Polishing condition determination device, polishing condition determination method, and quality evaluation device

Abstract

To provide a technique that can properly determine the state of polishing of the surface of metal.SOLUTION: A quality evaluation device 4 has a processor 5 for performing: acquisition processing 5a of acquiring a target image to be a determination target from a microscopic image of the surface of metal corroded by a tissue observation corrosion liquid after polishing; image generation processing 5c of generating, from a grayscale image based on the target image, at least one of a bright-side image, in which particles of tissues of the metal are shown as bright objects and the others are shown as dark regions, and a dark-side image, in which the particles of tissues of the metal are shown as dark objects and the others are shown as bright regions; polishing state determination processing 5d of outputting the result of determination as to the polishing state of the surface of the metal on the basis of a value that shows the degree of flatness of the objects in the image generated by the image generation processing 5c.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a polishing condition determining device, a polishing condition determining method, and a quality evaluation device. [Background technology]

[0002] 2. Description of the Related Art Metal materials, particularly steel materials, are often evaluated for quality based on physical properties such as carbon concentration, amount of retained austenite, and hardness.

[0003] For example, the amount of retained austenite is measured by X-ray analysis. Patent Document 1 discloses a technique for determining the amount of retained austenite in a steel material from the results of X-ray analysis. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2018-040770 A Summary of the Invention [Problem to be solved by the invention]

[0005] Incidentally, the quality of metallic materials is also evaluated by observing their structure using a microscope. The metal structure reflects the composition and heat treatment history of the metal material. Therefore, by inputting a microscopic image of the metal structure into a computer and quantifying the characteristics of the metal structure, it is possible to obtain estimated values ​​of the physical properties of the metal material, such as the carbon concentration, amount of retained austenite, and hardness.

[0006] The work of taking the microscopic image of the metal structure includes work of polishing the metal surface, corroding it, observing it under a microscope, etc. Since the work of polishing the metal surface, corroding it, observing it under a microscope, etc. is performed manually by an operator, the polished state or corroded state of the metal surface may be in a good state or in a bad state.

[0007] Here, when attempting to estimate the physical properties of a metal material based on a microscopic image, if the polished condition or corroded state of the metal surface captured in the microscopic image is poor, there is a risk that the accuracy of estimating the physical properties will be reduced. For this reason, it is necessary to appropriately judge the polished state and corroded state of the metal surface captured as a microscopic image. [Means for solving the problem]

[0008] The polishing condition determination device according to the embodiment is an acquisition process for acquiring a target image to be determined from a microscopic image of a metal surface corroded by a corrosive liquid for microstructural observation after polishing; an image generation process for generating at least one of a bright side image in which grains of the metal texture are shown as bright objects and other areas are shown as dark areas, or a dark side image in which grains of the metal texture are shown as dark objects and other areas are shown as bright areas, from a grayscale image based on the target image; a polishing condition determination process that outputs a determination result regarding the polishing condition of the metal surface based on a value indicating the flatness of the object included in the image generated by the image generation process; The apparatus includes a processing unit that executes the above steps.

[0009] A polishing condition determination method according to an embodiment from another viewpoint includes the steps of: A method for determining a polished condition of a metal surface corroded by a corrosive liquid for microstructural observation after polishing, comprising the steps of: Obtaining a target image to be judged from the microscopic image of the metal surface; Generate at least one of a bright side image in which the grains of the metal texture are shown as bright objects and other areas are shown as dark areas, or a dark side image in which the grains of the metal texture are shown as dark objects and other areas are shown as bright areas, from a grayscale image based on the target image; A judgment result regarding the polishing state of the metal surface is output based on a value indicating the flatness of the object contained in the generated image.

[0010] Further, a quality evaluation device according to an embodiment from another viewpoint is A quality evaluation device for evaluating the quality of a metal based on a microscopic image of a metal surface corroded by an etching solution for microstructural observation after polishing, comprising: an acquisition process for acquiring a target image that is to be used for determining the polishing state of the metal surface from the microscopic image; an image generation process for generating at least one of a bright side image in which grains of the metal texture are shown as bright objects and other areas are shown as dark areas, or a dark side image in which grains of the metal texture are shown as dark objects and other areas are shown as bright areas, from a grayscale image based on the target image; a polishing condition determination process that outputs a determination result regarding the polishing condition of a metal surface based on a value indicating the flatness of the object included in the image generated by the image generation process; a quality evaluation process for obtaining a region image of a region to be quality evaluated from the microscope image when the judgment result of the polishing state judgment process satisfies a predetermined condition, generating the bright side image and the dark side image from a grayscale image based on the region image, and obtaining an estimated value of a physical property value of the metal based on the bright side image and the dark side image; The apparatus includes a processing unit that executes the above steps. Effect of the Invention

[0011] According to the present disclosure, the polishing condition of a metal surface can be appropriately determined. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a block diagram showing an example of a quality evaluation system. [Diagram 2] FIG. 2 is a flowchart showing an example of a quality evaluation method using the quality evaluation system. [Diagram 3] FIG. 3 is a diagram for explaining the steps of preparing a sample and polishing and etching the sample. [Figure 4]FIG. 4 is a flowchart showing an example of the quality evaluation process. [Diagram 5] FIG. 5(a) is an example of an image showing the entire imaging target range, and FIG. 5(b) is an example of a region image acquired from the image showing the entire imaging target range. [Figure 6] FIG. 6(a) is a diagram showing a portion of a region image, FIG. 6(b) is a diagram of a dark side image generated from this region image, and FIG. 6(c) is a diagram of a bright side image generated from this region image. [Figure 7] FIG. 7 is a diagram showing an example of a histogram based on the brightness of each pixel constituting a region image and the frequency of occurrence thereof. [Figure 8] FIG. 8 is an explanatory diagram showing one of the dark objects included in the dark side image (FIG. 6(b)). [Figure 9] FIG. 9 is an explanatory diagram showing one of the bright objects included in the bright side image (FIG. 6(c)). [Figure 10] FIG. 10 is a flowchart showing an example of the determination process. [Figure 11] FIG. 11 shows images of cross sections of samples prepared using the evaluation target material, which were mirror-polished and then corroded for different corroding times. [Figure 12] FIG. 12 is a diagram showing histograms based on the luminance values ​​(brightness) of each of these target images. [Figure 13] FIG. 13 is a diagram showing the relationship between the most frequent value of each histogram and the difference between the estimated value and the actually measured value of the carbon concentration using the target image corresponding to each histogram. [Figure 14] FIG. 14 shows images of cross sections of samples prepared using the evaluation target material, which were polished under different polishing conditions and then corroded. [Figure 15] FIG. 15 is a diagram showing the relationship between the aspect ratio of an object included in a bright side image and the difference between the estimated value and the actually measured value of the carbon concentration in each target image. [Figure 16] FIG. 16 is a diagram showing a part of a flowchart of a determination process according to a modified example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] First, the contents of the embodiment will be listed and described. [Outline of the embodiment] (1) An embodiment of a polishing condition determination device includes: an acquisition process for acquiring a target image to be determined from a microscopic image of a metal surface corroded by a corrosive liquid for microstructural observation after polishing; an image generation process for generating at least one of a bright side image in which grains of the metal texture are shown as bright objects and other areas are shown as dark areas, or a dark side image in which grains of the metal texture are shown as dark objects and other areas are shown as bright areas, from a grayscale image based on the target image; a polishing condition determination process that outputs a determination result regarding the polishing condition of the metal surface based on a value indicating the flatness of the object included in the image generated by the image generation process; The apparatus includes a processing unit that executes the above steps.

[0014] If polishing marks are present on the metal surface, the polishing marks will appear as objects in the image generated by the image generation process. Since the polishing marks are linear, the flatness of the object due to the polishing marks is greater than the flatness of the object due to the grain structure. If there are many objects that are caused by polishing marks among the objects included in the image generated by the image generation process, the value indicating the flatness of the object will be relatively large. In other words, the value indicating the flatness of the object indicates the amount of polishing marks. According to the above configuration, the polishing condition of the metal surface is quantitatively determined by outputting a judgment result on the polishing condition of the metal surface based on a value indicating the flatness of the object affected by the presence or absence of polishing marks. As a result, the polishing condition of the metal surface can be appropriately judged.

[0015] (2) In the above-mentioned polishing condition judging device, The value indicating the flatness of the object preferably includes at least one of the aspect ratio, circularity, and length of the major axis of the object. In this case, the aspect ratio, circularity, and / or major axis length of the object can be used to quantitatively determine the polished state of the metal surface.

[0016] (3) In the above-mentioned polishing condition judging device, The processing unit executes, before the image generation process, a corrosion state determination process for determining a corrosion state of the metal surface based on a histogram based on a luminance value representing the brightness of each pixel constituting the target image and the frequency of occurrence of the luminance value, In the image generation process, when a determination result of the corrosion state determination process satisfies a predetermined condition, at least one of the bright side image and the dark side image may be generated. In this case, after the corroded state of the metal surface is quantitatively determined, the polished state of the metal surface can be quantitatively determined.

[0017] (4) A method for determining a polishing condition according to an embodiment from another viewpoint, A method for determining a polished condition of a metal surface corroded by a corrosive liquid for microstructural observation after polishing, comprising the steps of: Obtaining a target image to be judged from the microscopic image of the metal surface; Generate at least one of a bright side image in which the grains of the metal texture are shown as bright objects and other areas are shown as dark areas, or a dark side image in which the grains of the metal texture are shown as dark objects and other areas are shown as bright areas, from a grayscale image based on the target image; A judgment result regarding the polishing state of the metal surface is output based on a value indicating the flatness of the object contained in the generated image.

[0018] According to the above configuration, a judgment result regarding the polishing condition of the metal surface is output based on a value indicating the flatness of the object, which is affected by the presence or absence of polishing marks during polishing, so that the polishing condition of the metal surface can be appropriately judged.

[0019] (5) Furthermore, a quality evaluation device according to an embodiment from another viewpoint is A quality evaluation device for evaluating the quality of a metal based on a microscopic image of a metal surface corroded by an etching solution for microstructural observation after polishing, comprising: an acquisition process for acquiring a target image that is to be used for determining the polishing state of the metal surface from the microscopic image; an image generation process for generating at least one of a bright side image in which grains of the metal texture are shown as bright objects and other areas are shown as dark areas, or a dark side image in which grains of the metal texture are shown as dark objects and other areas are shown as bright areas, from a grayscale image based on the target image; a polishing condition determination process that outputs a determination result regarding the polishing condition of a metal surface based on a value indicating the flatness of the object included in the image generated by the image generation process; a quality evaluation process for obtaining a region image of a region to be quality evaluated from the microscope image when the judgment result of the polishing state judgment process satisfies a predetermined condition, generating the bright side image and the dark side image from a grayscale image based on the region image, and obtaining an estimated value of a physical property value of the metal based on the bright side image and the dark side image; The apparatus includes a processing unit that executes the above steps.

[0020] According to the above-mentioned configuration, since the polished state of the metal surface can be quantitatively determined, the polished state of the metal surface can be appropriately determined. As a result, for example, a microscope image in which the polished state of the metal surface is poor can be prevented from being used in the quality evaluation process, and a decrease in the estimation accuracy of the physical property value can be suppressed.

[0021] [Details of the embodiment] Hereinafter, preferred embodiments will be described with reference to the drawings. [Overall system configuration] FIG. 1 is a block diagram showing an example of a quality evaluation system. The quality evaluation system 1 in FIG. 1 has a function of evaluating the quality of metals based on a microscope image of the metal surface. The quality evaluation system 1 includes a microscope 2 , a camera 3 , and a quality evaluation device 4 . The microscope 2 is a metallurgical microscope capable of observing the surface of a metal. The camera 3 is incorporated in the microscope 2 and has a function of capturing an image observed by the microscope 2. The camera 3 is connected to the quality evaluation device 4, and provides the captured microscope image to the quality evaluation device 4 as image data.

[0022] The quality evaluation device 4 is configured by a computer having a processor 5 and a storage device 6. The quality evaluation device 4 also includes an input / output unit 7 having a function of receiving input from an operator and outputting information and the like to the operator. The input / output unit 7 is, for example, a keyboard, a mouse, a touch panel, a monitor, a speaker, a printer, an indicator, and the like.

[0023] The storage device 6 stores computer programs and the like to be executed by the processor 5. The processor 5 reads the computer programs recorded in a computer-readable non-transitory recording medium such as the storage device 6, thereby executing each process of the processor 5, which will be described below. The storage device 6 also stores a microscopic image 6a provided by the camera 3, threshold data 6b, and a quality assessment model 6c. The microscope image 6 a is image data provided by the camera 3 . The threshold data 6b includes upper and lower limit values ​​Th1 to Th4 that are threshold values ​​used in a corrosion state determination process and a polishing state determination process, which will be described later. The processor 5 refers to the upper and lower limit values ​​Th1 to Th4 of the threshold data 6b as necessary. The quality evaluation model 6c is a model used in a quality evaluation process described later, and includes a carbon concentration estimation model, a retained austenite amount estimation model, and a hardness estimation model.

[0024] The processor 5 executes the above-mentioned computer program to execute an acquisition process 5a, a corrosion state determination process 5b, an image generation process 5c, a polishing state determination process 5d, and a quality evaluation process 5e. Each of these processes will be described later.

[0025] [Quality evaluation method] FIG. 2 is a flowchart showing an example of a quality evaluation method using the quality evaluation system 1. The present system 1 can perform quality evaluation of heat-treated members made of low-carbon steel, low-carbon alloy steel, etc. Examples of low-carbon steel include S10C, S25C, and S40C. Examples of low-carbon alloy steel include SCr415, SCM415, SCM435, SNCM420, and SAE5120.

[0026] In the following, a case where a raceway of a rolling bearing is used as an evaluation target component that is the subject of quality evaluation will be described. This raceway is a component made of low carbon alloy steel or low carbon steel, more specifically, SAE 5120. The raceway is tempered after carburizing and quenching. In this quality evaluation method, estimated values ​​of physical properties such as carbon concentration, amount of retained austenite, hardness, etc. at the carburized portion of the raceway are used for the quality evaluation. Therefore, the carburized layer of the raceway is the region to be evaluated for quality.

[0027] In this quality evaluation method, first, a sample is prepared using a race (step S1 in FIG. 2), and the sample is polished and corroded (step S2 in FIG. 2).

[0028] FIG. 3 is a diagram for explaining the steps of preparing a sample and polishing and etching the sample. In the sample preparation process, first, the race 100, which is the component to be evaluated, is cut with a high-speed cutter or the like to obtain a cut piece 102. The cut piece 102 is embedded in resin 104 to obtain a sample 106. At this time, the cross section 102 a of the cut piece 102 is exposed at the observation surface 106 a of the sample 106 . Next, in a polishing and etching step, the observation surface 106a of the sample 106 is polished by a metal polishing machine or the like. The observation surface 106a is polished by waterproof paper, and then polished by diamond paste or the like. As a result, the observation surface 106a (cross section 102a) is mirror-polished.

[0029] Next, the mirror-polished observation surface 106a is immersed in an etching solution for observing a structure, such as a nital solution (a nitric acid alcohol solution), for a predetermined period of time, to cause the cross section 102a to be corroded (etched).

[0030] Next, the sample 106 is set on the microscope 2, a required portion of the cross section 102a is set in the field of view of the microscope 2, and a microscope image is taken (step S3 in FIG. 2). In this method, since the carburized layer of the bearing ring 100, which is the evaluation target component, is the quality evaluation target, the carburized layer portion of the cross section 102a is placed in the field of view of the microscope 2, and a microscopic image is taken by the camera 3. As a result, a microscopic image of the carburized layer on the cross section 102a is taken. The above steps S1 to S3 are performed by an operator.

[0031] The microscopic image captured by the camera 3 is provided to a quality evaluation device 4 . The quality evaluation device 4, which has received the microscopic image, executes a judgment process (step S4 in FIG. 2). The determination process in step S4 in FIG. 2 is a process for determining the corroded state and polished state of the cross section 102a of the sample 106, which is a metal surface corroded by the corrosive liquid for microstructure observation, and outputting the determination results regarding the corroded state and polished state of the cross section 102a. This determination process will be explained later.

[0032] The quality evaluation device 4 outputs information indicating either "pass" or "fail" as the judgment result regarding the corrosion state and polishing state of the cross section 102a to the operator. If the result of the judgment process output from the quality evaluation device 4 indicates "fail", the operator polishes and corrodes the sample again (step S2 in FIG. 2), and repeats the steps again.

[0033] On the other hand, if the result of the judgment process output from the quality evaluation device 4 indicates "pass", the operator takes a microscope image of the sample 106 (step S6 in FIG. 2). The microscope image captured here is an image used in the quality evaluation process. In the quality evaluation process, an image capturing a metal structure in a range wider than the imaging range of the microscope image may be required. In this case, in step S6, the imaging target range is set to a range wider than the imaging range of the microscope image. This imaging target range is divided into multiple parts according to the imaging range of the microscope image, and multiple microscope images are obtained by capturing the multiple divided ranges. More specifically, the carburized layer exists in a range from the raceway surface 102a1 (FIG. 3) in the cross section 102a to a depth of about 1 mm to 3 mm directly below the raceway surface 102a1. Therefore, the imaging target range is determined so as to include the carburized layer along the contour of the raceway surface 102a1, and the imaging target range is divided along the contour of the raceway surface 102a1 to obtain multiple microscope images.

[0034] In FIG. 2, the microscope image captured in step S6 is provided to the quality evaluation device 4. The processor 5 of the quality evaluation device 4, to which the plurality of microscopic images have been given, stores the plurality of microscopic images in the storage device 6, and executes the quality evaluation process 5e (step S7 in FIGS. 1 and 2).

[0035] FIG. 4 is a flowchart showing an example of the quality evaluation process. When a command to perform quality evaluation processing is given together with a plurality of microscope images, the processor 5 starts the quality evaluation processing 5e, and obtains an area image of the area to be subjected to quality evaluation (step S10 in FIG. 4). The area image is obtained from a plurality of given microscope images. The processor 5 joins the plurality of microscope images together to generate an image showing the entire imaging target range. The processor 5 obtains an image of the carburized layer portion of the cross section 102a as the area image from the image showing the entire imaging target range.

[0036] FIG. 5(a) is an example of an image showing the entire imaging target range, and FIG. 5(b) is an example of a region image acquired from the image showing the entire imaging target range. In FIG. 5(a), the cross section 102a is imaged in a range of several hundreds of μm in the depth direction from the track surface 102a1 along the contour of the track surface 102a1. 5(a), the processor 5 acquires a band-shaped region in the vicinity of a point 50 to 100 μm in the depth direction from the track surface 102a1 as a region image. The width dimension of the region image in the depth direction is about 50 to 100 μm.

[0037] When the region image is acquired, the processor 5 converts the region image into a grayscale image and then performs image processing (step S11 in FIG. 4). The image processing includes pre-processing and processing to generate a bright side image and a dark side image. The pre-processing includes a process for removing noise contained in the area image converted into a grayscale image, and a process for clarifying the contours of the crystal grains captured in the area image.

[0038] Since the region image is a combination of multiple microscope images, the luminance value (brightness) fluctuates periodically. In the noise removal process, noise that appears as such periodic brightness fluctuations is removed by correcting the brightness of each pixel that constitutes the region image. In addition, in the process of clarifying the contours of crystal grains, the brightness of each pixel constituting the region image is corrected so that the slope of the cumulative frequency of the histogram based on the brightness of each pixel and its occurrence frequency becomes constant.

[0039] After completing the above image processing, the processor 5 executes a process for generating a bright side image and a dark side image. FIG. 6(a) is a diagram showing a portion of a region image, FIG. 6(b) is a diagram of a dark side image generated from this region image, and FIG. 6(c) is a diagram of a bright side image generated from this region image. A dark side image is an image in which tissue grains in a region image are shown as dark objects (black objects) and the rest are shown as light regions (white regions). The bright side image is an image in which tissue grains in the area image are shown as bright objects (white objects) and the rest are shown as dark areas (black areas).

[0040] The grains shown as dark objects in the dark-side image (FIG. 6(b)) and the grains shown as bright objects in the bright-side image (FIG. 6(c)) represent different grains. Dark objects (dark regions) are areas that have been corroded by the etching, and light objects (light regions) are areas that have not been corroded by the etching. The bright side image and the dark side image are generated by the processor 5 as follows. First, a histogram is generated from the preprocessed grayscale image (Fig. 6(a)). This histogram is based on the brightness of each pixel that composes the region image and its occurrence frequency. Fig. 7 is a diagram showing an example of the histogram, where the horizontal axis represents brightness (0 to 255) and the vertical axis represents the frequency of occurrence. Fig. 7 also shows a curve L indicating the cumulative frequency for each brightness (each tone).

[0041] In order to generate the bright side image and the dark side image, a first threshold value and a second threshold value are set in advance for the brightness. In the histogram shown in Fig. 7, the brightness at which the cumulative ratio from the dark side (brightness 0) is a first set value is set as the first threshold. The first set value is, for example, a value of 30% or more and 50% or less. For example, when 40% is used as the first set value, the brightness at which the cumulative ratio from the dark side (brightness 0) is 40% (here, the brightness is assumed to be "100") is set as the first threshold in the histogram shown in Fig. 7. In addition, in the histogram shown in Fig. 7, the brightness at which the cumulative ratio from the bright side (brightness 255) is the second set value is set as the second threshold. The second set value is, for example, a value between 10% and 30%. For example, when 20% is used as the second set value, the brightness (here, brightness "180") at which the cumulative ratio from the bright side (brightness 255) is 20% is set as the second threshold in the histogram shown in Fig. 7. The second threshold is a value larger than the first threshold.

[0042] Of the pixels in the pre-processed region image (Fig. 6(a)), pixels whose brightness is equal to or less than the first threshold (brightness equal to or less than 100) are considered to be elements that make up a dark object. In contrast, pixels whose brightness exceeds the second threshold (brightness equal to or greater than 180) are considered to be elements that make up a bright object. In this way, a dark-side image (Fig. 6(b)) is generated from the region image (Fig. 6(a)) in which pixels equal to or less than the first threshold are black and other regions are white. Also, a bright-side image (Fig. 6(c)) is generated from the region image (Fig. 6(a)) in which areas that exceed the second threshold are white and other regions are black. In this manner, the processor 5 generates a bright-side image and a dark-side image based on the region image.

[0043] After generating the bright side image and the dark side image, the processor 5 calculates the feature amount based on the bright side image and the dark side image (step S12 in FIG. 4). As shown in Fig. 6(b), the dark side image is an image in which tissue grains are shown as dark objects (black objects). The processor 5 obtains dark side feature amounts of a plurality of objects included in the dark side image (Fig. 6(b)). As shown in Fig. 6(c), the bright side image is an image in which tissue grains are shown as bright objects (white objects). Processor 5 obtains bright side feature amounts of multiple objects included in the bright side image (Fig. 6(c)).

[0044] FIG. 8 is an explanatory diagram showing one of the dark objects included in the dark side image (FIG. 6(b)). FIG. 9 is an explanatory diagram showing one of the bright objects included in the bright side image (FIG. 6(c)). Multiple objects are extracted from each of the bright side image and the dark side image. The extracted object is a mass portion having a predetermined area. Note that objects whose area is smaller than a threshold value and objects whose area is larger than a threshold value are excluded from the objects to be extracted. Dark side features of each object extracted from the dark side image are calculated. Bright side features of each object extracted from the bright side image are calculated.

[0045] Examples of dark side features include the major axis, minor axis, angle, circularity, maximum brightness, skewness, pixel count, aspect ratio, and tone density of a dark object. Examples of bright side features include the maximum brightness, major axis, angle, circularity, median brightness, kurtosis, skewness, pixel count, and aspect ratio of a bright object. As shown in Figs. 8 and 9, the long axis is the maximum dimension of the object, and the short axis is the maximum dimension in the direction perpendicular to the long axis. The angle is the inclination angle of the long axis with respect to the width direction. The circularity is the calculated value of "4π x (area of ​​object) / (perimeter of object)^2". The aspect ratio is the calculated value of "long axis / short axis". The concentricity is the calculated value of "(area of ​​object) / (area of ​​the smallest rectangle that surrounds the object)". The median value of brightness is as follows: "When a histogram is created with the horizontal axis representing brightness and the vertical axis representing frequency for an object to be characterized in a grayscale image (Fig. 6(a)), the median value of the histogram is the maximum value of the histogram." The maximum value of brightness is as follows: "When the histogram is created, the maximum value of the histogram is the maximum value." The skewness and kurtosis are values ​​calculated from the shape of the histogram.

[0046] After calculating the bright-side feature amount and the dark-side feature amount based on the bright-side image and the dark-side image, the processor 5 normalizes the bright-side feature amount and the dark-side feature amount of each of the multiple objects, and calculates estimated values ​​of physical property values ​​such as the carbon concentration, the amount of retained austenite, and hardness based on the normalized bright-side feature amount and dark-side feature amount (step S13 in FIG. 4). The processor 5 refers to the quality assessment model 6c in the storage device 6 and calculates an estimated value of the physical property value.

[0047] As described above, the quality assessment model 6c includes a carbon concentration estimation model, a retained austenite amount estimation model, and a hardness estimation model. Each of these models is an arithmetic expression for calculating an estimated value of the carbon concentration, an estimated value of the amount of retained austenite, and an estimated value of the hardness based on the bright side feature amount and the dark side feature amount. Each model is a model that is machine-learned using training data in which the bright side feature amount and the dark side feature amount are associated with each estimated value. The processor 5 uses the bright side feature amount and the dark side feature amount obtained in step S12 in FIG. 4 as a data set, calculates each estimated value, and outputs it via the input / output unit 7, thereby completing the quality evaluation process.

[0048] [Regarding the judgment process] In FIG. 2, the quality evaluation device 4, which has been provided with the microscope image captured in step S3, stores the microscope image in the storage device 6 and executes a judgment process (step S4 in FIG. 2). FIG. 10 is a flowchart showing an example of the determination process. As described above, the judgment process is a process of judging the corroded state and polished state of the cross section 102a of the sample 106, which is a metal surface corroded by an etching solution for microstructural observation, and outputting judgment results regarding the corroded state and polished state of the cross section 102a.

[0049] In the determination process, first, the processor 5 executes the acquisition process 5a (FIG. 1) to acquire a target image to be determined from a given microscope image (step S21 in FIG. 10). The target image is an image that is to be used to judge the corrosion state and polishing state of the cross section 102a. The target image may be an image of a portion of cross section 102a included in the microscope image, but it is preferable to obtain an image of the carburized portion of cross section 102a as the target image, similar to the area image in step S10 in FIG.

[0050] When the target image is acquired, the processor 5 executes the corrosion state determination process 5b (FIG. 1), obtains a determination value from a histogram based on the luminance value (lightness or darkness) representing the brightness of each pixel constituting the target image and its occurrence frequency, and compares the obtained determination value with a threshold value set for the determination value. In this embodiment, the determination value is the mode that can be obtained from the histogram (step S22 in FIG. 10), and the obtained mode is compared with the mode threshold value (upper limit Th1, lower limit Th2) set for the mode (step S23). More specifically, the processor 5 determines whether or not the mode is equal to or greater than the lower limit Th2 and equal to or less than the upper limit Th1 (step S23).

[0051] The upper limit value Th1 and the lower limit value Th2 set for the mode are set according to the material of the evaluation target component. For example, in the case of the material of the evaluation target component in this embodiment (low carbon alloy steel or low carbon steel), the upper limit value Th1 is set to 185 and the lower limit value Th2 is set to 70. The upper limit value Th1 and the lower limit value Th2 are set as follows.

[0052] That is, a plurality of target images of the cross section 102a with different corrosion states were obtained, and the most frequent value of the histogram based on the brightness value of each target image was obtained. Furthermore, an estimated value of the carbon concentration was obtained using each target image, and the difference between the actual value and the estimated value of the carbon concentration for each target image was obtained, and an upper limit value Th1 and a lower limit value Th2 were set based on the difference between each target image and the most frequent value of the histogram corresponding to each target image.

[0053] FIG. 11 shows images of cross sections 102a of samples 106 made from the evaluation target material, which were mirror-polished and then corroded for different corroding times. Each target image is an image of the cross section 102a of the same sample 106 that has been mirror-polished under the same conditions and corroded for a different corroding time. A 3% Nital solution was used for the corrosion, and the target images were obtained with the luminance of the light source of the microscope 2 kept constant when obtaining each image. In Fig. 11, target images are shown, in order from the left side of the page, at corrosion times of 1 second, 3 seconds, 5 seconds, 7 seconds, and 10 seconds. As shown in Fig. 11, the longer the corrosion time, the more the corrosion of the cross section 102a progresses, and the texture grains in the cross section 102a appear darker.

[0054] Fig. 12 is a diagram showing histograms based on the luminance values ​​(brightness) of each of these target images. In Fig. 12, the horizontal axis indicates brightness, which is the luminance value of each pixel that constitutes the target image, and the vertical axis indicates the frequency of occurrence of each brightness. As mentioned above, brightness has 256 gradations from 0 to 255. In FIG. 12, histogram H1 corresponds to a target image with a corrosion time of 1 second, histogram H3 corresponds to a target image with a corrosion time of 3 seconds, histogram H5 corresponds to a target image with a corrosion time of 5 seconds, histogram H7 corresponds to a target image with a corrosion time of 7 seconds, and histogram H10 corresponds to a target image with a corrosion time of 10 seconds. In FIG. 12, the mode of histogram H1 is 189, the mode of histogram H3 is 183, the mode of histogram H5 is 133, the mode of histogram H7 is 73, and the mode of histogram H10 is 23.

[0055] In this manner, multiple target images of the cross-section 102a with different corrosion states (target images with different histogram modes) were obtained, and quality assessment process 5e (FIG. 1) was performed using each target image to obtain an estimate of the carbon concentration for each target image. Next, the carbon concentration of the cross section 102a was measured by quantitative analysis using an EPMA, the difference between the measured value and each estimated value was obtained, and for each histogram (each target image), the difference between the measured value and the estimated value was associated with the mode, and an upper limit Th1 and a lower limit Th2 for the mode were set. The measured carbon concentration of the cross section 102a (in the carburized portion) of the target image shown in FIG. 12 was 0.8.

[0056] Fig. 13 is a diagram showing the relationship between the mode of each histogram and the difference between the estimated and measured carbon concentration values ​​for the target image corresponding to each histogram. In Fig. 13, the horizontal axis shows the mode of the histogram, and the vertical axis shows the ratio (%) of the difference between the estimated and measured carbon concentration values ​​to the measured value.

[0057] In FIG. 13, the group of black circles P1 with a mode value of 189 indicates the difference due to the target image corresponding to histogram H1. The group of black circles P3 with a mode value of 183 indicates the difference due to the target image corresponding to histogram H3. The group of black circles P5 with a mode value of 133 indicates the difference due to the target image corresponding to histogram H5. The group of black circles P7 with a mode value of 73 indicates the difference due to the target image corresponding to histogram H7. The group of black circles P10 with a mode value of 23 indicates the difference due to the target image corresponding to histogram H10.

[0058] As shown in FIG. 13, the differences between the target images corresponding to histograms H3, H5, and H7 are within ±0.1%, while the differences between the target images corresponding to histograms H1 and H10 exceed ±0.1%. Based on this result, the upper limit Th1 for the mode is set to 185, and the lower limit Th2 is set to 70. As a result, if the mode of a histogram based on the luminance values ​​of a target image is equal to or greater than the lower limit Th2 and equal to or less than the upper limit Th1, the difference between the estimated carbon concentration from the target image and the actual measured value will be within ±0.1%.

[0059] In step S23 in FIG. 10, if it is determined that the most frequent value of the histogram based on the brightness values ​​of the target image acquired in step S21 in FIG. 10 is not between the upper limit value Th1 and the lower limit value Th2, the processor 5 executing the corrosion state determination process 5b (FIG. 1) proceeds to step S25 in FIG. 10, outputs information indicating “fail” to the operator via the input / output unit 7, and ends the determination process. In this case, the judgment result is "fail", so as described in step S5 in FIG. 2, the operator polishes and corrodes the sample again (step S2 in FIG. 2), and sequentially redoes the work.

[0060] On the other hand, if it is determined that the most frequent value of the histogram based on the luminance values ​​of the target image acquired in step S21 in FIG. 10 is equal to or greater than the lower limit Th2 and equal to or less than the upper limit Th1, the processor 5 proceeds to step S24 in FIG. In this case, the processor 5 determines the corrosion state of the cross section 102a of the target image acquired in step S21 in Fig. 10 as "pass". If the determination result in the subsequent step S27 in Fig. 10 is positive, the processor 5 outputs information indicating "pass" to the operator.

[0061] The processor 5 of this embodiment outputs information indicating "pass" or information indicating "fail" to the operator according to the most frequent value as the judgment value in step S23 in Fig. 10. That is, in the corrosion state judgment process 5b, the processor 5 outputs a judgment result regarding the corrosion state of the cross section 102a based on the most frequent value (judgment value) obtained from a histogram of the luminance values ​​representing the brightness of each pixel constituting the target image and their occurrence frequency.

[0062] When the cross section 102a is corroded by the tissue observation corrosive liquid, a brightness (darkness) contrast corresponding to the tissue is generated on the cross section 102a. Therefore, the luminance value of each pixel constituting the target image is affected by the state of corrosion. Therefore, according to the above configuration, the corrosion state of the cross section 102a is judged based on the most frequent value obtained from a histogram based on the brightness value affected by the corrosion state, so that it is possible to output a quantitative judgment result of the corrosion state of the cross section 102a. As a result, it is possible to appropriately judge the corrosion state of the cross section 102a.

[0063] In addition, the brightness of the light source of the microscope 2 may also affect the brightness value of each pixel that constitutes the target image, but in this embodiment, the corrosion state of the cross section 102a can be determined taking into account the influence of the brightness of the light source.

[0064] In addition, in the above configuration, the corrosion state of the cross section 102a is determined by comparing the mode obtained from the histogram with the upper limit value Th1 and the lower limit value Th2, so that the corrosion state can be appropriately determined by setting the upper limit value Th1 and the lower limit value Th2. In other words, if the upper limit value Th1 and the lower limit value Th2 are set so that the mode is suitable for the quality evaluation process 5e (FIG. 1), it can be determined whether the corrosion state is suitable for the quality evaluation process 5e.

[0065] When the process proceeds to step S24 in FIG. 10, the processor 5 executes the image generation process 5c (FIG. 1) to generate a bright side image based on the target image acquired in step S21 in FIG. 10 (step S24 in FIG. 10). The bright side image is the same image as the bright side image generated in the image processing of step S11 in FIG. The processor 5 generates a bright side image by the same process as the image process in step S11 in FIG. 4 (step S24 in FIG. 10). In this embodiment, a bright side image is generated in step S24 in FIG. 10, but a dark side image may be generated instead of the bright side image.

[0066] When the bright side image is generated, the processor 5 executes the polishing condition determination process 5d and obtains the aspect ratio as a value indicating the flatness of the plurality of objects included in the bright side image generated by the image generation process 5c (step S26). The processor 5, for example, normalizes the aspect ratio of each of the plurality of objects and performs processing using the normalized aspect ratio. Processor 5 compares the obtained aspect ratio with the upper limit set for the aspect ratio (step S27). More specifically, the processor 5 determines whether or not the aspect ratio is equal to or smaller than the upper limit Th3 (step S27).

[0067] The upper limit Th3, which is a flatness threshold value set for the aspect ratio, is set as follows. That is, a plurality of target images of the cross-section 102a with different polishing conditions were obtained, and the aspect ratio of the object included in the bright side image of each target image was obtained. Furthermore, an estimated value of the carbon concentration was obtained using each target image, and the difference between the actual value and the estimated value of the carbon concentration for each target image was obtained, and the upper limit value Th3 was set based on the difference between each target image and the aspect ratio of the object included in the bright side image of each target image.

[0068] FIG. 14 shows images of cross sections 102a of samples 106 made from the evaluation target material, which were polished under different polishing conditions and then corroded. Each of the target images G1, G2, G3, G4, and G5 was acquired by polishing the sample 106 under the conditions shown below, immersing the cross section 102a in a 3% Nital solution for 5 seconds, and keeping the brightness of the light source of the microscope 2 constant.

[0069] Polishing conditions Target image G1: Polishing with waterproof sandpaper (220 grit 10 seconds, 400 grit 10 seconds, 800 grit 10 seconds, 2000 grit 10 seconds) → Diamond polishing 30 seconds Target image G2: Polishing with waterproof sandpaper (220 grit 10 seconds, 400 grit 10 seconds, 800 grit 10 seconds, 2000 grit 10 seconds) → Diamond polishing 120 seconds → Waterproof sandpaper 2000 grit 10 seconds → Diamond polishing 120 seconds Target image G3: Polishing with waterproof sandpaper (220 grit 10 seconds, 400 grit 10 seconds, 800 grit 10 seconds, 2000 grit 10 seconds) → Diamond polishing 10 seconds Target image G4: Sanding with waterproof sandpaper (220 grit 10 seconds, 400 grit 10 seconds, 800 grit 10 seconds, 2000 grit 10 seconds) Target image G5: Sanding with waterproof sandpaper (220 grit 10 seconds, 400 grit 10 seconds, 800 grit 10 seconds, 2000 grit 3 seconds)

[0070] The polishing conditions for target image G1 are normal polishing conditions. The polishing conditions for target image G2 are diamond polishing, then polishing again with waterproof paper #2000, and then diamond polishing, intentionally creating minute hole-like defects called pits in the cross section 102a. The polishing conditions for target image G3 are shorter than the normal polishing conditions for diamond polishing. The polishing conditions for target image G4 are shorter than the normal polishing conditions for diamond polishing. The polishing conditions for target image G5 are shorter than the normal polishing conditions for diamond polishing, and the polishing time with waterproof paper #2000 is also shorter. Target images G3, G4, and G5 are conditions that reproduce a state in which polishing is insufficient.

[0071] Here, the polished state refers to the properties of the polished surface due to polishing marks and the like, and cross sections 102a with different polished states are obtained depending on the above-mentioned polishing conditions. As described above, a plurality of target images of the cross section 102a having different polishing conditions were obtained, and the aspect ratios of a plurality of objects included in the bright side image of each target image were calculated. Furthermore, a quality assessment process 5e (FIG. 1) was performed using each target image to obtain an estimate of the carbon concentration for each target image. Next, the difference between the actual measurement value and each estimated value of the carbon concentration was calculated, and for each target image, the difference between the actual measurement value and the estimated value was associated with the aspect ratio, and an upper limit value Th3 for the aspect ratio was set.

[0072] Fig. 15 is a diagram showing the relationship between the aspect ratio of an object included in a bright side image and the difference between the estimated value and the actual measured value of the carbon concentration in each target image. In Fig. 15, the horizontal axis shows the aspect ratio of the object included in the bright side image, and the vertical axis shows the ratio of the difference between the estimated value and the actual measured value of the carbon concentration to the actual measured value.

[0073] 15, black dots P10 indicate the aspect ratio and difference due to the target image G5, black dots P11 indicate the aspect ratio and difference due to the target image G4, and black dots P12 indicate the aspect ratio and difference due to the target images G1, G2, and G3.

[0074] 15, the aspect ratio of the target image G5 is about 4. Furthermore, the difference between the actual measured value and the estimated value of the carbon concentration in the target image G5 is 0.1% or more. The aspect ratio of the target image G4 is about 3. Furthermore, the difference between the actual measured value and the estimated value of the carbon concentration in the target image G4 is 0.1% or more. Moreover, the aspect ratio of the target images G1, G2, and G3 is about 2. Moreover, the difference between the actual measured value and the estimated value of the carbon concentration in the target images G1, G2, and G3 is 0.05% or less.

[0075] Based on this result, the upper limit Th3 for the aspect ratio of the object included in the bright side image is set to 2.5. In other words, the allowable range of the aspect ratio is set to within 2.5. As a result, if the aspect ratio of an object included in a target image is equal to or smaller than this upper limit Th3, the difference between the estimated carbon concentration from the target image and the actual measured value will be 0.05% or less.

[0076] In step S27 in FIG. 10, if it is determined that the aspect ratio of the object contained in the target image acquired in step S21 in FIG. 10 is not less than or equal to upper limit value Th3, processor 5 proceeds to step S25 in FIG. 10, outputs information indicating “fail” to the worker via input / output unit 7, and terminates the determination process. In this case, the judgment result is "fail", so as described in step S5 in FIG. 2, the operator polishes and corrodes the sample again (step S2 in FIG. 2), and sequentially redoes the work.

[0077] On the other hand, if it is determined that the aspect ratio of the object contained in the target image is equal to or less than the upper limit value Th3, the processor 5 proceeds to step S28 in FIG. 10, outputs information indicating “pass” to the worker via the input / output unit 7, and terminates the determination process. In this case, the judgment result is “pass”, so as explained in step S5 in FIG. 2, the worker captures a microscopic image for the quality evaluation process (step S6 in FIG. 2), and then the processor 5 of the quality evaluation device 4, which has been given the microscopic image, executes the quality evaluation process 5e (step S7 in FIGS. 1 and 2).

[0078] As described above, the processor 5 performs a judgment process to judge the corrosion state and polishing state of the cross section 102a, and outputs information indicating "pass" or "fail" regarding the corrosion state and polishing state of the cross section 102a to the operator. As a result, if the corroded and polished state of the cross-section 102a is good, the quality evaluation process 5e is executed, and if the corroded and polished state of the cross-section 102a is not good, information indicating "fail" is output, allowing the operator to polish and corrode the sample again, and preventing the quality evaluation process 5e from being executed using a cross-section 102a that is not good in corroded and polished state.

[0079] In the polishing condition determination process 5d (step S27 in Figs. 1 and 10), the processor 5 of this embodiment outputs information indicating "pass" or "fail" to the operator according to the aspect ratio of the object. That is, in the polishing condition determination process 5d, the processor 5 outputs a determination result regarding the polishing condition of the cross section 102a based on the aspect ratio, which is a value indicating the flatness of the object included in the bright side image generated by the image generation process 5c. If polishing marks are present on the cross section 102a, the polishing marks will appear as objects in the bright side image. Since the polishing marks are linear, the aspect ratio of the object due to the polishing marks will be larger than the aspect ratio of the texture grains. If many objects due to polishing marks are present in the bright side image generated by the image generation process 5c (FIG. 1), the aspect ratio of the object will be relatively large. In other words, the aspect ratio of the object indicates the amount of polishing marks. According to the above configuration, the polishing condition of the cross section 102a is quantitatively determined by outputting the judgment result on the polishing condition of the cross section 102a based on the aspect ratio of the object that is affected by the presence or absence of polishing marks during polishing. As a result, the polishing condition of the cross section 102a can be appropriately judged.

[0080] In this embodiment, the processor 5 executes a corrosion state determination process 5b for determining the corrosion state of the cross section 102a based on the luminance value representing the brightness of each pixel constituting the target image and the most frequent value (determination value) obtained from a histogram based on the frequency of occurrence of the luminance value, and executes an image generation process 5c and a polishing state determination process 5d when the determination result of the corrosion state determination process 5b is not "fail" (when the determination result of the corrosion state determination process 5b is "pass"). This allows the corrosion state of the cross section 102a to be quantitatively evaluated, and then the polishing state of the cross section 102a to be quantitatively evaluated.

[0081] Furthermore, according to the above configuration, if the judgment results of both the corrosion state judgment process 5b and the polishing state judgment process 5d are not “fail” (if they are “pass”), the processor 5 executes the quality evaluation process 5e, acquires an area image from the microscope image, and generates from the grayscale image based on the area image a bright side image in which the grains of the tissue of the cross section 102a are shown as bright objects and everything else is shown as dark areas, and a dark side image in which the grains of the tissue of the cross section 102a are shown as dark objects and everything else is shown as bright areas, and obtains an estimate of the physical property values ​​of the cut piece 102 based on the bright side image and the dark side image.

[0082] According to the above-mentioned configuration, the corrosion state and polishing state of the cross section 102a can be quantitatively determined, and therefore the corrosion state and polishing state of the cross section 102a can be appropriately determined. As a result, for example, a microscope image in which the corrosion state or polishing state of the cross section 102a is poor can be prevented from being used in the quality evaluation process, and a decrease in the estimation accuracy of the physical property value can be suppressed.

[0083] [Modifications] FIG. 16 is a diagram showing a part of a flowchart of a determination process according to a modified example. The processor 5 of this modified example differs from the above embodiment in that in the corrosion state judgment process 5b (step S23 in Figures 1 and 10), in addition to the most frequent value obtained from a histogram based on the luminance values ​​representing the brightness of each pixel constituting the target image, the standard deviation obtained from the histogram is used as the judgment value. Note that Fig. 16 shows only steps S22 and S23 which are different from Fig. 10. The other steps S21, and S24 to S28 are the same as those in Fig. 10.

[0084] In this modification, the processor 5 obtains the standard deviation as well as the mode of the histogram in step S22 in FIG. Next, in the corrosion state determination process 5b, the processor 5 determines whether or not the mode is equal to or greater than the lower limit Th2 and equal to or less than the upper limit Th1, and the standard deviation is equal to or greater than the lower limit Th4 (step S23 in FIG. 16). If the mode is not greater than or equal to the lower limit Th2 and less than or equal to the upper limit Th1, or if the standard deviation is not greater than or equal to the lower limit Th4, the processor 5 proceeds to step S25 (Figure 10), outputs information indicating "fail" to the operator via the input / output unit 7, and ends the judgment process.

[0085] On the other hand, if the mode is equal to or greater than the lower limit Th2 and equal to or less than the upper limit Th1, and the standard deviation is equal to or greater than the lower limit Th4, the processor 5 proceeds to step S24 (FIG. 10) and continues the process.

[0086] The lower limit value Th4, which is a standard deviation threshold value set for the standard deviation, is set according to the material of the evaluation target component, similar to the mode. For example, in the case of the material of the evaluation target component in this embodiment (low carbon alloy steel or low carbon steel), the lower limit value Th4 is set to 15. The lower limit value Th4 is set as follows.

[0087] That is, the standard deviation is calculated for each of the histograms H1, H3, H5, H7, and H10 in FIG. 12, and a lower limit Th4 is set for each histogram based on the standard deviation and the difference between the estimated value and the actually measured value of the carbon concentration from the target image. In FIG. 12, the standard deviation of histogram H1 is 10.56, the standard deviation of histogram H3 is 15.27, the standard deviation of histogram H5 is 20.39, the standard deviation of histogram H7 is 24.19, and the standard deviation of histogram H10 is 15.45. Based on this result, the lower limit Th4 for the standard deviation is set to 15.

[0088] The smaller the standard deviation, the narrower the peak width of the histogram. Therefore, it can be said that the smaller the standard deviation, the smaller the variation in brightness gradation contained in the target image, and the smaller the amount of data represented by gradation. Therefore, by setting a lower limit value for the standard deviation, it is possible to relatively increase the variation in brightness contained in the target image, and to ensure a certain amount of data represented by gradation, and the polishing state of the cross section 102a can be more appropriately determined by the polishing state determination process 5d.

[0089] In this embodiment, the judgment values ​​include the mode and standard deviation of the histogram, and the use of two judgment values ​​from different viewpoints makes it possible to more appropriately judge the corrosion state of the cross section 102a.

[0090] In the above embodiment, only the most frequent value obtained from a histogram based on the luminance values ​​representing the brightness of each pixel constituting the target image is used as the judgment value, and in the above modified example, the most frequent value and the standard deviation obtained from the histogram are used as the judgment value, but it is also possible to use only the standard deviation as the judgment value.

[0091] 〔others〕 The embodiments disclosed herein are illustrative in all respects and are not restrictive. For example, the processor 5 of the above embodiment uses the aspect ratio as a value indicating the flatness of an object included in the bright side image in the polishing condition determination process 5d (step S27 in Figs. 1 and 10), but instead of the aspect ratio, the circularity of the object or the long axis of the object may be used. Also, multiple values ​​selected from these may be used as values ​​indicating the flatness of the object in the polishing condition determination process 5d. The long axis of an object due to polishing marks is much larger than the long axis of an object of texture grains. Therefore, the presence of polishing marks can be determined based on the long axis of the object, which is a value indicating the flatness of the object.

[0092] In addition, in the above embodiment, an example was given of the case where the processor 5 of the quality evaluation device 4 executes the acquisition process 5a, the corrosion state determination process 5b, the image generation process 5c, the polishing state determination process 5d, and the quality evaluation process 5e, but the quality evaluation device 4 can also be a determination device that determines the corrosion state and polishing state by having the processor 5 execute each process other than the quality evaluation process 5e. Moreover, by making the processor 5 execute only the acquisition process 5a, the image generation process 5c, and the polished condition determination process 5d, the quality evaluation device 4 can also be used as a polished condition determination device. In this case, in the polishing condition determination process 5d, the processor 5 outputs information indicating "pass" or information indicating "fail" to the operator based on the aspect ratio of the object.

[0093] The scope of the present invention is not limited to the above-described embodiment, but includes all modifications within the scope of the equivalents of the configurations described in the claims. [Explanation of symbols]

[0094] 1. Quality Evaluation System 2. Microscope 3. Camera 4. Quality evaluation equipment 5 Processors 5a Acquisition process 5b Corrosion state determination process 5c Image generation processing 5d Polishing condition judgment process 5e Quality Evaluation Process 6 Storage device 6a Microscopic image 6b Threshold Data 6c Quality assessment model 7 Input / output section 100 bearing ring 102 Cut piece 102a cross section 102a1 Raceway surface 106 Samples 106a Observation surface 255 Brightness G1 Target image G2 Target image G3 Target image G4 Target image G5 Target Image H1 Histogram H10 Histogram H3 Histogram H5 Histogram H7 Histogram L curve P1 Black circle group P10 Black circle group P11 Black circle group P12 Black circle group P3 Black circle group P5 Black circle group P7 Black circle group

Claims

1. an acquisition process for acquiring a target image to be determined from a microscopic image of a metal surface corroded by a corrosive liquid for microstructural observation after polishing; a corrosion state determination process for determining a corrosion state of the metal surface based on a histogram based on a luminance value representing the brightness of each pixel constituting the target image and the frequency of occurrence of the luminance value; When the judgment result of the corrosion state judgment process satisfies a predetermined condition, an image generation process is performed to generate at least one of a bright side image in which the grains of the metal structure are shown as bright objects and other areas are shown as dark areas from a grayscale image based on the target image, or a dark side image in which the grains of the metal structure are shown as dark objects and other areas are shown as bright areas; a polishing condition determination process that outputs a determination result regarding the polishing condition of the metal surface based on a value indicating the flatness of the object included in the image generated by the image generation process; A processing unit for executing Polishing condition judgment device.

2. The value indicating the flatness of the object includes at least one of the aspect ratio, the circularity, and the length of the major axis of the object. The polishing condition determining device according to claim 1 .

3. A method for determining a polished condition of a metal surface corroded by a corrosive liquid for microstructural observation after polishing, comprising the steps of: Obtaining a target image to be judged from the microscopic image of the metal surface; determining a corrosion state of the metal surface based on a histogram based on a luminance value representing the brightness of each pixel constituting the target image and the frequency of occurrence of the luminance value; When the corrosion state determination result satisfies a predetermined condition, at least one of a bright side image in which the grains of the metal structure are shown as bright objects and other areas are shown as dark areas, or a dark side image in which the grains of the metal structure are shown as dark objects and other areas are shown as bright areas is generated from the grayscale image based on the target image, A judgment result regarding the polishing state of the metal surface is output based on a value indicating the flatness of the object contained in the generated image. Method for determining polishing condition.

4. A quality evaluation device for evaluating the quality of a metal based on a microscopic image of a metal surface corroded by an etching solution for microstructural observation after polishing, comprising: an acquisition process for acquiring a target image that is to be used for determining the polishing state of the metal surface from the microscopic image; a corrosion state determination process for determining a corrosion state of the metal surface based on a histogram based on a luminance value representing the brightness of each pixel constituting the target image and the frequency of occurrence of the luminance value; When the judgment result of the corrosion state judgment process satisfies a predetermined condition, an image generation process is performed to generate at least one of a bright side image in which the grains of the metal structure are shown as bright objects and other areas are shown as dark areas from a grayscale image based on the target image, or a dark side image in which the grains of the metal structure are shown as dark objects and other areas are shown as bright areas; a polishing condition determination process that outputs a determination result regarding the polishing condition of a metal surface based on a value indicating the flatness of the object included in the image generated by the image generation process; a quality evaluation process for obtaining an area image of an area to be quality evaluated from the microscope image when the judgment result of the polishing state judgment process satisfies a predetermined condition, generating the bright side image and the dark side image from a grayscale image based on the area image, and determining physical property values ​​of the metal based on the bright side image and the dark side image; A processing unit for executing Quality assessment device.

Images