted to the image processing computer 90 via the communication line 85 .
- These cameras 81 and 82 perform an imaging step of capturing an image including the material 1 to be rolled.
- these cameras 81 and 82 take images of the material to be rolled 1 at different times during rolling of one roll that constitutes the material to be rolled 1, which is an abnormality detection target.
- the lighting device 67 illuminates the material to be rolled 1, particularly the material to be rolled 1 in the range captured by the cameras 81 and 82, and is appropriately arranged on the ceiling of the rolling mill where the rolling equipment 100 is installed. Although it can be a general lighting equipment, it may be a dedicated lighting device.
- the image processing computer 90 is a device configured by a computer or the like that controls the operation of each device in the rolling mill 100, and has a luminance reference value setting section 91, an image processing section 92, a database 93, and the like.
- the luminance reference value setting unit 91 extracts the material to be rolled 1 from at least one image captured by the cameras 81 and 82, and determines whether the sheet is normal or not based on the luminance data of the pixels within the range of the material to be rolled 1. This is the part that obtains the reference value of the brightness that is determined to be present, and is the execution subject of the brightness reference value setting process.
- the luminance reference value setting unit 91 extracts images from the moving images.
- the image processing unit 92 uses one or more of the one or more captured images as comparison images, extracts the material 1 to be rolled from each comparison image, and determines the brightness of the pixels within the range of the material 1 to be rolled. It is a part that detects rolling abnormality on the surface based on the luminance difference between the data and the luminance reference value, and is the main body that executes the image processing process.
- the image processing section 92 has a detection area setting section 92A, a reflected light area setting section 92B, an abnormal area setting section 92C, and the like.
- the detection area setting part 92A is a part for setting a detection area of the rolled material 1, which is an abnormality detection target, from the comparison image.
- the reflected light region setting portion 92B is a portion that sets a reflected light region in which the illumination light originating from the illumination device 67 is reflected on the surface of the material 1 to be rolled, from the comparative image.
- the abnormal area setting unit 92C is a part that detects an abnormal portion of the surface from the detection area using the reference value as a threshold, and sets an area from which the reflected light area is removed as an abnormal area.
- the comparative image processed by the image processing unit 92 is basically the latest image.
- the database 93 stores one component of the brightness of the R (red) value, G (green) value, and B (blue) value of the pixels within the range of the material 1 to be rolled in the image of the material 1 to be rolled.
- It is a storage device that stores information on the boundary line.
- it is configured with an SSD, HDD, or the like.
- the display device 95 is a display device such as a display and an audio device such as an alarm device. It is a device for communicating about Therefore, a display is often used as the display device 95 .
- the operator checks the display screen of the display device 95, each stand itself, and between the stands to see if there is a rolling abnormality such as a strip reduction phenomenon. For example, when the operator confirms the display that the rolling strip reduction phenomenon has occurred on the display device 95, and the operation to be performed such as bending correction, leveling correction, roll speed correction, roll gap opening of the downstream stand, etc. is displayed.
- a rolling abnormality such as a strip reduction phenomenon.
- the operator is notified of the occurrence of the rolling strip reduction phenomenon on the display screen of the display device 95, and a correction or stop signal is sent to the rolling mill control device to avoid the rolling abnormality. It is possible to adopt a mode in which the avoidance operation is performed by automatic control, or a mode in which various correction operations or stop operation is performed by automatic control without displaying on the display device 95 .
- FIG. 3 is a diagram showing how the range of the material to be rolled is extracted from the image
- FIG. 4 is a diagram showing an example of a luminance (RGB) histogram of pixels within the plate range for one image
- FIGS. FIGS. 8 to 11 are diagrams showing an example of extraction determination processing of an abnormal area
- FIGS. 12 to 14 are abnormal areas by illumination area It is a figure explaining the flow of the calculation method of.
- the type and material of the material to be rolled 1 are the same, it is detected by the camera depending on the brightness of the lighting during rolling, the amount of water vapor in the surroundings, and the image processing settings of the camera. It is necessary to correspond because the brightness to be applied is different.
- an image including the material 1 to be rolled is acquired by the cameras 81 and 82 .
- the state of the material to be rolled 1 is continuously imaged in a moving image format.
- the captured image is output to the image processing computer 90 via the communication line 85 .
- the luminance reference value setting unit 91 binarizes the background and the area where the material 1 exists from the image of the material 1 to be rolled during rolling, as shown in FIG. Then, the range 1A of the material to be rolled 1 is extracted from the brightness area equal to or higher than a certain threshold. After that, abnormality detection processing is performed on the range 1A extracted by the image processing section 92 including the detection area setting section 92A, the reflected light area setting section 92B, the abnormal area setting section 92C, and the like.
- this extracted range 1A may include a region slightly inside or outside the actual plate region, and does not necessarily have to match the material to be rolled 1. Since the position of the material 1 to be imaged may change due to the fluctuation, the range 1A must be extracted so as to follow the change.
- the luminance reference value setting unit 91 obtains the luminance distribution of the pixels inside the range 1A of the material to be rolled 1 for the selected one image, and determines that the plate has no abnormality. Calculate the brightness reference value that Here, the brightness reference value setting unit 91 divides the brightness data into three components of R value, G value, and B value, and sets the brightness reference values as a reference R value (R value 0 ), a reference G value (G value 0 ), and a reference B value (B 0 value).
- Two values (a combination of the R0 value and the G0 value, the R0 value and the B0 value, and the B0 value and the G0 value) may be obtained from the luminance reference values.
- the brightness reference value setting unit 91 can be configured to process the brightness data in a gray scale such as 8 bits (256 gradations) or 16 bits (65536 gradations). In the case of gray scale, the subsequent processing is basically the same, and the details are omitted.
- a method of selecting from one image as a process for obtaining three values of a reference R value (R 0 value), a reference G value (G 0 value), and a reference B value (B 0 value) as luminance reference values. and a method of selecting from a plurality of images. First, a method for selecting a luminance reference value from one image will be described.
- the luminance reference value setting unit 91 sets the number of measurement points for the luminance (RGB) of all pixels in the range 1A extracted in FIG.
- a luminance frequency distribution (histogram) of R, G, and B values is obtained.
- R red
- G green
- B blue
- all of RGB take values from 0 to 255.
- FIG. 4 shows an example of a plate area luminance (RGB) histogram for one image.
- the brightness reference value setting unit 91 divides the area indicated by the integrated value of each distribution into two (central position: 50%) as a normal board. Let be the initial luminance reference value for each RGB component to be determined. Also, one value can be selected within an allowable range of ⁇ 20% from the central position of 50% and used as the luminance reference value for each of the RGB components. Note that the allowable range does not have to be " ⁇ 20%" and can be changed as appropriate.
- the value (position) used to obtain the brightness reference value may be specified by the operator before rolling the material 1 to be detected as an abnormality detection target, or may be set using a preset value of the device. A format in which the optimum value is appropriately learned may be used.
- the value that divides the area into two can be an initial luminance reference value for each.
- the luminance reference value may be used.
- the reference value may be recalculated to update the brightness reference value as needed, and there is no particular limitation.
- the brightness reference value setting unit 91 obtains the brightness reference value by averaging the brightness data captured in a plurality of images. It is desired that the luminance reference value is re-determined by adding the luminance data captured to the new image.
- the luminance reference value setting unit 91 performs a method shown in FIGS. 4 to 7 on two or more images captured by the cameras 81 and 82.
- the brightness reference value is obtained for each image of a specific location captured by each camera.
- the same method is used for luminance G and luminance B as well.
- the luminance R reference value R 0 (R 12 +R 3 )/2, and the moving average is taken.
- the same method is used for luminance G and luminance B as well.
- updating of the brightness reference value may be stopped halfway when it is determined to be stable, or the brightness reference value may be continuously updated during rolling of one coil. and is not particularly limited.
- the image processing unit 92 divides the luminance data from the image into R value, G value, and B value, and subtracts the reference R value from the R value, the reference G value from the G value, and the reference B value from the B value. to find the luminance difference of each.
- the last (latest) image among the multiple images may also be used as a comparison image.
- the image processing unit 92 detects a rolling abnormality based on the relationship between the luminance differences of the two components among the luminance differences.
- the abnormality determination method (i) determination based on the relationship between the luminance differences of the two components (using a threshold of a specific value) and (ii) the relationship between the luminance differences of the two components (using an arbitrary threshold boundary ) and the determination based on ).
- the details of the determination based on the relationship between the luminance differences of the two components (using a threshold of a specific value) will be described.
- the image processing unit 92 detects an abnormality when both luminance differences of the two components of the R value, G value, and B value are equal to or greater than their respective thresholds.
- both the luminance difference between the B value and the reference B value and the luminance difference between the R value and the reference R value are determined for each luminance difference.
- Both of the luminance differences of the two components forming one combination are equal to or greater than the respective luminance difference thresholds (G a and B a in FIG. 8), and the other combinations
- both of the luminance differences of the two components are equal to or greater than the respective luminance difference thresholds (R a and B a )
- the relationship between the luminance difference GG 0 and the luminance difference RR 0 is used to determine whether both the luminance differences of the two components are equal to or greater than their respective thresholds (G a and R a ). can be used for determination.
- the determination process as shown in Figs. 8 and 9 is particularly effective in an environment with little water vapor, because water vapor generated during rolling becomes noise in image processing.
- this treatment is not affected by the presence or absence of steam, and can be preferably performed under rolling conditions with a large amount of steam. Moreover, it can be suitably executed regardless of whether or not the reflected light region of the illumination light originating from the illumination device 67 and reflected on the surface of the material to be rolled is removed.
- the image processing unit 92 detects an abnormality in the plate surface based on the luminance difference of one component, the luminance difference of the other component, and an arbitrary threshold boundary.
- the image processing unit 92 calculates the brightness difference of two components (the brightness difference between the B value and the reference B value and the G value and The detection result of whether or not there is an abnormality is obtained from the boundary obtained therefrom, and the luminance difference of the two components (the B value and the reference B and the luminance difference between the R value and the reference R value) and the boundary obtained therefrom, the detection result as to whether or not there is an abnormality is obtained. More specifically, it is determined whether the plot of the luminance difference (RR 0 , GG 0 , BB 0 ) from the reference value is on the abnormal side of the boundary line.
- the image processing unit 92 detects that the plate surface is abnormal when both detection results are determined to be abnormal.
- the relationship between the luminance difference GG 0 and the luminance difference RR 0 can be used. It is desirable to use the difference and either luminance difference.
- any one of the three combinations may be used for determination. Moreover, it may be detected as an abnormality when either one of the two combinations exceeds an arbitrary threshold boundary. Furthermore, any of the three combinations may be used for determination. When using any of the three combinations, it may be detected as an abnormality when any one of them exceeds an arbitrary threshold boundary, or when two of the majority votes exceed an arbitrary threshold boundary, it is detected as an abnormality. Alternatively, an abnormality may be detected only when all of the three are equal to or greater than an arbitrary threshold boundary. In these cases, as described above, priority can be given to the luminance difference between the G value and the B value.
- the threshold boundary line for separation can be determined and drawn by, for example, the operator of the rolling equipment 100 or the employee of the manufacturer of the abnormality detection device from the result diagram.
- mathematical techniques can be used to classify normal and abnormal, for example, using data clustering techniques (data classification techniques).
- data classification techniques data classification techniques.
- FIG. 12 the details of the removal of the reflected light area originating from the lighting device 67 will be described with reference to FIGS. 12 to 14.
- FIG. 12 the details of the removal of the reflected light area originating from the lighting device 67 will be described with reference to FIGS. 12 to 14.
- the abnormal area has the shape of the luminance distribution in the rolling direction (conveyance direction).
- the abnormal area and the area of the reflected light originating from the illumination device 67 are mixed. It is an image in which the reflected light area 1A1 is reflected, and it is desirable to remove the reflected light area originating from the illumination device 67 from the aperture/reflected light area 1A1.
- the RGB colors of the reflected light region originating from the lighting device 67 are close to white, and for example, the RGB colors of the aperture part may be close to yellow
- binarization processing is performed using a luminance threshold
- the detection area setting unit 92A detects the area determined as abnormal using the above-described methods of FIGS. and set. After that, as shown in FIG. 13, a reflected light region setting unit 92B extracts and deletes a relatively long reflected light region 1A2 in the plate width direction derived from the illumination device 67 from the aperture/reflected light region 1A1. As shown in FIG. 14, only the true abnormal area 1A3 (relatively long area in the transport direction) is extracted. Thereafter, the abnormal area setting unit 92C sets the detected true abnormal area 1A3 as an abnormal area, and shifts to the final detection process of whether or not a rolling abnormality is detected.
- the abnormal rolling area may be set by the process shown in FIG. 8 or the like after that.
- the image processing unit 92 preferably removes the area of the reflected light from the lighting device 67 and sets the abnormal area, or the abnormal area detected as the abnormal part of the surface by the method of FIG. If the total value or the value obtained by dividing the total area value by the area of the range 1A of the entire material 1 to be rolled is larger than a certain threshold value ( ⁇ ), it is determined that the material 1 to be rolled has a rolling abnormality. do.
- FIG. 15 is a flow chart of abnormality determination processing in the abnormality detection device of the embodiment.
- step S101 images are acquired by the cameras 81 and 82 (step S101).
- This step S101 corresponds to the image capturing step, and preferably a moving image is captured.
- the brightness reference value setting unit 91 of the image processing computer 90 determines whether or not the material to be rolled 1 is present in the image captured in step S101 (step S102). When it is determined that the material 1 to be rolled exists, the process proceeds to step S103, whereas when it is determined that it does not exist, the process proceeds to step S111.
- step S103 After that, after setting the plate detection area in the luminance reference value setting unit 91 (step S103), the luminance reference value for each target coil is selected (step S104). These steps S103 and S104 correspond to the luminance reference value setting step.
- step S105 the difference from the brightness of the comparison image captured after the brightness reference value selection image is obtained (step S105), and an abnormality candidate is determined (step S106).
- the image processing unit 92 performs processing for removing the reflected light area originating from the illumination device 67 (step S107).
- step S108 the image processing unit 92 executes final abnormality determination processing (step S108), and determines whether or not there is a rolling abnormality such as reduction (step S109).
- step S110 determines whether or not there is a rolling abnormality such as reduction
- step S111 the process proceeds to step S111.
- the display device 95 displays that fact.
- intervention processing for each stand 10, 20, 30, 40, 50, 60, 70 can be automatically executed.
- steps S101 to S111 described above are executed during the rolling of one rolled coil, and the process ends when the rolling of one rolled coil is completed.
- the abnormality detection device of the present embodiment described above is a device for detecting a rolling abnormality on the surface of the material 1 to be rolled by a rolling mill.
- Cameras 81 and 82 for imaging the material 1 to be rolled, and the material 1 to be rolled is extracted from at least one image captured by the cameras 81 and 82.
- the brightness reference value that serves as a reference for comparing the abnormality is obtained each time, and the reference value is obtained only for the comparative image of the material 1 to be rolled of the same coil. Since it is used, it is possible to detect a rolling abnormality on the surface of the material 1 to be rolled in consideration of the disturbance peculiar to the material 1 to be rolled, and to improve the detection accuracy of abnormal rolling of the plate compared with the conventional technique.
- the brightness reference value setting unit 91 divides the brightness data into three components of the R value, the G value, and the B value, and sets two or more of the three components of the reference R value, the reference G value, and the reference B value as the reference values.
- the image processing unit 92 divides the brightness data of the pixels within the range of the material to be rolled 1 into R value, G value, and B value, and determines the reference R value from the R value, the reference G value from the G value, Each luminance difference is obtained by subtracting the reference B value from the B value, and the rolling abnormality is detected based on the relationship between the luminance differences of the two components of each luminance difference. Therefore, it is possible to further improve the abnormality detection accuracy.
- the cameras 81 and 82 are for capturing moving images
- the brightness reference value setting unit 91 extracts images from the moving images, and simply averages or weights the brightness data captured in a plurality of images.
- the luminance reference value By obtaining the luminance reference value by performing moving average processing, it is possible to obtain the luminance reference value calculated based on the luminance data within the range of the rolled material 1 captured in a plurality of continuous images.
- the brightness reference value setting unit 91 adds the brightness data captured in the new image to the brightness data already obtained to recalculate the brightness reference value. Even if there is a fluctuation, the brightness data of the previous image is also used to obtain the brightness reference value, so the abnormality due to the fluctuation is reduced, and the plate is judged to have no abnormality. value can be obtained.
- the brightness reference value setting unit 91 divides the brightness data into three components of R value, G value and B value, and obtains the brightness distribution of each of the R value, G value and B value indicated by the number of measurement points for brightness.
- the luminance of each RGB component that divides the area indicated by the integrated value of each distribution into two, or the luminance that is the largest number of measurement points in each distribution is set as the initial luminance reference value, and further the initial luminance reference value is By setting a specific luminance range including If the brightness data divides the area indicated by the integrated value of the B component brightness data distribution into about half, or if it is around the brightness that records the most plots, the brightness data of the normal surface area that occupies most of the detection range is sufficient. , the luminance (reference value) of the normal surface area of the plate can be obtained with high accuracy by eliminating the influence of the luminance data of the reflected light area reflected on the plate surface by the illumination device 67 in a narrow part. .
- an illumination device 67 for illuminating the material to be rolled 1 is provided, and the image processing unit 92 sets a detection region of the material to be rolled 1, which is an abnormality detection target, from the latest image.
- a reflected light area reflected on the surface of the material to be rolled 1 derived from the illumination light of 67 is set, and the area obtained by removing the reflected light area from the detection area is used as a new detection area, and the newly obtained detection is obtained.
- the region is set as an abnormal region, and the rolling abnormality is detected, thereby removing the reflected light region of the illumination light of the illumination device 67.
- a true surface anomaly can be extracted, and a further improvement in anomaly detection accuracy can be achieved.
- the luminance difference is obtained by subtracting the luminance reference value from the luminance data.
- the image processing unit 92 determines that both of the luminance differences of the two components that form one combination of the R value, the G value, and the B value are equal to or greater than the respective threshold values, and that the luminance differences of the two components that form another combination When both of are equal to or higher than the respective brightness difference thresholds, it is detected as a rolling abnormality, so that two sets of combinations of two components are used, and when both detect an abnormality, it is determined that the surface is abnormal. A normal part is less likely to be erroneously detected as an abnormal part, and a further improvement in abnormality detection accuracy can be achieved.
- the luminance difference data is plotted for each of the R value and the G value, the G value and the B value, and the R value and the B value, the data group with the normal plate and the data group with the abnormal plate form a certain line. There is a tendency to separate at the boundary. Therefore, by using the line as the threshold boundary of the luminance difference of each component, it is possible to achieve further improvement in abnormality detection accuracy.
- the image processing unit 92 determines that the detection result obtained from the luminance difference of two components that form one combination of the R value, the G value, and the B value and the threshold boundary obtained therefrom is abnormal, and If the detection result obtained from the luminance difference of the other two components and the threshold boundary obtained from them is abnormal, it is detected as a rolling abnormality, so that two combinations of two components are used. Since it is determined that the surface is abnormal when an abnormality is detected in both cases, it is difficult to erroneously detect a normal portion as an abnormal portion, and the accuracy of abnormality detection can be further improved.
- the image processing unit 92 uses the luminance difference between the G value and the B value. Since the material to be rolled 1 has a reddish color tone, when the R value is used, the brightness of the normal part and the abnormal part do not change so much, and it may not be suitable for discrimination. Therefore, by using the G value and the B value, the abnormality can be detected without considering the ground color of the material 1 to be rolled.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Textile Engineering (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mechanical Engineering (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
Description
なお、本発明は上記の実施例に限られず、種々の変形、応用が可能なものである。上述した実施例は本発明を分かりやすく説明するために詳細に説明したものであり、必ずしも説明した全ての構成を備えるものに限定されない。
1A…抽出された被圧延材の範囲
1A1…絞り部兼反射光領域
1A2…反射光領域
1A3…異常領域
10…F1スタンド
11,21,31,41,51,61,71…圧下シリンダ
12,22,32,42,52,62,72…荷重検出器
20…F2スタンド
30…F3スタンド
40…F4スタンド
50…F5スタンド
60…F6スタンド
61…圧下シリンダ
65…張力制御用のルーパー
67…照明装置
70…F7スタンド
71…圧下シリンダ
81,82…カメラ
85…通信線
90…画像処理計算機
91…輝度基準値設定部
92…画像処理部
92A…検出領域設定部
92B…反射光領域設定部
92C…異常領域設定部
93…データベース
95…表示装置
100…圧延設備
101…異常検出装置
Claims (15)
- 圧延機により圧延される金属帯板の表面の圧延異常を検出する異常検出装置であって、
前記圧延異常の検出対象である前記金属帯板の圧延中に、前記金属帯板を撮像するカメラと、
前記カメラにより撮像された少なくとも1枚の画像から前記金属帯板を抽出し、前記金属帯板の範囲内の画素の輝度データから板に異常がないと判断される輝度基準値を求める輝度基準値設定部と、
撮像された1枚以上の前記画像の中の1枚以上を比較画像とし、各々の比較画像から前記金属帯板を抽出し、前記金属帯板の範囲内の画素の輝度データと前記輝度基準値との輝度差に基づいて前記圧延異常を検出する画像処理部と、を備える
ことを特徴とする異常検出装置。 - 請求項1に記載の異常検出装置において、
前記輝度基準値設定部は、前記輝度データをR値、G値、B値の3成分に分け、前記輝度基準値として基準R値、基準G値、および基準B値の3成分のうち2成分以上の値を求め、
前記画像処理部は、前記金属帯板の範囲内の画素の輝度データをR値、G値、B値に分け、前記R値から前記基準R値を、前記G値から前記基準G値を、前記B値から前記基準B値を各々減算して各々の前記輝度差を求め、各々の前記輝度差のうち2成分の前記輝度差の関係性に基づいて前記圧延異常を検出する
ことを特徴とする異常検出装置。 - 請求項1または2に記載の異常検出装置において、
前記カメラは、動画を撮像するものであり、
前記輝度基準値設定部は、前記動画から前記画像を抽出し、複数の前記画像に撮像されている前記輝度データを単純平均、または、重み付けをした移動平均の処理を行うことで前記輝度基準値を求める
ことを特徴とする異常検出装置。 - 請求項3に記載の異常検出装置において、
前記輝度基準値設定部は、最新の画像が撮像されるたびに、既に求めていた前記輝度データに新しい画像に撮像されている前記輝度データを加算して前記輝度基準値を求めなおす
ことを特徴とする異常検出装置。 - 請求項2乃至4のいずれか1項に記載の異常検出装置において、
前記輝度基準値設定部は、
前記輝度データをR値、G値、B値の3成分に分け、
輝度に対する計測点数で示される各々のR値、G値、B値の輝度の分布を求め、
各々の前記分布の積分値で示される面積を2分割する各々のRGB成分の輝度、又は各々の前記分布の中で最も多い計測点数である輝度を初期輝度基準値とし、さらにその初期輝度基準値を含む特定の輝度範囲を設定し、その設定された輝度範囲の中から、R値、G値、B値の選定を行って、各々の前記輝度基準値とする
ことを特徴とする異常検出装置。 - 請求項1乃至5のいずれか1項に記載の異常検出装置において、
前記金属帯板を照らす照明装置を更に備え、
前記画像処理部は、最新の画像から、異常の検出対象となる前記金属帯板の検出領域を設定し、前記最新の画像から、前記照明装置の照明光に由来する前記金属帯板の表面に映る反射光領域を設定し、前記検出領域から、前記反射光領域を除去した領域を、改めて検出領域とし、改めて得られた前記検出領域内の画素の輝度データと前記輝度基準値の輝度差の関係性に基づいて、異常領域と設定して、前記圧延異常を検出する
ことを特徴とする異常検出装置。 - 請求項2に記載の異常検出装置において、
前記輝度差は、前記輝度データから前記輝度基準値を引いたものであり、
前記画像処理部は、R値、G値、B値のうち、2成分の前記輝度差の両方が各々の輝度差閾値以上となる場合に前記圧延異常として検出する
ことを特徴とする異常検出装置。 - 請求項7に記載の異常検出装置において、
前記画像処理部は、前記R値、前記G値、前記B値のうち、一つの組合せとなる2成分の前記輝度差の両方が各々の閾値以上となり、且つ、他の組合せとなる2成分の前記輝度差の両方が各々の輝度差閾値以上となる場合に、前記圧延異常として検出する
ことを特徴とする異常検出装置。 - 請求項2に記載の異常検出装置において、
前記金属帯板が映った画像中のR値、G値、B値のうち、1成分の前記輝度差に対する他の1成分の前記輝度差を2成分からなる2次元グラフに複数プロットした分布から、正常値と異常値とを分ける閾値境界が予め求められたデータベースを更に備え、
前記画像処理部は、前記1成分の前記輝度差と前記他の1成分の前記輝度差と前記閾値境界とに基づいて、前記圧延異常を検出する
ことを特徴とする異常検出装置。 - 請求項9に記載の異常検出装置において、
前記画像処理部は、R値、G値、B値のうち、一つの組合せとなる2成分の前記輝度差とそれらから求められた前記閾値境界とから得られた検出結果が異常であり、且つ、他の組合せとなる2成分の前記輝度差とそれらから求められた前記閾値境界とから得られた検出結果が異常となる場合に、前記圧延異常として検出する
ことを特徴とする異常検出装置。 - 請求項7または9に記載の異常検出装置において、
前記画像処理部は、前記G値および前記B値の前記輝度差を用いる
ことを特徴とする異常検出装置。 - 圧延機により圧延される金属帯板の表面の圧延異常を検出する異常検出方法であって、
異常の検出対象である前記金属帯板の圧延中に、前記金属帯板をカメラで撮像する撮像工程と、
前記撮像工程で撮像された少なくとも1枚の画像から前記金属帯板を抽出し、前記金属帯板の範囲内の画素の輝度データから輝度基準値を求める輝度基準値設定工程と、
撮像された1枚以上の前記画像の中の1枚以上を比較画像とし、各々の比較画像から前記金属帯板を抽出し、前記金属帯板の範囲内の画素の輝度データと前記輝度基準値との輝度差に基づいて前記圧延異常を検出する画像処理工程と、を備える
ことを特徴とする異常検出方法。 - 請求項12に記載の異常検出方法において、
前記輝度基準値設定工程では、前記輝度データをR値、G値、B値の3成分に分け、前記輝度基準値として基準R値、基準G値、および基準B値を求め、
前記画像処理工程では、前記金属帯板の範囲内の画素の輝度データをR値、G値、B値に分け、前記R値から前記基準R値を、前記G値から前記基準G値を、前記B値から前記基準B値を各々減算して各々の前記輝度差を求め、各々の前記輝度差のうち2成分の前記輝度差の関係性に基づいて前記圧延異常を検出する
ことを特徴とする異常検出方法。 - 請求項12または13に記載の異常検出方法において、
前記撮像工程では、動画を撮像し、
前記輝度基準値設定工程では、前記動画から前記画像を抽出し、複数の前記画像に撮像されている前記輝度データを単純平均、または、重み付けをした移動平均の処理を行うことで前記輝度基準値を求める
ことを特徴とする異常検出方法。 - 請求項14に記載の異常検出方法において、
前記輝度基準値設定工程では、最新の画像が撮像されるたびに、既に求めていた前記輝度データに、新しい画像に撮像されている前記輝度データを加え、前記輝度基準値を求めなおす
ことを特徴とする異常検出方法。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2021/024917 WO2023276101A1 (ja) | 2021-07-01 | 2021-07-01 | 異常検出装置および異常検出方法 |
JP2021575082A JP7025608B1 (ja) | 2021-07-01 | 2021-07-01 | 異常検出装置および異常検出方法 |
CN202180090197.0A CN116783010A (zh) | 2021-07-01 | 2021-07-01 | 异常检测装置以及异常检测方法 |
EP21948405.2A EP4257258A4 (en) | 2021-07-01 | 2021-07-01 | ANOMALY DETECTION DEVICE AND ANOMALY DETECTION METHOD |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2021/024917 WO2023276101A1 (ja) | 2021-07-01 | 2021-07-01 | 異常検出装置および異常検出方法 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023276101A1 true WO2023276101A1 (ja) | 2023-01-05 |
Family
ID=81124386
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/024917 WO2023276101A1 (ja) | 2021-07-01 | 2021-07-01 | 異常検出装置および異常検出方法 |
Country Status (4)
Country | Link |
---|---|
EP (1) | EP4257258A4 (ja) |
JP (1) | JP7025608B1 (ja) |
CN (1) | CN116783010A (ja) |
WO (1) | WO2023276101A1 (ja) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP7114822B1 (ja) * | 2022-03-25 | 2022-08-08 | Primetals Technologies Japan株式会社 | 画像の補正方法および異常の検出方法、ならびに画像補正装置および異常検出装置 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH06167576A (ja) * | 1992-11-30 | 1994-06-14 | Kawasaki Steel Corp | 付着間紙の検出方法及び帯板処理ライン |
JP2010078574A (ja) * | 2008-09-29 | 2010-04-08 | Toppan Printing Co Ltd | 板状金属表面自動検査装置 |
JP2010085096A (ja) | 2008-09-29 | 2010-04-15 | Toshiba Corp | 表面検査装置 |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5659540B2 (ja) * | 2009-04-15 | 2015-01-28 | Jfeスチール株式会社 | 鋼板表面欠陥検査方法および装置 |
JP6808888B1 (ja) * | 2020-11-05 | 2021-01-06 | Primetals Technologies Japan株式会社 | 不良判断装置および不良判断方法 |
-
2021
- 2021-07-01 WO PCT/JP2021/024917 patent/WO2023276101A1/ja active Application Filing
- 2021-07-01 EP EP21948405.2A patent/EP4257258A4/en active Pending
- 2021-07-01 CN CN202180090197.0A patent/CN116783010A/zh active Pending
- 2021-07-01 JP JP2021575082A patent/JP7025608B1/ja active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH06167576A (ja) * | 1992-11-30 | 1994-06-14 | Kawasaki Steel Corp | 付着間紙の検出方法及び帯板処理ライン |
JP2010078574A (ja) * | 2008-09-29 | 2010-04-08 | Toppan Printing Co Ltd | 板状金属表面自動検査装置 |
JP2010085096A (ja) | 2008-09-29 | 2010-04-15 | Toshiba Corp | 表面検査装置 |
Non-Patent Citations (1)
Title |
---|
See also references of EP4257258A4 |
Also Published As
Publication number | Publication date |
---|---|
CN116783010A (zh) | 2023-09-19 |
EP4257258A4 (en) | 2024-01-24 |
JP7025608B1 (ja) | 2022-02-24 |
EP4257258A1 (en) | 2023-10-11 |
JPWO2023276101A1 (ja) | 2023-01-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110431404B (zh) | 表面缺陷检查方法及表面缺陷检查装置 | |
CN107085714B (zh) | 一种基于视频的森林火灾检测方法 | |
WO2023276101A1 (ja) | 異常検出装置および異常検出方法 | |
CN110458157A (zh) | 一种电力电缆生产过程智能监控系统 | |
CN116862908B (zh) | 一种基于图像处理的金属齿轮啮合缺陷检测方法 | |
CN117670993B (zh) | 一种基于机器视觉的纺织生产加工监控系统 | |
CN115049668A (zh) | 基于特征抽取的钢带辊印识别方法 | |
CN113744326B (zh) | 一种在ycrcb颜色空间中基于种子区域生长法则的火灾检测方法 | |
JP2022181167A (ja) | 鋼板の形状判別方法、形状測定方法、形状制御方法、製造方法、形状判別モデルの生成方法、及び形状判別装置 | |
CN117078679B (zh) | 一种基于机器视觉的散热风扇自动组装线生产检测方法 | |
JP7114822B1 (ja) | 画像の補正方法および異常の検出方法、ならびに画像補正装置および異常検出装置 | |
WO2023276102A1 (ja) | 異常検出装置および異常検出方法 | |
JP2006194869A (ja) | 自動検査装置及び異物検査方法 | |
JP4403036B2 (ja) | 疵検出方法及び装置 | |
CN114240920A (zh) | 一种外观缺陷检测方法 | |
CN112991251B (zh) | 一种表面缺陷检测的方法、装置及设备 | |
TWI454327B (zh) | 鋼帶切尾之偵測方法 | |
EP2957860A1 (en) | Shape measuring device | |
CN117952948B (zh) | 一种线束缺陷检测方法 | |
CN111508397B (zh) | 显示面板的检测方法和显示面板的检测装置 | |
JP2020001065A (ja) | 鋼材非圧下部幅検出装置及びその検出方法 | |
KR100622341B1 (ko) | 슬라브 낙하방지 시스템을 이용한 낙하방지 감시방법 | |
JP2738252B2 (ja) | 画像による帯状材のエッジ検出装置 | |
CN118608525B (zh) | 一种基于图像处理的非标工业品缺陷检测方法 | |
JP6043178B2 (ja) | フラットパネルディスプレイの自動ムラ検出装置および自動ムラ検出方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
ENP | Entry into the national phase |
Ref document number: 2021575082 Country of ref document: JP Kind code of ref document: A |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21948405 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202180090197.0 Country of ref document: CN |
|
ENP | Entry into the national phase |
Ref document number: 2021948405 Country of ref document: EP Effective date: 20230705 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202317048009 Country of ref document: IN |
|
NENP | Non-entry into the national phase |
Ref country code: DE |