WO2023228572A1 - 組織写真評価方法、組織写真評価装置、撮影装置及びプログラム - Google Patents
組織写真評価方法、組織写真評価装置、撮影装置及びプログラム Download PDFInfo
- Publication number
- WO2023228572A1 WO2023228572A1 PCT/JP2023/013410 JP2023013410W WO2023228572A1 WO 2023228572 A1 WO2023228572 A1 WO 2023228572A1 JP 2023013410 W JP2023013410 W JP 2023013410W WO 2023228572 A1 WO2023228572 A1 WO 2023228572A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- tissue
- deviation
- quantitative value
- phase
- pass
- Prior art date
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 113
- 238000003384 imaging method Methods 0.000 title claims abstract description 76
- 238000004364 calculation method Methods 0.000 claims abstract description 149
- 230000000007 visual effect Effects 0.000 claims abstract description 58
- 239000007769 metal material Substances 0.000 claims abstract description 51
- 230000003287 optical effect Effects 0.000 claims description 8
- 238000000034 method Methods 0.000 description 69
- 239000013078 crystal Substances 0.000 description 53
- 239000002184 metal Substances 0.000 description 22
- 238000005498 polishing Methods 0.000 description 15
- 229910000831 Steel Inorganic materials 0.000 description 12
- 230000006870 function Effects 0.000 description 12
- 238000012545 processing Methods 0.000 description 12
- 239000010959 steel Substances 0.000 description 12
- 239000000463 material Substances 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 229910000859 α-Fe Inorganic materials 0.000 description 8
- 238000003860 storage Methods 0.000 description 7
- 229910000734 martensite Inorganic materials 0.000 description 6
- 238000011161 development Methods 0.000 description 5
- 238000005530 etching Methods 0.000 description 4
- 239000000203 mixture Substances 0.000 description 4
- 238000005728 strengthening Methods 0.000 description 4
- 230000000052 comparative effect Effects 0.000 description 3
- 238000010191 image analysis Methods 0.000 description 3
- 238000003703 image analysis method Methods 0.000 description 3
- 229910001562 pearlite Inorganic materials 0.000 description 3
- 238000002360 preparation method Methods 0.000 description 3
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 2
- 229910003460 diamond Inorganic materials 0.000 description 2
- 239000010432 diamond Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000001747 exhibiting effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010422 painting Methods 0.000 description 2
- 238000001556 precipitation Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 239000006104 solid solution Substances 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 229910000885 Dual-phase steel Inorganic materials 0.000 description 1
- 239000003082 abrasive agent Substances 0.000 description 1
- 239000006061 abrasive grain Substances 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000007747 plating Methods 0.000 description 1
- 239000000377 silicon dioxide Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/20—Metals
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N1/00—Sampling; Preparing specimens for investigation
- G01N1/28—Preparing specimens for investigation including physical details of (bio-)chemical methods covered elsewhere, e.g. G01N33/50, C12Q
-
- 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
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
- G01N23/22—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material
- G01N23/225—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material using electron or ion
- G01N23/2251—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material using electron or ion using incident electron beams, e.g. scanning electron microscopy [SEM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
-
- 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 disclosure relates to a tissue photo evaluation method, a tissue photo evaluation device, an imaging device, and a program.
- the present disclosure particularly relates to a photo evaluation method, a structure photo evaluation device, a photographing device, and a program that target structure photos of metal materials.
- metal materials including steel have the same composition, their properties strongly depend on the metal structure on the scale of an optical microscope or electron microscope (for example, a scale of mm to ⁇ m).
- a method of changing the composition such as a solid solution strengthening method by adding a solid solution strengthening element and a precipitation strengthening method by adding a precipitation strengthening element.
- a method may be used in which the final metal structure is changed by changing heat treatment conditions with the same composition.
- Patent Document 1 discloses a method for preparing an observation sample for observation with an electron microscope.
- each phase After performing sample preparation using known polishing and etching methods on a metal material such as a steel plate, when observing the metal structure using a known imaging device such as an electron microscope, the contrast of each phase is generally observed. Since the values are different, each phase can be classified. For example, when a typical steel plate consisting of a ferrite phase and a pearlite phase is prepared as a sample using a known method and photographed with an optical microscope, the ferrite phase is observed as a gray contrast, and the pearlite phase is observed as a black contrast. Therefore, it is possible to classify the ferrite phase and the pearlite phase. Development is carried out by observing the metal structure using such a method and feeding back the observation results.
- the metallographic structure may be evaluated using a structural photograph with an insufficient number of fields of view, and the metallographic structure cannot be appropriately evaluated, and there is a possibility that the correlation between the metallographic structure and material properties may be misinterpreted. Making manufacturing process decisions based on misinterpreted correlations may not produce products with desired characteristics. Furthermore, in an attempt to avoid erroneous interpretations, observers may take tissue photographs with more fields of view than necessary, reducing work efficiency.
- An object of the present disclosure which was made in view of the above circumstances, is to provide a tissue photo evaluation method, a tissue photo evaluation device, a photographing device, and a program that can appropriately and efficiently evaluate the number of fields of view in a structure photo of a metal material.
- a tissue photo evaluation method includes: an input step of acquiring a plurality of tissue photographs taken at a predetermined imaging magnification for at least two or more fields of view of the metal material; a phase classification step of classifying phases in the plurality of tissue photographs; a quantitative value calculation step of calculating a quantitative value of the classified phase; a deviation calculation step of calculating the deviation of the quantitative value; a visual field number pass/fail determination step of determining whether the number of fields of view of the plurality of tissue photographs is pass/fail based on the deviation; an output step of outputting the pass/fail information; Equipped with.
- the tissue photo evaluation method includes: an input step of acquiring a plurality of tissue photographs taken at a predetermined imaging magnification for at least two or more fields of view of the metal material; a phase classification step of classifying phases in the plurality of tissue photographs; a quantitative value calculation step of calculating a quantitative value of the classified phase; a deviation calculation step of calculating the deviation of the quantitative value; a visual field number pass/fail determination step of determining whether the number of fields of view of the plurality of tissue photographs is pass/fail based on the deviation; a statistical value calculation step of calculating a statistical value based on the quantitative value of the phase; an output step of outputting the statistical value; Equipped with.
- the tissue photo evaluation method includes: an input step of acquiring a plurality of tissue photographs taken at two or more magnifications for at least two or more fields of view of the metal material; a phase classification step of classifying phases in the plurality of tissue photographs; a quantitative value calculation step of calculating a quantitative value of the classified phase; a magnification determination step of determining a representative imaging magnification based on the quantitative value; a deviation calculation step of calculating a deviation of the quantitative value for the plurality of tissue photographs corresponding to the representative imaging magnification; a visual field number pass/fail determination step of determining whether the number of fields of view of the plurality of tissue photographs is pass/fail based on the deviation; a statistical value calculation step of calculating a statistical value based on the quantitative value of the phase; an output step of outputting the statistical value; Equipped with.
- the output step outputs the pass/fail along with the statistical value.
- the quantitative value is at least one of area ratio, ellipsoid size, Feret diameter, average diameter, circularity, and number density.
- the tissue photo evaluation device includes: an input unit that obtains a plurality of tissue photographs taken at a predetermined imaging magnification for at least two or more fields of view of the metal material; a phase classification unit that classifies phases in the plurality of tissue photographs; a quantitative value calculation unit that calculates a quantitative value of the classified phase; a deviation calculation unit that calculates the deviation of the quantitative value; a visual field number pass/fail determination unit that determines whether the number of visual fields of the plurality of tissue photographs is pass/fail based on the deviation; an output unit that outputs the pass/fail; Equipped with.
- the tissue photo evaluation device includes: an input unit that obtains a plurality of tissue photographs taken at a predetermined imaging magnification for at least two or more fields of view of the metal material; a phase classification unit that classifies phases in the plurality of tissue photographs; a quantitative value calculation unit that calculates a quantitative value of the classified phase; a deviation calculation unit that calculates the deviation of the quantitative value; a visual field number pass/fail determination unit that determines whether the number of visual fields of the plurality of tissue photographs is pass/fail based on the deviation; a statistical value calculation unit that calculates a statistical value based on the quantitative value of the phase; an output unit that outputs the statistical value; Equipped with.
- the tissue photo evaluation device includes: an input unit that obtains a plurality of tissue photographs taken at two or more magnifications for at least two or more fields of view of the metal material; a phase classification unit that classifies phases in the plurality of tissue photographs; a quantitative value calculation unit that calculates a quantitative value of the classified phase; a magnification determination unit that determines a representative imaging magnification based on the quantitative value; a deviation calculation unit that calculates a deviation of the quantitative value for the plurality of tissue photographs corresponding to the representative imaging magnification; a visual field number pass/fail determination unit that determines whether the number of visual fields of the plurality of tissue photographs is pass/fail based on the deviation; a statistical value calculation unit that calculates a statistical value based on the quantitative value of the phase; an output unit that outputs the statistical value; Equipped with.
- An imaging device includes: The plurality of tissue photographs obtained by the tissue photograph evaluation apparatus according to any one of (6) to (8) are photographed.
- the photographing device is an optical microscope or a scanning electron microscope.
- a program includes: computer, an input unit that obtains a plurality of tissue photographs taken at a predetermined imaging magnification for at least two or more fields of view of the metal material; a phase classification unit that classifies phases in the plurality of tissue photographs; a quantitative value calculation unit that calculates a quantitative value of the classified phase; a deviation calculation unit that calculates the deviation of the quantitative value; a visual field number pass/fail determination unit that determines whether the number of visual fields of the plurality of tissue photographs is pass/fail based on the deviation; an output unit that outputs the pass/fail; function as
- a program includes: computer, an input unit that obtains a plurality of tissue photographs taken at a predetermined imaging magnification for at least two or more fields of view of the metal material; a phase classification unit that classifies phases in the plurality of tissue photographs; a quantitative value calculation unit that calculates a quantitative value of the classified phase; a deviation calculation unit that calculates the deviation of the quantitative value; a visual field number pass/fail determination unit that determines whether the number of visual fields of the plurality of tissue photographs is pass/fail based on the deviation; a statistical value calculation unit that calculates a statistical value based on the quantitative value of the phase; an output unit that outputs the statistical value; function as
- a program includes: computer, an input unit that obtains a plurality of tissue photographs taken at two or more magnifications for at least two or more fields of view of the metal material; a phase classification unit that classifies phases in the plurality of tissue photographs; a quantitative value calculation unit that calculates a quantitative value of the classified phase; a magnification determination unit that determines a representative imaging magnification based on the quantitative value; a deviation calculation unit that calculates a deviation of the quantitative value for the plurality of tissue photographs corresponding to the representative imaging magnification; a visual field number pass/fail determination unit that determines whether the number of visual fields of the plurality of tissue photographs is pass/fail based on the deviation; a statistical value calculation unit that calculates a statistical value based on the quantitative value of the phase; an output unit that outputs the statistical value; function as
- tissue photo evaluation method it is possible to provide a tissue photo evaluation method, a tissue photo evaluation device, a photographing device, and a program that can appropriately and efficiently evaluate the number of fields of view in a structure photo of a metal material.
- FIG. 1 is a schematic diagram showing a configuration example of a tissue photo evaluation system including a tissue photo evaluation apparatus according to an embodiment of the present disclosure.
- FIG. 2 is a flowchart showing processing of a tissue photograph evaluation method according to an embodiment of the present disclosure.
- FIG. 3 is a schematic diagram showing a configuration example of a tissue photo evaluation system including a tissue photo evaluation apparatus according to an embodiment of the present disclosure.
- FIG. 4 is a flowchart showing processing of a tissue photograph evaluation method according to an embodiment of the present disclosure.
- FIG. 5 is a schematic diagram showing a configuration example of a tissue photo evaluation system including a tissue photo evaluation device according to an embodiment of the present disclosure.
- FIG. 6 is a flowchart showing processing of a tissue photo evaluation method according to an embodiment of the present disclosure.
- FIG. 7 is a diagram illustrating a tissue photograph used in an example.
- FIG. 8 is a diagram showing the microstructure photograph of FIG. 7 that has undergone the phase classification process.
- FIG. 1 is a block diagram of a tissue photo evaluation system 1 including a tissue photo evaluation device 10 according to the first embodiment.
- the tissue photo evaluation system 1 includes a tissue photo evaluation device 10 and a photographing device 30.
- the tissue photo evaluation device 10 includes an input section 11, an output section 12, and a calculation section 13.
- the calculation section 13 includes a phase classification section 14 , a quantitative value calculation section 15 , a deviation calculation section 16 , and a visual field number pass/fail judgment section 19 .
- the photographing device 30 photographs a plurality of tissue photographs of the metal material obtained by the tissue photograph evaluation device 10.
- the photographing device 30 is, for example, an optical microscope or a scanning electron microscope, but is not limited to these as long as it has the function of photographing the structure of a metal material.
- tissue photo evaluation device 10 executes processing for evaluating a plurality of tissue photos of a metal material taken by the imaging device 30.
- the metal material is a steel material or a metal material having multiple metal phases.
- the evaluation performed by the tissue photo evaluation device 10 includes evaluation of the number of fields of view of a plurality of tissue photos.
- the evaluation of the number of fields of view of a plurality of microstructure photographs is an evaluation of whether a sufficient number of fields of view has been obtained to quantitatively evaluate the metallographic structure.
- the tissue photo evaluation device 10 may directly perform tissue evaluation or may determine the properties of the tissue photo. The property of the tissue photograph to be determined is, for example, whether the number of fields of view is acceptable or not.
- the tissue photo evaluation device 10 determines whether the number of fields of view of the tissue photo is acceptable.
- the number of fields of view means the number of tissue photographs having different fields of view.
- the number of fields of view and the number of tissue photographs may be different, in embodiments of the present disclosure, each tissue photograph has a different field of view, and the number of fields of view is described as being equal to the number of multiple tissue photographs of the metal material taken. do.
- the input unit 11 is an input interface of the tissue photo evaluation device 10 that acquires data necessary for processing to evaluate a plurality of tissue photos.
- the input unit 11 acquires a plurality of tissue photographs taken at a predetermined imaging magnification for at least two or more fields of view of the metal material.
- the data format of the plurality of tissue photographs may be a commonly used image data format such as TIFF or BMP.
- the output unit 12 is an output interface of the tissue photo evaluation device 10 that outputs properties of the tissue photo (for example, determined pass/fail and statistical values to be described later).
- the output unit 12 may transmit information such as the properties of the tissue photograph to other devices. Further, the output unit 12 may display the properties of the tissue photograph on a display device such as various displays. In the present embodiment, the output unit 12 outputs pass/fail for the number of fields of view of a plurality of tissue photographs.
- the calculation unit 13 performs calculations for evaluating a plurality of tissue photographs. Further, the calculation unit 13 may have a function as a control unit that controls the entire tissue photo evaluation device 10.
- the calculation unit 13 may be one or more processors.
- the processor is, for example, a general-purpose processor or a dedicated processor specialized for specific processing, but is not limited to these and can be any processor.
- the calculation unit 13 includes the phase classification unit 14, the quantitative value calculation unit 15, the deviation calculation unit 16, and the field of view number pass/fail determination unit 19.
- the functions of the phase classification section 14, the quantitative value calculation section 15, the deviation calculation section 16, and the field of view number pass/fail judgment section 19 may be realized by software.
- one or more programs may be stored in a storage device that can be accessed by the calculation unit 13.
- the calculation unit 13 functions as the phase classification unit 14, the quantitative value calculation unit 15, the deviation calculation unit 16, and the field of view number pass/fail judgment unit 19. good.
- phase classification unit 14 classifies phases in a plurality of tissue photographs. Details of the processing executed by the phase classification unit 14 will be described later.
- the quantitative value calculation unit 15 calculates quantitative values of the phases classified by the phase classification unit 14. Details of the quantitative value and the process executed by the quantitative value calculation unit 15 will be described later.
- the deviation calculation unit 16 calculates the deviation of the quantitative value calculated by the quantitative value calculation unit 15. The details of the process executed by the deviation calculation unit 16 will be described later.
- the field of view number pass/fail determination section 19 determines whether or not the number of fields of view of a plurality of tissue photographs is pass/fail based on the deviation calculated by the deviation calculation section 16. Details of the process executed by the field of view number pass/fail determining unit 19 will be described later.
- the tissue photo evaluation device 10 is not limited to a specific device, but can be realized by a computer as an example.
- a computer includes a storage device such as a memory and a hard disk drive, a CPU, and an input/output device.
- the calculation unit 13 may be realized by a CPU.
- the program read by the calculation unit 13 may be stored in a storage device.
- the input section 11 and the output section 12 may be realized by input/output devices.
- FIG. 2 is a flowchart showing the processing of the tissue photo evaluation method executed by the tissue photo evaluation apparatus 10 according to the present embodiment.
- the structure photo evaluation method includes an input step of acquiring a plurality of structure photos taken at a predetermined imaging magnification for at least two or more fields of view of a metal material, and a phase classification step of classifying phases in the plurality of structure photos. , a quantitative value calculation step that calculates the quantitative value of the classified phase, a deviation calculation step that calculates the deviation of the quantitative value, and a field number pass/fail judgment that determines pass/fail for the number of fields of view of multiple tissue photographs based on the deviation.
- the process and the output process of outputting pass/fail are performed in this order.
- the tissue photo evaluation method if the field of view number pass/fail judgment step does not pass (in other words, it fails), the tissue photo obtained in the input step is added and these steps are executed again. do.
- the input step is a step in which the input unit 11 acquires a plurality of tissue photographs taken at a predetermined imaging magnification for at least two or more visual fields of the metal material (step S11).
- the microstructure photograph be taken using a known photographing device such as an optical microscope or a scanning electron microscope after performing sample preparation such as polishing the surface of the metal material (sample) by a known method.
- Sample preparation generally involves rough polishing and then final polishing.
- Rough polishing and final polishing may be performed by known methods.
- Rough polishing by a known method is, for example, polishing to remove scratches that are visible to the naked eye using a commercially available sandpaper (such as Emily paper) coated with abrasive grains on paper.
- final polishing by a known method is polishing using an abrasive of 0.05 ⁇ m to 2 ⁇ m until the sample becomes a mirror surface.
- abrasive known abrasives such as diamond and silica can be used.
- Mirror polishing is performed until polishing scratches are no longer noticeable when observed with an optical microscope at a magnification of 10 to 500 times. If many polishing scratches remain, it will cause errors during phase classification in the phase classification process, so it is desirable to perform polishing so that as few scratches as possible remain.
- etching with nital or the like may be performed to clarify the phase contrast. Etching may be omitted when the target is a sample whose phase can be classified without etching.
- the number of fields of view for tissue photography should be at least 2 or more.
- the field of view is randomly determined.
- two or more fields of view may be obtained by continuously photographing while changing the field of view little by little.
- the imaging device 30 has a function of automatically determining the field of view by using random numbers in a program, such a function may be used.
- the magnification for taking tissue photographs is not limited to a specific magnification, and may be any magnification that allows observation of the target tissue.
- DP steel Dual Phase steel
- an imaging magnification in the range of 500 times to 3000 times.
- a plating layer of a plated steel sheet it is preferable to select an imaging magnification in the range of 1000 times to 5000 times.
- the phase classification step is a step in which the phase classification unit 14 classifies phases in a plurality of tissue photographs (step S12).
- phase classification may be performed by hand-painting by identifying phases with the naked eye, by using binarization of image brightness values, or by advanced image analysis techniques. It is preferable to apply a method that can classify as accurately as possible.
- phase classification by hand painting lacks objectivity. Therefore, it is preferable to use binarization or advanced image analysis techniques. It is more preferable to use advanced image analysis techniques as exemplified below.
- the advanced image analysis method is a random forest model that specifies multiple regions of each phase from the taken tissue photographs, calculates feature values from the brightness values of the image of the designated regions, and repeats N-value processing from the calculated feature values.
- classification is performed using techniques such as neural network models or support vector machines. It is preferable to use one or more of the following eight specific examples (C1 to C8) as the feature value.
- the identity feature value is a feature value that indicates the brightness value itself of the tissue photograph.
- the Mean feature value is a feature value indicating the average value of brightness values in a predetermined range of the tissue photograph. That is, the Mean feature value is obtained by extracting a predetermined range "(number of pixels x) x (number of pixels y)" from each phase of the tissue photograph and averaging the brightness values therein.
- the "number of pixels x" and the “number of pixels y" may be the same size or different sizes.
- the region of "(number of pixels x) It may be calculated for y.
- the lower limit of "pixel number x" and “pixel number y" is, for example, larger than the noise included in the microstructure photograph, and less than 1/2 of the smaller crystal grain size among the multiple phases of the metal structure. It is preferable to set the range to include.
- the upper limit includes crystal grains that are less than half of the larger crystal grain size, because if the pixel range is too large, it may be affected by grain boundaries or other adjacent phases. It is preferable that the
- noise included in the tissue photograph refers to, for example, a portion of the tissue photograph where the brightness value suddenly increases. Furthermore, “making the number of pixels x and y larger than the noise” indicates that the number of pixels x and y should be made larger than the width of the noise.
- the Gaussian feature value is a feature value that indicates an average value of brightness values in a predetermined range of a tissue photograph, with weights increasing closer to the center. That is, the Gaussian feature value is obtained by extracting a predetermined range "(number of pixels x) x (number of pixels y)" from each phase of the tissue photograph, and extracting an average value with larger weights for central pixels.
- the "number of pixels x" and the "number of pixels y" may be the same size or different sizes.
- the region of "(number of pixels x) It may be calculated for y.
- the lower limit of "pixel number x" and “pixel number y" is, for example, larger than the noise included in the microstructure photograph, and less than 1/2 of the smaller crystal grain size among the multiple phases of the metal structure. It is preferable to set the range to include.
- the upper limit includes crystal grains that are less than half of the larger crystal grain size, because if the pixel range is too large, it may be affected by grain boundaries or other adjacent phases. It is preferable that the
- the Median feature value is a feature value that indicates the median value of brightness values in a predetermined range of the tissue photograph. That is, the median feature value is obtained by extracting a predetermined range "(number of pixels x) x (number of pixels y)" from each phase of the tissue photograph, and extracting the median value from the brightness values therein.
- the "number of pixels x" and the “number of pixels y" may be the same size or different sizes.
- the region of "(number of pixels x) It may be calculated for y.
- the lower limit of "pixel number x" and “pixel number y" is, for example, larger than the noise included in the microstructure photograph, and less than 1/2 of the smaller crystal grain size among the multiple phases of the metal structure. It is preferable to set the range to include.
- the upper limit includes crystal grains that are less than half of the larger crystal grain size, because if the pixel range is too large, it may be affected by grain boundaries or other adjacent phases. It is preferable that the
- the Max feature value is a feature value indicating the maximum value of brightness values in a predetermined range of the tissue photograph. That is, the Max feature value is obtained by extracting a predetermined range "(number of pixels x) x (number of pixels y)" from each phase of the tissue photograph, and extracting the maximum value from the luminance values therein.
- the "number of pixels x" and the “number of pixels y" may be the same size or different sizes.
- the region of "(number of pixels x) It may be calculated for y.
- the lower limit of "pixel number x" and “pixel number y" is, for example, larger than the noise included in the microstructure photograph, and less than 1/2 of the smaller crystal grain size among the multiple phases of the metal structure. It is preferable to set the range to include.
- the upper limit includes crystal grains that are less than half of the larger crystal grain size, because if the pixel range is too large, it may be affected by grain boundaries or other adjacent phases. It is preferable that the
- the Min feature value is a feature value indicating the minimum value of brightness values in a predetermined range of the tissue photograph. That is, the Min feature value is obtained by extracting a predetermined range "(number of pixels x) x (number of pixels y)" from each phase of the tissue photograph, and extracting the minimum value from the luminance values therein.
- the "number of pixels x" and the “number of pixels y" may be the same size or different sizes.
- the region of "(number of pixels x) It may be calculated for y.
- the lower limit of "pixel number x" and “pixel number y" is, for example, larger than the noise included in the microstructure photograph, and less than 1/2 of the smaller crystal grain size among the multiple phases of the metal structure. It is preferable to set the range to include.
- the upper limit includes crystal grains that are less than half of the larger crystal grain size, because if the pixel range is too large, it may be affected by grain boundaries or other adjacent phases. It is preferable that the
- Derivative feature values are obtained by extracting a predetermined range "(number of pixels x) x (number of pixels y)" from each phase of the tissue photograph, and calculating differential values in the x and y directions for pixels at the edges of the range. It is.
- the "number of pixels x" and the “number of pixels y” may be the same size or different sizes.
- the region of "(number of pixels x) It may be calculated for y.
- the lower limit of "pixel number x" and "pixel number y” is, for example, larger than the noise included in the microstructure photograph, and less than 1/2 of the smaller crystal grain size among the multiple phases of the metal structure. It is preferable to set the range to include.
- the upper limit includes crystal grains that are less than half of the larger crystal grain size, because if the pixel range is too large, it may be affected by grain boundaries or other adjacent phases. It is preferable that the
- the Derivative added feature value is obtained by convolving the Derivative feature value by calculating the Mean feature value, Gaussian feature value, Median feature value, Max feature value, and Min feature value with respect to the Derivative feature value. It is.
- the "number of pixels x" and the “number of pixels y" may be the same size or different sizes. In addition, the region of "(number of pixels x) It may be calculated for y.
- the lower limit of "pixel number x" and "pixel number y" is, for example, larger than the noise included in the microstructure photograph, and less than 1/2 of the smaller crystal grain size among the multiple phases of the metal structure. It is preferable to set the range to include.
- the upper limit includes crystal grains that are less than half of the larger crystal grain size, because if the pixel range is too large, it may be affected by grain boundaries or other adjacent phases. It is preferable that the
- processing may be performed to cut off the boundary (outer periphery) for accurate analysis.
- the quantitative value calculation step is a step in which the quantitative value calculation unit 15 calculates quantitative values of the phases classified by the phase classification unit 14.
- the quantitative value for example, at least one of the following (1) to (6) is calculated.
- the quantitative values (1) to (5) are calculated for each crystal grain of the identified phase after classification, so multiple A numerical value is obtained.
- those parameters may be used.
- the area ratio is calculated by calculating the ratio of the area of each crystal grain of the specified phase to the area of the entire structure photograph in each structure photograph.
- the area ratio of each crystal grain is calculated according to the following formula.
- f is the area ratio of each crystal grain.
- a i is the area of each crystal grain.
- a sum is the area of the entire tissue photograph. Furthermore, by calculating the sum of the area ratios of each crystal grain for the identified phase, the area ratio of the identified phase per one microstructure photograph is calculated.
- the ellipsoid size is calculated by approximating the shape of each crystal grain of the identified phase to an ellipse in each microstructure photograph.
- the ellipsoid size is at least one of the major axis, minor axis, and aspect ratio of the approximated ellipsoid. Furthermore, by calculating the average value of the ellipsoid size of each crystal grain for the identified phase, the average ellipsoid size of the identified phase per microstructure photograph is calculated.
- the average diameter of the crystal grains is calculated by determining the area of each crystal grain of the specified phase in each microstructure photograph and taking the square root of the area. Furthermore, by calculating the average value of the identified phase from the average diameter calculated for each crystal grain, the average average diameter of the identified phase per one microstructure photograph is calculated.
- C is the roundness.
- S is the area.
- P is the perimeter.
- the circularity is 1.0.
- the roundness becomes smaller than 1.0.
- each microstructure photograph the number density of each microstructure photograph is calculated by counting the number of crystal grains of the specified phase and dividing the number of crystal grains by the area of the entire microstructure photograph.
- the quantitative value it is preferable to use one or more of (1) to (6), and more preferably two or more.
- a quantitative value including the area ratio in (1) it is preferable to use.
- a deviation is calculated for each visual field.
- the deviation calculation unit 16 calculates the average value N i of the quantitative values i of the tissue photographs of all visual fields for the identified phase. Furthermore, the deviation calculation unit 16 calculates an average value ⁇ ij of the quantitative value i of the tissue photograph of the visual field j for the identified phase.
- the deviation calculation unit 16 divides the average value ⁇ ij of the quantitative values i of the tissue photographs of the visual field j by the average value N i of the quantitative values i of the tissue photographs of all visual fields, and calculates the standardized quantitative value of the visual field j. i, ( ⁇ ij /N i ) is calculated.
- the deviation calculation unit 16 calculates the average value of the deviations of the quantitative values i.
- the average value of the deviation is calculated by dividing the sum of "the absolute value of the value obtained by subtracting 1 from each standardized quantitative value i" by the number of fields of view (number of tissue photographs), and is expressed by the following formula.
- S i is the average value of the deviation of the quantitative value i.
- n is the number of fields of view (number of tissue photographs).
- normalized area ratio means the area ratio standardized in the above deviation calculation step.
- normalized Feret diameter and “normalized circularity” mean standardized Feret diameter and standardized circularity, respectively.
- the field of view number pass/fail judgment step (step S15) is a step in which the field of view number pass/fail judgment unit 19 judges whether the number of fields of view of the tissue photograph is pass/fail based on the deviation of the quantitative value i.
- the field of view number pass/fail determining unit 19 first determines whether the number of fields of view (number of tissue photographs) is such that the tissue can be appropriately evaluated (pass/fail) based on the average deviation value S i calculated by the deviation calculation unit 16. .
- the visual field number pass/fail determining unit 19 determines that the number of visual fields is sufficient (Yes in step S16), and adds the tissue photograph. Do not take pictures.
- the threshold value is 0.1 as an example, but it is not limited to a specific value and may be set depending on, for example, the type of target metal.
- the visual field number pass/fail judgment unit 19 determines that if even one of the average values S i of the deviations of each quantitative value is larger than the threshold value, the deviation of each quantitative value will be large and the relationship between the quantitative value and the material properties cannot be accurately grasped. Therefore, it is determined to be a failure (No in step S16). If it is determined to be a failure, the visual field number pass/fail determining unit 19 adds the tissue photograph obtained in the input step, returns the process to the input step (step S11), and executes the series of processes again.
- step S17 If the field of view number pass/fail determining unit 19 determines that the result is acceptable (Yes in step S16), the output process is executed (step S17).
- the output step is a step in which the output unit 12 outputs the pass/fail of the number of visual fields.
- the output process is executed only in the case of a pass, but the output process may be executed even after a predetermined number of failures. For example, after the process of returning from step S16 to step S11 is repeated a predetermined number of times (for example, five times), if the field of view number pass/fail determining unit 19 determines that the field of view has failed, an output step that outputs a failure is performed. May be executed.
- the number of fields of view in a tissue photograph of a metal material can be appropriately and efficiently evaluated by the tissue photograph evaluation method executed by the tissue photograph evaluation apparatus 10 according to the present embodiment.
- the tissue photograph evaluation apparatus 10 By feeding back the evaluation results, an appropriate number of fields of view for observing the metal structure can be determined, regardless of the subjectivity of the observer. Furthermore, since the observer does not have to take unnecessary photographs of tissues while changing the field of view, work efficiency can be improved.
- FIG. 3 is a block diagram of a tissue photo evaluation system 1 including a tissue photo evaluation device 10 according to the second embodiment.
- the tissue photo evaluation device 10 according to the present embodiment outputs statistical values based on quantitative values of phases when performing tissue photo evaluation. By outputting such statistical values, it becomes possible to verify the evaluation performed by the tissue photo evaluation device 10 or to make a secondary pass/fail judgment outside the tissue photo evaluation device 10.
- the tissue photo evaluation device 10 according to the present embodiment includes the constituent elements of the tissue photo evaluation device 10 according to the first embodiment, and further includes a statistical value calculation unit 20. In order to avoid redundant explanation, configurations different from the first embodiment will be explained below.
- the statistical value calculation unit 20 calculates statistical values based on the quantitative values of the phases. In this embodiment, the statistical value calculation unit 20 calculates statistical values based on all the quantitative values of the plurality of tissue photographs input to the input unit 11. Statistical values may include, for example, average values, median values, standard deviations, etc., but are not limited to any particular value. In the present embodiment, the statistical value calculation unit 20 calculates statistical values when the field of view number pass/fail determination unit 19 determines that the field of view is passed. However, the present invention is not limited to this case, and the statistical value calculation unit 20 may calculate the statistical value after a predetermined number of failures. Furthermore, the output unit 12 may output pass/fail along with the statistical values calculated by the statistical value calculation unit 20.
- the input unit 11 acquires a plurality of tissue photographs taken at a predetermined imaging magnification for at least two or more visual fields of the metal material, as in the first embodiment.
- the calculation unit 13 which is a processor
- the calculation unit 13 is controlled by the phase classification unit 14, the quantitative value calculation unit 15, the deviation calculation unit 16, the field of view number pass/fail judgment unit 19, and the statistical value calculation. It may function as part 20.
- FIG. 4 is a flowchart showing the processing of the tissue photo evaluation method executed by the tissue photo evaluation apparatus 10 according to the present embodiment.
- the structure photo evaluation method includes an input step of acquiring a plurality of structure photos taken at a predetermined imaging magnification for at least two or more fields of view of a metal material, and a phase classification step of classifying phases in the plurality of structure photos. , a quantitative value calculation step that calculates the quantitative value of the classified phase, a deviation calculation step that calculates the deviation of the quantitative value, and a field number pass/fail judgment that determines pass/fail for the number of fields of view of multiple tissue photographs based on the deviation.
- a statistical value calculation step of calculating a statistical value based on the quantitative value of the phase, and an outputting step of outputting the statistical value are performed in this order.
- the tissue photo evaluation method when it is determined that the field of view number pass/fail determination step is failed, the tissue photo obtained in the input step is added and these steps are executed again.
- step S21 The input process (step S21), the phase classification process (step S22), the quantitative value calculation process (step S23), the deviation calculation process (step S24), and the field of view number pass/fail judgment process (step S25) are the same as those in the first embodiment. It is the same as the process in the name. As in the first embodiment, if it is determined that the field of view number pass/fail determination process does not pass (No in step S26), the process returns to the input process (step S21) and the series of processes is executed again.
- step S27 Statistical value calculation process
- the statistical value calculation unit 20 calculates the average value and standard deviation for all visual fields of each quantitative value calculated in the quantitative value calculation step.
- the output step is executed (step S28).
- the output step is a step of outputting the statistical values calculated by the statistical value calculating section 20.
- pass/fail may be output together with the statistical values.
- the number of fields of view in a tissue photograph of a metal material can be appropriately and efficiently evaluated by the tissue photograph evaluation method executed by the tissue photograph evaluation apparatus 10 according to the present embodiment.
- the tissue photograph evaluation method executed by the tissue photograph evaluation apparatus 10 By feeding back the evaluation results, an appropriate number of fields of view for observing the metal structure can be determined, regardless of the subjectivity of the observer. Furthermore, since the observer does not have to take unnecessary photographs of tissues while changing the field of view, work efficiency can be improved. Further, by outputting the statistical values, it becomes possible to verify or make a secondary pass/fail judgment on the evaluation performed by the tissue photo evaluation device 10 outside the tissue photo evaluation device 10.
- FIG. 5 is a block diagram of a tissue photo evaluation system 1 including a tissue photo evaluation device 10 according to the third embodiment.
- the tissue photograph evaluation apparatus 10 according to the present embodiment determines the representative imaging magnification before evaluating the number of fields of view.
- the tissue photo evaluation device 10 according to the present embodiment includes the components of the tissue photo evaluation device 10 according to the second embodiment, and further includes a magnification determination unit 17. In order to avoid redundant explanation, configurations that are different from the first embodiment and the second embodiment will be explained below.
- the input unit 11 acquires a plurality of tissue photographs taken at two or more imaging magnifications for at least two or more fields of view of the metal material. That is, unlike the first embodiment and the second embodiment, the input unit 11 acquires a plurality of tissue photographs in a state where the imaging magnification is not determined.
- the photographing magnification of the tissue photograph is preferably 3 or more.
- the photographing magnification of the tissue photograph is more preferably 5 or more. It is preferable to select the imaging magnification at random.
- the magnification determining unit 17 determines a representative imaging magnification based on the quantitative value calculated by the quantitative value calculating unit 15. The details of the process executed by the magnification determination unit 17 will be described later.
- the calculation unit 13 which is a processor
- the calculation unit 13 is divided into a phase classification unit 14, a quantitative value calculation unit 15, a deviation calculation unit 16, a magnification determination unit 17, a field number It may function as the pass/fail determination section 19 and the statistical value calculation section 20.
- FIG. 6 is a flowchart showing the process of the tissue photo evaluation method executed by the tissue photo evaluation apparatus 10 according to the present embodiment.
- the structure photo evaluation method includes an input step of acquiring multiple structure photos taken at two or more imaging magnifications for at least two or more fields of view of a metal material, and a phase classification step of classifying phases in the plurality of structure photos. a quantitative value calculation step that calculates the quantitative value of the classified phase; a magnification determination step that determines the representative imaging magnification based on the quantitative value; and a quantitative value calculation step that determines the representative imaging magnification based on the quantitative value.
- a deviation calculation step (second deviation calculation step) in which the deviation is calculated, a field number pass/fail judgment step in which the number of fields of view of multiple tissue photographs is determined based on the deviation, and a statistical value is calculated based on the quantitative value of the phase.
- a statistical value calculation step and an output step of outputting the statistical values are performed.
- the tissue photo evaluation method when it is determined that the field of view number pass/fail determination step is failed, the tissue photo obtained in the input step is added and these steps are executed again.
- step S31 The input step (step S31), phase classification step (step S32), and quantitative value calculation step (step S33) are the same as the steps with the same names in the second embodiment.
- the magnification determining step is a step in which the magnification determining section 17 determines a representative imaging magnification based on the quantitative value calculated by the quantitative value calculating section 15 (step S34).
- the magnification determination unit 17 can determine the imaging magnification as follows.
- Section 17 employs a smaller imaging magnification.
- a microstructure photograph in which there are two or more crystal grains with an area ratio of more than 10% may show that the grains are cut off at the boundary (periphery) of the microstructure photograph, or that the number of crystal grains photographed is small. This is because the size distribution may not be evaluated correctly.
- the fact that the number exceeds 1/3 of the total number indicates that it is not a characteristic of some exceptional tissue photographs, but a tendency in tissue photographs of that imaging magnification.
- the number of grains with the largest area ratio of less than 3% of the entire tissue photograph is 1/1/2 of the total number of tissue photographs at that magnification obtained in the input process.
- the magnification determination unit 17 adopts a larger imaging magnification. This is because a microstructure photograph in which the crystal grains with the largest area ratio is less than 3% of the entire microstructure photograph has many small crystal grains, and the shape of the crystal grains cannot be appropriately evaluated.
- the fact that the number exceeds 1/3 of the total number indicates that it is not a characteristic of some exceptional tissue photographs, but a tendency in tissue photographs of that imaging magnification.
- the magnification determining unit 17 sets the photographing magnification that satisfies the conditions A and B as the representative photographing magnification.
- Condition A is that for a tissue photo taken at a certain magnification, "the number of tissue photos in which two or more crystal grains with an area ratio exceeding 10% are present is 1/3 of the total number of tissue photos at that magnification obtained in the input process. "Do not exceed.”
- condition B is that for a tissue photograph at a certain imaging magnification, "a tissue photograph in which the crystal grains with the largest area ratio account for less than 3% of the entire tissue photograph is a tissue photograph at that imaging magnification obtained in the input process.” The total number must not exceed 1/3 of the total number of
- the upper limit value (10%) and lower limit value (3%) of the area ratio in conditions A and B of the magnification determination process are only examples, and the size and shape of the crystal grains of the target metal material are It is not limited as long as it is a numerical value that can be evaluated.
- the quantitative value used in the conditions of the magnification determination step is the area ratio in this embodiment, but may be, for example, the ellipsoid size or the Feret diameter. Further, when the shape or number of each crystal grain has a large influence on material properties, the quantitative value used in the conditions of the magnification determination step may be, for example, circularity or number density. In this embodiment, since the area ratio of a phase generally affects material properties in many cases, an example using the area ratio has been described.
- the first deviation calculation step is a step in which the deviation calculation section 16 calculates the deviation of the quantitative value obtained by the quantitative value calculation section 15.
- the second deviation calculation process the deviation calculation process for each field of view as in the first and second embodiments. It is called.
- the deviation calculation unit 16 calculates the standard deviation of each quantitative value for each imaging magnification that is a candidate for the representative imaging magnification.
- the imaging magnification with the smallest standard deviation is determined as the representative imaging magnification.
- the imaging magnification with the smaller standard deviation of the quantitative value considered important is determined as the representative imaging magnification.
- the imaging magnification with the smallest standard deviation of the area ratio is determined as the representative imaging magnification.
- the magnification determination step is executed again.
- the magnification determining section 17 determines one final representative photographing magnification from among the candidates for the representative photographing magnification already selected, based on the deviation calculated by the deviation calculating section 16. .
- a second deviation calculation step is executed (step S37).
- the second deviation calculation step is the same as the deviation calculation step (step S24) of the second embodiment.
- the visual field number pass/fail determination process (step S38), the statistical value calculation process (step S40), and the output process (step S41) are the same as the processes with the same names in the second embodiment.
- the branching according to the pass/fail of the visual field number pass/fail determination process is the same as step S26 of the second embodiment.
- the number of fields of view in a tissue photograph of a metal material can be appropriately and efficiently evaluated by the tissue photograph evaluation method executed by the tissue photograph evaluation apparatus 10 according to the present embodiment.
- the tissue photograph evaluation method executed by the tissue photograph evaluation apparatus 10 By feeding back the evaluation results, an appropriate number of fields of view for observing the metal structure can be determined, regardless of the subjectivity of the observer.
- work efficiency can be improved.
- the processing by the magnification determination unit 17 allows the representative magnification to be objectively and efficiently determined from a plurality of microstructure photographs of the metal material.
- Example Hereinafter, the effects of the present disclosure will be specifically explained based on Examples, but the present disclosure is not limited to these Examples.
- a tissue photo evaluation method using the tissue photo evaluation apparatus 10 according to the first embodiment described above was performed.
- a DP steel plate consisting of a ferrite phase and a martensitic phase was roughly polished, finished polished using diamond paste, and then etched with nital. Thereafter, tissue photographs of two fields of view were randomly taken using an electron microscope at a magnification of 1000 times. A plurality of tissue photographs were obtained (input step).
- FIG. 7 shows some of the obtained tissue photographs.
- the phase exhibiting white contrast is martensite
- the phase exhibiting black contrast is ferrite.
- FIG. 8 shows the microstructure photograph of FIG. 7 after the phase classification process.
- black is the martensite phase
- white is the ferrite phase.
- the area ratio, Feret diameter, and roundness of each crystal grain were calculated as quantitative values for the martensite phase in each microstructure photograph (quantitative value calculation step).
- Table 1 shows the calculated values for each visual field.
- 0.1 was used as the threshold value in determining whether the number of fields of view was acceptable or not.
- the average value of the deviation of roundness is 0.1 or less.
- the average value of the deviation of the area ratio and Feret diameter exceeded 0.1, and it was determined that the structure of this sample could not be appropriately evaluated using two fields of view. In other words, a failure was indicated in the visual field number pass/fail determination (visual field number pass/fail determination step).
- the Feret diameter indicates the average Feret diameter per tissue photograph.
- Table 2 shows the results when the number of fields of view is three in total. Further, Table 3 shows the results when the number of fields of view was nine in total.
- the tissue can be appropriately evaluated by photographing nine fields of view of this sample using the tissue photo evaluation apparatus 10.
- the number of fields of view was determined based on the subjectivity of the observer for the same sample.
- more than 10 visual fields were photographed, and it took a long time to photograph and make a judgment. This device allows efficient imaging and completes judgment instantly.
- the number of fields of view of the microstructure photograph of the metal material could be appropriately and efficiently evaluated.
- the correlation with material properties can be considered objectively, and efficient material development is expected.
- the quantitative values of each phase can be appropriately evaluated, so the development of efficient steel materials or metal materials having multiple metal phases is expected.
- the tissue photo evaluation method, tissue photo evaluation device, imaging device, and program according to the present embodiment can appropriately and efficiently evaluate the number of fields of view of a tissue photo of a metal material.
Landscapes
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Image Processing (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
- Investigating And Analyzing Materials By Characteristic Methods (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
Description
金属材料の少なくとも2以上の視野について所定の撮影倍率で撮影された複数の組織写真を取得する入力工程と、
前記複数の組織写真での相を分類する相分類工程と、
分類された前記相の定量値を算出する定量値算出工程と、
前記定量値の偏差を算出する偏差算出工程と、
前記偏差に基づいて前記複数の組織写真の視野数について合否を判定する視野数合否判定工程と、
前記合否を出力する出力工程と、
を備える。
金属材料の少なくとも2以上の視野について所定の撮影倍率で撮影された複数の組織写真を取得する入力工程と、
前記複数の組織写真での相を分類する相分類工程と、
分類された前記相の定量値を算出する定量値算出工程と、
前記定量値の偏差を算出する偏差算出工程と、
前記偏差に基づいて前記複数の組織写真の視野数について合否を判定する視野数合否判定工程と、
前記相の定量値に基づいて統計値を算出する統計値算出工程と、
前記統計値を出力する出力工程と、
を備える。
金属材料の少なくとも2以上の視野について2以上の撮影倍率で撮影された複数の組織写真を取得する入力工程と、
前記複数の組織写真での相を分類する相分類工程と、
分類された前記相の定量値を算出する定量値算出工程と、
前記定量値に基づいて代表撮影倍率を決定する倍率決定工程と、
前記代表撮影倍率に該当する前記複数の組織写真について、前記定量値の偏差を算出する偏差算出工程と、
前記偏差に基づいて前記複数の組織写真の視野数について合否を判定する視野数合否判定工程と、
前記相の定量値に基づいて統計値を算出する統計値算出工程と、
前記統計値を出力する出力工程と、
を備える。
前記出力工程は、前記統計値とともに前記合否を出力する。
前記定量値は、面積率、楕円体サイズ、フェレー径、平均径、真円度及び数密度の少なくとも1つである。
金属材料の少なくとも2以上の視野について所定の撮影倍率で撮影された複数の組織写真を取得する入力部と、
前記複数の組織写真での相を分類する相分類部と、
分類された前記相の定量値を算出する定量値算出部と、
前記定量値の偏差を算出する偏差算出部と、
前記偏差に基づいて前記複数の組織写真の視野数について合否を判定する視野数合否判定部と、
前記合否を出力する出力部と、
を備える。
金属材料の少なくとも2以上の視野について所定の撮影倍率で撮影された複数の組織写真を取得する入力部と、
前記複数の組織写真での相を分類する相分類部と、
分類された前記相の定量値を算出する定量値算出部と、
前記定量値の偏差を算出する偏差算出部と、
前記偏差に基づいて前記複数の組織写真の視野数について合否を判定する視野数合否判定部と、
前記相の定量値に基づいて統計値を算出する統計値算出部と、
前記統計値を出力する出力部と、
を備える。
金属材料の少なくとも2以上の視野について2以上の撮影倍率で撮影された複数の組織写真を取得する入力部と、
前記複数の組織写真での相を分類する相分類部と、
分類された前記相の定量値を算出する定量値算出部と、
前記定量値に基づいて代表撮影倍率を決定する倍率決定部と、
前記代表撮影倍率に該当する前記複数の組織写真について、前記定量値の偏差を算出する偏差算出部と、
前記偏差に基づいて前記複数の組織写真の視野数について合否を判定する視野数合否判定部と、
前記相の定量値に基づいて統計値を算出する統計値算出部と、
前記統計値を出力する出力部と、
を備える。
(6)から(8)のいずれかの組織写真評価装置によって取得される前記複数の組織写真を撮影する。
前記撮影装置は光学顕微鏡又は走査型電子顕微鏡である。
コンピュータを、
金属材料の少なくとも2以上の視野について所定の撮影倍率で撮影された複数の組織写真を取得する入力部と、
前記複数の組織写真での相を分類する相分類部と、
分類された前記相の定量値を算出する定量値算出部と、
前記定量値の偏差を算出する偏差算出部と、
前記偏差に基づいて前記複数の組織写真の視野数について合否を判定する視野数合否判定部と、
前記合否を出力する出力部と、
として機能させる。
コンピュータを、
金属材料の少なくとも2以上の視野について所定の撮影倍率で撮影された複数の組織写真を取得する入力部と、
前記複数の組織写真での相を分類する相分類部と、
分類された前記相の定量値を算出する定量値算出部と、
前記定量値の偏差を算出する偏差算出部と、
前記偏差に基づいて前記複数の組織写真の視野数について合否を判定する視野数合否判定部と、
前記相の定量値に基づいて統計値を算出する統計値算出部と、
前記統計値を出力する出力部と、
として機能させる。
コンピュータを、
金属材料の少なくとも2以上の視野について2以上の撮影倍率で撮影された複数の組織写真を取得する入力部と、
前記複数の組織写真での相を分類する相分類部と、
分類された前記相の定量値を算出する定量値算出部と、
前記定量値に基づいて代表撮影倍率を決定する倍率決定部と、
前記代表撮影倍率に該当する前記複数の組織写真について、前記定量値の偏差を算出する偏差算出部と、
前記偏差に基づいて前記複数の組織写真の視野数について合否を判定する視野数合否判定部と、
前記相の定量値に基づいて統計値を算出する統計値算出部と、
前記統計値を出力する出力部と、
として機能させる。
(組織写真評価システム)
図1は、第1実施形態に係る組織写真評価装置10を備える組織写真評価システム1のブロック図である。組織写真評価システム1は、組織写真評価装置10と、撮影装置30と、を備える。組織写真評価装置10は、入力部11と、出力部12と、演算部13と、を備える。演算部13は、相分類部14と、定量値算出部15と、偏差算出部16と、視野数合否判定部19と、を備える。
撮影装置30は、組織写真評価装置10によって取得される金属材料の複数の組織写真を撮影する。撮影装置30は、例えば光学顕微鏡又は走査型電子顕微鏡であるが、金属材料の組織を撮影する機能を有する装置であれば、これらに限定されない。
組織写真評価装置10は、撮影装置30によって撮影された金属材料の複数の組織写真を評価するための処理を実行する。ここで、金属材料は、鉄鋼材料又は複数の金属相を有する金属材料である。組織写真評価装置10が実行する評価は、複数の組織写真の視野数の評価を含む。複数の組織写真の視野数の評価とは、金属組織を定量評価するのに十分な視野数が得られているかについての評価である。組織写真評価装置10は、直接的に組織評価まで行ってよいし、組織写真の性質を決定してよい。決定される組織写真の性質は、例えば視野数の合否である。本実施形態において、組織写真評価装置10は、組織写真の視野数の合否を決定する。ここで、視野数は、異なる視野を有する組織写真の数を意味する。視野数と組織写真の数とが異なってよいが、本開示の実施形態において、組織写真がそれぞれ異なる視野を有し、視野数は撮影された金属材料の複数の組織写真の数に等しいとして説明する。
入力部11は、複数の組織写真を評価する処理に必要なデータを取得する、組織写真評価装置10の入力インターフェースである。本実施形態において、入力部11は、金属材料の少なくとも2以上の視野について所定の撮影倍率で撮影された複数の組織写真を取得する。複数の組織写真のデータ形式は、TIFF、BMP等の一般に使用されている画像のデータ形式であってよい。
出力部12は、組織写真の性質(例えば決定された合否及び後述の統計値など)を出力する、組織写真評価装置10の出力インターフェースである。出力部12は、組織写真の性質などの情報を、他の装置などに送信してよい。また、出力部12は、組織写真の性質などを、各種ディスプレイなどの表示装置に表示させてよい。本実施形態において、出力部12は、複数の組織写真の視野数についての合否を出力する。
演算部13は、複数の組織写真を評価するための演算を行う。また、演算部13は、組織写真評価装置10の全体を制御する制御部としての機能を備えてよい。演算部13は、1つ以上のプロセッサであってよい。プロセッサは、例えば汎用のプロセッサ又は特定の処理に特化した専用プロセッサであるが、これらに限られず任意のプロセッサとすることができる。
相分類部14は、複数の組織写真での相を分類する。相分類部14が実行する処理の詳細については後述する。
定量値算出部15は、相分類部14によって分類された相の定量値を算出する。定量値及び定量値算出部15が実行する処理の詳細については後述する。
偏差算出部16は、定量値算出部15によって算出される定量値の偏差を算出する。偏差算出部16が実行する処理の詳細については後述する。
視野数合否判定部19は、偏差算出部16によって算出された偏差に基づいて、複数の組織写真の視野数について合否を判定する。視野数合否判定部19が実行する処理の詳細については後述する。
図2は、本実施形態に係る組織写真評価装置10が実行する組織写真評価方法の処理を示すフローチャートである。概要として、組織写真評価方法は、金属材料の少なくとも2以上の視野について所定の撮影倍率で撮影された複数の組織写真を取得する入力工程と、複数の組織写真での相を分類する相分類工程と、分類された相の定量値を算出する定量値算出工程と、定量値の偏差を算出する偏差算出工程と、偏差に基づいて複数の組織写真の視野数について合否を判定する視野数合否判定工程と、合否を出力する出力工程と、をこの順で行う。ここで、組織写真評価方法は、視野数合否判定工程において、合格しなかった場合(すなわち不合格の場合)に、入力工程で取得される組織写真を追加した上で、これらの工程を再度実行する。
入力工程は、入力部11が金属材料の少なくとも2以上の視野について所定の撮影倍率で撮影された複数の組織写真を取得する工程である(ステップS11)。
相分類工程は、相分類部14が複数の組織写真での相を分類する工程である(ステップS12)。
恒等特徴値は、組織写真の輝度値そのものを示す特徴値である。
Mean特徴値は、組織写真の所定の範囲における輝度値の平均値を示す特徴値である。すなわち、Mean特徴値は、組織写真の各相から所定の範囲「(画素数x)×(画素数y)」を取り出し、その中の輝度値を平均化したものである。「画素数x」及び「画素数y」は、同一のサイズでよく、異なるサイズでよい。また、「(画素数x)×(画素数y)」の領域が長方形である必要はなく、組織写真が球状の形状である場合、球状の領域にすることが好ましく、複数の画素数x、yについて算出してよい。「画素数x」及び「画素数y」の下限は、例えば組織写真に含まれるノイズよりも大きく、かつ金属組織の複数の相のうち、結晶粒径が小さい方の1/2未満の大きさが含まれる範囲とすることが好ましい。上限は、画素の範囲を大きくしすぎると、粒界の影響又は隣接する他相の影響を受けることがあるため、結晶粒径が大きい方の結晶粒径の1/2未満の大きさが含まれる範囲とすることが好ましい。
Gausian特徴値は、組織写真の所定の範囲において、中心に近いほど重みを大きくした輝度値の平均値を示す特徴値である。すなわち、Gausian特徴値は、組織写真の各相から所定の範囲「(画素数x)×(画素数y)」を取り出し、中心の画素ほど重みを大きくした平均値を取り出したものである。「画素数x」及び「画素数y」は、同一のサイズでよく、異なるサイズでよい。また、「(画素数x)×(画素数y)」の領域が長方形である必要はなく、組織写真が球状の形状である場合、球状の領域にすることが好ましく、複数の画素数x、yについて算出してよい。「画素数x」及び「画素数y」の下限は、例えば組織写真に含まれるノイズよりも大きく、かつ金属組織の複数の相のうち、結晶粒径が小さい方の1/2未満の大きさが含まれる範囲とすることが好ましい。上限は、画素の範囲を大きくしすぎると、粒界の影響又は隣接する他相の影響を受けることがあるため、結晶粒径が大きい方の結晶粒径の1/2未満の大きさが含まれる範囲とすることが好ましい。
Median特徴値は、組織写真の所定の範囲における輝度値の中央値を示す特徴値である。すなわち、Median特徴値は、組織写真の各相から所定の範囲「(画素数x)×(画素数y)」を取り出し、その中の輝度値から中央値を取り出したものである。「画素数x」及び「画素数y」は、同一のサイズでよく、異なるサイズでよい。また、「(画素数x)×(画素数y)」の領域が長方形である必要はなく、組織写真が球状の形状である場合、球状の領域にすることが好ましく、複数の画素数x、yについて算出してよい。「画素数x」及び「画素数y」の下限は、例えば組織写真に含まれるノイズよりも大きく、かつ金属組織の複数の相のうち、結晶粒径が小さい方の1/2未満の大きさが含まれる範囲とすることが好ましい。上限は、画素の範囲を大きくしすぎると、粒界の影響又は隣接する他相の影響を受けることがあるため、結晶粒径が大きい方の結晶粒径の1/2未満の大きさが含まれる範囲とすることが好ましい。
Max特徴値は、組織写真の所定の範囲における輝度値の最大値を示す特徴値である。すなわち、Max特徴値は、組織写真の各相から所定の範囲「(画素数x)×(画素数y)」を取り出し、その中の輝度値から最大値を取り出したものである。「画素数x」及び「画素数y」は、同一のサイズでよく、異なるサイズでよい。また、「(画素数x)×(画素数y)」の領域が長方形である必要はなく、組織写真が球状の形状である場合、球状の領域にすることが好ましく、複数の画素数x、yについて算出してよい。「画素数x」及び「画素数y」の下限は、例えば組織写真に含まれるノイズよりも大きく、かつ金属組織の複数の相のうち、結晶粒径が小さい方の1/2未満の大きさが含まれる範囲とすることが好ましい。上限は、画素の範囲を大きくしすぎると、粒界の影響又は隣接する他相の影響を受けることがあるため、結晶粒径が大きい方の結晶粒径の1/2未満の大きさが含まれる範囲とすることが好ましい。
Min特徴値は、組織写真の所定の範囲における輝度値の最小値を示す特徴値である。すなわち、Min特徴値は、組織写真の各相から所定の範囲「(画素数x)×(画素数y)」を取り出し、その中の輝度値から最小値を取り出したものである。「画素数x」及び「画素数y」は、同一のサイズでよく、異なるサイズでよい。また、「(画素数x)×(画素数y)」の領域が長方形である必要はなく、組織写真が球状の形状である場合、球状の領域にすることが好ましく、複数の画素数x、yについて算出してよい。「画素数x」及び「画素数y」の下限は、例えば組織写真に含まれるノイズよりも大きく、かつ金属組織の複数の相のうち、結晶粒径が小さい方の1/2未満の大きさが含まれる範囲とすることが好ましい。上限は、画素の範囲を大きくしすぎると、粒界の影響又は隣接する他相の影響を受けることがあるため、結晶粒径が大きい方の結晶粒径の1/2未満の大きさが含まれる範囲とすることが好ましい。
Derivative特徴値は、組織写真の各相から所定の範囲「(画素数x)×(画素数y)」を取り出し、そのうちの端の画素に対してx方向及びy方向の微分値を計算したものである。「画素数x」及び「画素数y」は、同一のサイズでよく、異なるサイズでよい。また、「(画素数x)×(画素数y)」の領域が長方形である必要はなく、組織写真が球状の形状である場合、球状の領域にすることが好ましく、複数の画素数x、yについて算出してよい。「画素数x」及び「画素数y」の下限は、例えば組織写真に含まれるノイズよりも大きく、かつ金属組織の複数の相のうち、結晶粒径が小さい方の1/2未満の大きさが含まれる範囲とすることが好ましい。上限は、画素の範囲を大きくしすぎると、粒界の影響又は隣接する他相の影響を受けることがあるため、結晶粒径が大きい方の結晶粒径の1/2未満の大きさが含まれる範囲とすることが好ましい。
Derivative加算特徴値は、上記のDerivative特徴値に対して、上記のMean特徴値、Gaussian特徴値、Median特徴値、Max特徴値及びMin特徴値を演算することにより、Derivative特徴値を畳み込んだものである。「画素数x」及び「画素数y」は、同一のサイズでよく、異なるサイズでよい。また、「(画素数x)×(画素数y)」の領域が長方形である必要はなく、組織写真が球状の形状である場合、球状の領域にすることが好ましく、複数の画素数x、yについて算出してよい。「画素数x」及び「画素数y」の下限は、例えば組織写真に含まれるノイズよりも大きく、かつ金属組織の複数の相のうち、結晶粒径が小さい方の1/2未満の大きさが含まれる範囲とすることが好ましい。上限は、画素の範囲を大きくしすぎると、粒界の影響又は隣接する他相の影響を受けることがあるため、結晶粒径が大きい方の結晶粒径の1/2未満の大きさが含まれる範囲とすることが好ましい。
定量値算出工程は、定量値算出部15が相分類部14によって分類された相の定量値を算出する工程である。定量値として、例えば以下の(1)~(6)の少なくとも1つが算出される。
面積率は、各組織写真において、特定した相の各結晶粒の面積と組織写真全体の面積の比を求める。各結晶粒の面積率は下式に従い算出される。
楕円体サイズは、各組織写真において、特定した相の各結晶粒の形状を楕円近似することで算出される。楕円体サイズは、近似した楕円体の長径、短径及びアスペクト比の少なくとも1つである。また特定した相について、各結晶粒の楕円体サイズの平均値を算出することで、組織写真一枚当たりの特定した相の平均の楕円体サイズが算出される。
各組織写真において、特定した相の各結晶粒の界面から直線を描いた後、その直線距離が最大となるフェレー径が算出される。また、各結晶粒で算出したフェレー径の平均値を算出することで、組織写真一枚当たりの特定した相の平均のフェレー径が算出される。
各組織写真において、特定した相の各結晶粒の面積を求め、その面積の平方根を取ることで、結晶粒の平均径が算出される。また、特定した相について、各結晶粒で算出した平均径から平均値を算出することで、組織写真一枚当たりの特定した相の平均の平均径が算出される。
各組織写真において、特定した相の各結晶粒の面積と周長を求めることで、各結晶粒の真円度が下式に従い算出される。
各組織写真において、特定した相の結晶粒の数を数え、結晶粒の数を組織写真全体の面積で割ることにより、組織写真一枚当たりの数密度が算出される。
偏差算出工程(ステップS14)では、視野ごとに偏差が算出される。偏差算出部16は、特定した相について、全ての視野の組織写真の定量値iについて、平均値Niを算出する。また、偏差算出部16は、特定した相について、視野jの組織写真の定量値iについて、平均値μijを算出する。偏差算出部16は、視野jの組織写真の定量値iの平均値μijを、全ての視野の組織写真の定量値iの平均値Niで割って、視野jの規格化された定量値iである(μij/Ni)を算出する。さらに、偏差算出部16は、定量値iの偏差の平均値を算出する。偏差の平均値は、「それぞれの規格化された定量値iより1を引いた値の絶対値」の和を視野数(組織写真の枚数)で割ることにより算出され、下式で示される。
視野数合否判定工程(ステップS15)は、視野数合否判定部19が定量値iの偏差に基づいて組織写真の視野数の合否を判断する工程である。視野数合否判定部19は、まず偏差算出部16が算出した偏差の平均値Siに基づいて組織を適切に評価可能な視野数(組織写真の枚数)であるかどうか(合否)を判断する。例えば視野数合否判定部19は、各定量値の偏差の平均値Siがすべて閾値以下であるとき、十分な視野数であるため合格と判定し(ステップS16のYes)、組織写真の追加の撮影を行わない。閾値は一例として0.1であるが、特定の値に限定されず、例えば対象とする金属の種類などに応じて設定されてよい。例えば視野数合否判定部19は、各定量値の偏差の平均値Siが1つでも閾値より大きいと、各定量値のずれが大きく、定量値と材料特性との関係を正確に把握できなくなるため、不合格と判定する(ステップS16のNo)。不合格と判定する場合に、視野数合否判定部19は、入力工程で取得される組織写真を追加した上で、処理を入力工程(ステップS11)に戻して、一連の処理を再度実行させる。
視野数合否判定部19が合格と判定した場合に(ステップS16のYes)、出力工程が実行される(ステップS17)。出力工程は、出力部12が視野数の合否を出力する工程である。ここで、図2のフローチャートの例において、合格の場合にだけ出力工程が実行されるが、所定回数の不合格の後にも出力工程が実行されてよい。例えばステップS16からステップS11に戻る処理が所定回数(一例として5回)繰り返された後に、視野数合否判定部19が不合格と判定した場合には、不合格であることを出力する出力工程が実行されてよい。
図3は、第2実施形態に係る組織写真評価装置10を備える組織写真評価システム1のブロック図である。本実施形態に係る組織写真評価装置10は、組織写真評価を行うにあたり、相の定量値に基づく統計値を出力する。このような統計値が出力されることによって、組織写真評価装置10の外部において、組織写真評価装置10によって実行された評価についての検証又は二次的な合否判断などが可能になる。本実施形態に係る組織写真評価装置10は、第1実施形態に係る組織写真評価装置10の構成要素を含み、さらに統計値算出部20を備える。重複説明を回避するため、第1実施形態と異なる構成が以下に説明される。
統計値算出部20は、相の定量値に基づいて統計値を算出する。本実施形態において、統計値算出部20は、入力部11に入力された複数の組織写真の全ての定量値に基づいて統計値を算出する。統計値は例えば平均値、中央値、標準偏差などを含んでよいが、特定のものに限定されない。本実施形態において、統計値算出部20は、視野数合否判定部19が合格と判定した場合に統計値を算出する。ただし、このような場合に限定されず、統計値算出部20は、所定回数の不合格の後に統計値を算出してよい。また、出力部12は、統計値算出部20によって算出された統計値とともに合否を出力してよい。
図4は、本実施形態に係る組織写真評価装置10が実行する組織写真評価方法の処理を示すフローチャートである。概要として、組織写真評価方法は、金属材料の少なくとも2以上の視野について所定の撮影倍率で撮影された複数の組織写真を取得する入力工程と、複数の組織写真での相を分類する相分類工程と、分類された相の定量値を算出する定量値算出工程と、定量値の偏差を算出する偏差算出工程と、偏差に基づいて複数の組織写真の視野数について合否を判定する視野数合否判定工程と、相の定量値に基づいて統計値を算出する統計値算出工程と、統計値を出力する出力工程と、をこの順で行う。ここで、組織写真評価方法は、視野数合否判定工程において不合格と判定された場合に、入力工程で取得される組織写真を追加した上で、これらの工程を再度実行する。
視野数合否判定工程で合格と判定された場合に(ステップS26のYes)、統計値算出工程(ステップS27)が実行される。本実施形態の統計値算出工程において、統計値算出部20は、定量値算出工程で算出された各定量値の全ての視野についての平均値及び標準偏差を算出する。
図5は、第3実施形態に係る組織写真評価装置10を備える組織写真評価システム1のブロック図である。本実施形態に係る組織写真評価装置10は、視野数を評価する前に代表撮影倍率を決定する。本実施形態に係る組織写真評価装置10は、第2実施形態に係る組織写真評価装置10の構成要素を含み、さらに倍率決定部17を備える。重複説明を回避するため、第1実施形態、第2実施形態と異なる構成が以下に説明される。
倍率決定部17は、定量値算出部15によって算出された定量値に基づいて代表撮影倍率を決定する。倍率決定部17が実行する処理の詳細については後述する。
図6は、本実施形態に係る組織写真評価装置10が実行する組織写真評価方法の処理を示すフローチャートである。概要として、組織写真評価方法は、金属材料の少なくとも2以上の視野について2以上の撮影倍率で撮影された複数の組織写真を取得する入力工程と、複数の組織写真での相を分類する相分類工程と、分類された相の定量値を算出する定量値算出工程と、定量値に基づいて代表撮影倍率を決定する倍率決定工程と、代表撮影倍率に該当する複数の組織写真について、定量値の偏差を算出する偏差算出工程(第2偏差算出工程)と、偏差に基づいて複数の組織写真の視野数について合否を判定する視野数合否判定工程と、相の定量値に基づいて統計値を算出する統計値算出工程と、統計値を出力する出力工程と、を行う。ここで、組織写真評価方法は、視野数合否判定工程において不合格と判定された場合に、入力工程で取得される組織写真を追加した上で、これらの工程を再度実行する。
倍率決定工程は、倍率決定部17が定量値算出部15によって算出された定量値に基づいて代表撮影倍率を決定する工程である(ステップS34)。
ここで、条件Aと条件Bの両方を満たす撮影倍率が2水準以上存在することがあり得る。このような代表撮影倍率の候補が複数ある場合に(ステップS35のYes)、本実施形態において第1偏差算出工程が実行される(ステップS36)。第1偏差算出工程は、偏差算出部16が定量値算出部15によって求められた定量値の偏差を算出する工程である。ここで、撮影倍率ごとの定量値の偏差を算出する第1偏差算出工程と区別するために、第1実施形態及び第2実施形態のような視野ごとの偏差算出工程は第2偏差算出工程と称される。
以下、本開示の効果を実施例に基づいて具体的に説明するが、本開示はこれら実施例に限定されるものではない。実施例では、上記の第1実施形態に係る組織写真評価装置10による組織写真評価方法が行われた。
10 組織写真評価装置
11 入力部
12 出力部
13 演算部
14 相分類部
15 定量値算出部
16 偏差算出部
17 倍率決定部
19 視野数合否判定部
20 統計値算出部
30 撮影装置
Claims (13)
- 金属材料の少なくとも2以上の視野について所定の撮影倍率で撮影された複数の組織写真を取得する入力工程と、
前記複数の組織写真での相を分類する相分類工程と、
分類された前記相の定量値を算出する定量値算出工程と、
前記定量値の偏差を算出する偏差算出工程と、
前記偏差に基づいて前記複数の組織写真の視野数について合否を判定する視野数合否判定工程と、
前記合否を出力する出力工程と、
を備える、組織写真評価方法。 - 金属材料の少なくとも2以上の視野について所定の撮影倍率で撮影された複数の組織写真を取得する入力工程と、
前記複数の組織写真での相を分類する相分類工程と、
分類された前記相の定量値を算出する定量値算出工程と、
前記定量値の偏差を算出する偏差算出工程と、
前記偏差に基づいて前記複数の組織写真の視野数について合否を判定する視野数合否判定工程と、
前記相の定量値に基づいて統計値を算出する統計値算出工程と、
前記統計値を出力する出力工程と、
を備える、組織写真評価方法。 - 金属材料の少なくとも2以上の視野について2以上の撮影倍率で撮影された複数の組織写真を取得する入力工程と、
前記複数の組織写真での相を分類する相分類工程と、
分類された前記相の定量値を算出する定量値算出工程と、
前記定量値に基づいて代表撮影倍率を決定する倍率決定工程と、
前記代表撮影倍率に該当する前記複数の組織写真について、前記定量値の偏差を算出する偏差算出工程と、
前記偏差に基づいて前記複数の組織写真の視野数について合否を判定する視野数合否判定工程と、
前記相の定量値に基づいて統計値を算出する統計値算出工程と、
前記統計値を出力する出力工程と、
を備える、組織写真評価方法。 - 前記出力工程は、前記統計値とともに前記合否を出力する、請求項2又は3に記載の組織写真評価方法。
- 前記定量値は、面積率、楕円体サイズ、フェレー径、平均径、真円度及び数密度の少なくとも1つである、請求項1から3のいずれか一項に記載の組織写真評価方法。
- 金属材料の少なくとも2以上の視野について所定の撮影倍率で撮影された複数の組織写真を取得する入力部と、
前記複数の組織写真での相を分類する相分類部と、
分類された前記相の定量値を算出する定量値算出部と、
前記定量値の偏差を算出する偏差算出部と、
前記偏差に基づいて前記複数の組織写真の視野数について合否を判定する視野数合否判定部と、
前記合否を出力する出力部と、
を備える、組織写真評価装置。 - 金属材料の少なくとも2以上の視野について所定の撮影倍率で撮影された複数の組織写真を取得する入力部と、
前記複数の組織写真での相を分類する相分類部と、
分類された前記相の定量値を算出する定量値算出部と、
前記定量値の偏差を算出する偏差算出部と、
前記偏差に基づいて前記複数の組織写真の視野数について合否を判定する視野数合否判定部と、
前記相の定量値に基づいて統計値を算出する統計値算出部と、
前記統計値を出力する出力部と、
を備える、組織写真評価装置。 - 金属材料の少なくとも2以上の視野について2以上の撮影倍率で撮影された複数の組織写真を取得する入力部と、
前記複数の組織写真での相を分類する相分類部と、
分類された前記相の定量値を算出する定量値算出部と、
前記定量値に基づいて代表撮影倍率を決定する倍率決定部と、
前記代表撮影倍率に該当する前記複数の組織写真について、前記定量値の偏差を算出する偏差算出部と、
前記偏差に基づいて前記複数の組織写真の視野数について合否を判定する視野数合否判定部と、
前記相の定量値に基づいて統計値を算出する統計値算出部と、
前記統計値を出力する出力部と、
を備える、組織写真評価装置。 - 請求項6から8のいずれか一項に記載の組織写真評価装置によって取得される前記複数の組織写真を撮影する、撮影装置。
- 前記撮影装置は光学顕微鏡又は走査型電子顕微鏡である、請求項9に記載の撮影装置。
- コンピュータを、
金属材料の少なくとも2以上の視野について所定の撮影倍率で撮影された複数の組織写真を取得する入力部と、
前記複数の組織写真での相を分類する相分類部と、
分類された前記相の定量値を算出する定量値算出部と、
前記定量値の偏差を算出する偏差算出部と、
前記偏差に基づいて前記複数の組織写真の視野数について合否を判定する視野数合否判定部と、
前記合否を出力する出力部と、
として機能させるための、プログラム。 - コンピュータを、
金属材料の少なくとも2以上の視野について所定の撮影倍率で撮影された複数の組織写真を取得する入力部と、
前記複数の組織写真での相を分類する相分類部と、
分類された前記相の定量値を算出する定量値算出部と、
前記定量値の偏差を算出する偏差算出部と、
前記偏差に基づいて前記複数の組織写真の視野数について合否を判定する視野数合否判定部と、
前記相の定量値に基づいて統計値を算出する統計値算出部と、
前記統計値を出力する出力部と、
として機能させるための、プログラム。 - コンピュータを、
金属材料の少なくとも2以上の視野について2以上の撮影倍率で撮影された複数の組織写真を取得する入力部と、
前記複数の組織写真での相を分類する相分類部と、
分類された前記相の定量値を算出する定量値算出部と、
前記定量値に基づいて代表撮影倍率を決定する倍率決定部と、
前記代表撮影倍率に該当する前記複数の組織写真について、前記定量値の偏差を算出する偏差算出部と、
前記偏差に基づいて前記複数の組織写真の視野数について合否を判定する視野数合否判定部と、
前記相の定量値に基づいて統計値を算出する統計値算出部と、
前記統計値を出力する出力部と、
として機能させるための、プログラム。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020247029655A KR20240142547A (ko) | 2022-05-23 | 2023-03-30 | 조직 사진 평가 방법, 조직 사진 평가 장치, 촬영 장치 및 프로그램 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2022-084131 | 2022-05-23 | ||
JP2022084131A JP2023172383A (ja) | 2022-05-23 | 2022-05-23 | 組織写真評価方法、組織写真評価装置、撮影装置及びプログラム |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023228572A1 true WO2023228572A1 (ja) | 2023-11-30 |
Family
ID=88919015
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2023/013410 WO2023228572A1 (ja) | 2022-05-23 | 2023-03-30 | 組織写真評価方法、組織写真評価装置、撮影装置及びプログラム |
Country Status (3)
Country | Link |
---|---|
JP (1) | JP2023172383A (ja) |
KR (1) | KR20240142547A (ja) |
WO (1) | WO2023228572A1 (ja) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009287941A (ja) * | 2008-05-27 | 2009-12-10 | Nippon Steel Corp | 無機多孔体の観察試料および当該観察試料の作製方法 |
JP2019012037A (ja) * | 2017-06-30 | 2019-01-24 | Jfeスチール株式会社 | 材料特性推定装置及び材料特性推定方法 |
WO2022059186A1 (ja) * | 2020-09-18 | 2022-03-24 | 株式会社東芝 | 粒度推定装置、粒度推定方法、粒度推定プログラム、粒度推定システム。 |
-
2022
- 2022-05-23 JP JP2022084131A patent/JP2023172383A/ja active Pending
-
2023
- 2023-03-30 WO PCT/JP2023/013410 patent/WO2023228572A1/ja active Application Filing
- 2023-03-30 KR KR1020247029655A patent/KR20240142547A/ko unknown
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009287941A (ja) * | 2008-05-27 | 2009-12-10 | Nippon Steel Corp | 無機多孔体の観察試料および当該観察試料の作製方法 |
JP2019012037A (ja) * | 2017-06-30 | 2019-01-24 | Jfeスチール株式会社 | 材料特性推定装置及び材料特性推定方法 |
WO2022059186A1 (ja) * | 2020-09-18 | 2022-03-24 | 株式会社東芝 | 粒度推定装置、粒度推定方法、粒度推定プログラム、粒度推定システム。 |
Also Published As
Publication number | Publication date |
---|---|
KR20240142547A (ko) | 2024-09-30 |
JP2023172383A (ja) | 2023-12-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP7422825B2 (ja) | 顕微鏡スライド画像のための焦点重み付き機械学習分類器誤り予測 | |
JP6992475B2 (ja) | 情報処理装置、識別システム、設定方法及びプログラム | |
US7979212B2 (en) | Method and system for morphology based mitosis identification and classification of digital images | |
JP4420821B2 (ja) | 組織学的アセスメント | |
JP5156631B2 (ja) | 画像領域の自動選定 | |
CN113963042B (zh) | 基于图像处理的金属零件缺陷程度评估方法 | |
WO2021153633A1 (ja) | 金属組織の相の分類方法、金属組織の相の分類装置、金属組織の相の学習方法、金属組織の相の学習装置、金属材料の材料特性予測方法および金属材料の材料特性予測装置 | |
JP2005310123A (ja) | 特定シーンの画像を選別する装置、プログラムおよびプログラムを記録した記録媒体 | |
EP1563457A2 (en) | Image analysis | |
JP7054436B2 (ja) | 検出システム、情報処理装置、評価方法及びプログラム | |
JP2006514356A (ja) | 画像解析による有糸分裂活動の評価方法 | |
WO2005076197A2 (en) | Method and system for morphology based mitosis identification and classification of digital images | |
Lahrmann et al. | Semantic focusing allows fully automated single-layer slide scanning of cervical cytology slides | |
US20230206416A1 (en) | Computer-implemented method for quality control of a digital image of a sample | |
CN113176270B (zh) | 一种调光方法、装置及设备 | |
Iskakov et al. | A framework for the systematic design of segmentation workflows | |
JP2001188906A (ja) | 画像自動分類方法及び画像自動分類装置 | |
WO2021199937A1 (ja) | 金属組織の撮影条件決定方法、金属組織の撮影方法、金属組織の相分類方法、金属組織の撮影条件決定装置、金属組織の撮影装置、金属組織の相分類装置、金属材料の材料特性予測方法および金属材料の材料特性予測装置 | |
WO2023228572A1 (ja) | 組織写真評価方法、組織写真評価装置、撮影装置及びプログラム | |
JP2006292615A (ja) | 外観検査装置、外観検査方法、コンピュータを外観検査装置として機能させるためのプログラムおよび記録媒体 | |
WO2023228571A1 (ja) | 代表組織写真決定方法、代表組織写真決定装置、撮影装置及びプログラム | |
JP2004246618A (ja) | パターン認識における照合に用いられる画像の生成ならびに同画像を用いたパターン認識のための方法、装置、およびプログラム | |
Nandy et al. | Automatic nuclei segmentation and spatial FISH analysis for cancer detection | |
JP4981112B2 (ja) | 組織学的アセスメント | |
CN115290661B (zh) | 基于计算机视觉的橡胶圈缺陷识别方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 23811451 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 20247029655 Country of ref document: KR Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 1020247029655 Country of ref document: KR |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2023811451 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2023811451 Country of ref document: EP Effective date: 20240919 |